WO2022213465A1 - Neural network-based image recognition method and apparatus, electronic device, and medium - Google Patents

Abstract

The present application relates to the technical field of image detection and discloses a neural network-based image recognition method, comprising: constructing a distance perception loss function by using a Dice loss function and a Tversky loss function; using the distance perception loss function, a pre-constructed image detection algorithm, and a neural network model framework to construct a target object detection model to be trained, the neural network model framework comprising an input layer, a hidden layer, and an output layer; obtaining a target object image sample set, and using the target object image sample set to train the target object detection model to be trained, to obtain a trained target object detection model; obtaining a CT image to be detected, and quantizing and denoising said CT image to obtain denoised image data; and performing image recognition on the de-noised image data by using the target object detection model to obtain a target object recognition result. The present application further provides an image recognition apparatus, a device, and a computer-readable storage medium. The objective of the present application is to improve the accuracy of target object image recognition.

Description

基于神经网络的图像识别方法、装置、电子设备及介质Image recognition method, device, electronic device and medium based on neural network

本申请要求于2021年4月8日提交中国专利局、申请号为CN202110378729.2、名称为“基于神经网络的图像识别方法、装置、电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of the Chinese patent application with the application number CN202110378729.2 and titled "Neural Network-Based Image Recognition Method, Apparatus, Electronic Equipment" filed with the Chinese Patent Office on April 8, 2021, the entire contents of which are approved by Reference is incorporated in this application.

技术领域technical field

本申请涉及图像检测技术领域，尤其涉及一种基于神经网络的图像识别方法、装置、电子设备及计算机可读存储介质。The present application relates to the technical field of image detection, and in particular, to a neural network-based image recognition method, apparatus, electronic device, and computer-readable storage medium.

背景技术Background technique

随着科技的发展，人们对于人体、自然的探索逐渐加深，使得人们对于图像解读的精度也越来越严格，例如为保证更加准确高效的识别出医学图像中的肿瘤，现有技术中可以通过卷积神经网络分析CT图像，判断肿瘤大小、类别。但发明人发现目前常用的图像检测算法中通常使用焦点损失函数，这种方法会对小肿瘤及低对比度的肿瘤忽视，即不容易检测到小肿瘤，存在检测不精确的问题。因此，增加图像识别的精确度成为亟待解决的问题。With the development of science and technology, people's exploration of the human body and nature has gradually deepened, making people's accuracy of image interpretation more and more strict. For example, in order to ensure more accurate and efficient identification of tumors in medical images, the existing technology can be Convolutional neural networks analyze CT images to determine tumor size and type. However, the inventors found that the focal loss function is usually used in the commonly used image detection algorithms. This method ignores small tumors and tumors with low contrast, that is, it is not easy to detect small tumors, and there is a problem of inaccurate detection. Therefore, increasing the accuracy of image recognition becomes an urgent problem to be solved.

发明内容SUMMARY OF THE INVENTION

本申请提供的一种基于神经网络的图像识别方法，包括：A neural network-based image recognition method provided by this application includes:

利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数；Use the pre-built Dice loss function and Tversky loss function to build a distance-aware loss function;

利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层；Use the distance perception loss function, the pre-built image detection algorithm and the neural network model framework to construct the target object detection model to be trained, and the neural network model framework includes an input layer, a hidden layer and an output layer;

获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型；Obtaining a target object image sample set, and using the target object image sample set to train the target object detection model to be trained, to obtain a trained target object detection model;

获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据；Obtaining a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected to obtain denoised image data;

利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。Image recognition is performed on the denoised image data by using the target detection model to obtain a target recognition result.

本申请还提供一种基于神经网络的图像识别装置，所述装置包括：The present application also provides an image recognition device based on a neural network, the device comprising:

模型构建模块，用于利用预构建的Dice损失函数及Tversky损失函数构建距离感知损失函数，及利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架，构建待训练目标物检测模型，所述神经网络模型框架包括数据输入层、隐藏层、输出层；The model building module is used to construct a distance-aware loss function by using the pre-built Dice loss function and the Tversky loss function, and use the distance-aware loss function, the pre-built image detection algorithm and the neural network model framework to construct the target object detection to be trained. model, the neural network model framework includes a data input layer, a hidden layer, and an output layer;

模型训练模块，用于获取预构建的目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型；a model training module, configured to obtain a pre-built target image sample set, and use the target image sample set to train the target detection model to be trained to obtain a trained target detection model;

目标物预测模块，用于获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据，及利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。The target object prediction module is used to obtain the CT image to be detected, perform quantization and denoising processing on the CT image to be detected, obtain denoised image data, and use the target detection model to perform the denoising image data on the denoised image data. Image recognition to obtain target recognition results.

本申请还提供一种电子设备，所述电子设备包括：The present application also provides an electronic device, the electronic device comprising:

至少一个处理器；以及，at least one processor; and,

与所述至少一个处理器通信连接的存储器；其中，a memory communicatively coupled to the at least one processor; wherein,

所述存储器存储有可被所述至少一个处理器执行的计算机程序指令，所述计算机程序指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如下步骤：The memory stores computer program instructions executable by the at least one processor, the computer program instructions being executed by the at least one processor to enable the at least one processor to perform the steps of:

利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数；Use the pre-built Dice loss function and Tversky loss function to build a distance-aware loss function;

利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层；Use the distance perception loss function, the pre-built image detection algorithm and the neural network model framework to construct the target object detection model to be trained, and the neural network model framework includes an input layer, a hidden layer and an output layer;

获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模 型，得到训练完成的目标物检测模型；Obtaining a target object image sample set, and using the target object image sample set to train the target object detection model to be trained to obtain a trained target object detection model;

获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据；Obtaining a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected to obtain denoised image data;

利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。Image recognition is performed on the denoised image data by using the target detection model to obtain a target recognition result.

本申请还提供一种计算机可读存储介质，包括存储数据区和存储程序区，存储数据区存储创建的数据，存储程序区存储有计算机程序；其中，所述计算机程序被处理器执行时实现如下步骤：The present application also provides a computer-readable storage medium, including a storage data area and a storage program area, the storage data area stores created data, and the storage program area stores a computer program; wherein, the computer program is implemented as follows when executed by a processor step:

利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数；Use the pre-built Dice loss function and Tversky loss function to build a distance-aware loss function;

利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层；Use the distance perception loss function, the pre-built image detection algorithm and the neural network model framework to construct the target object detection model to be trained, and the neural network model framework includes an input layer, a hidden layer and an output layer;

获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型；Obtaining a target object image sample set, and using the target object image sample set to train the target object detection model to be trained, to obtain a trained target object detection model;

获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据；Obtaining a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected to obtain denoised image data;

利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。Image recognition is performed on the denoised image data by using the target detection model to obtain a target recognition result.

附图说明Description of drawings

图1为本申请一实施例提供的基于神经网络的图像识别方法的流程示意图；1 is a schematic flowchart of an image recognition method based on a neural network provided by an embodiment of the present application;

图2为图1提供的基于神经网络的图像识别方法中的一个步骤的详细实施流程图；Fig. 2 is a detailed implementation flow chart of a step in the neural network-based image recognition method provided in Fig. 1;

图3为图1提供的基于神经网络的图像识别方法中的另一个步骤的详细实施流程图；3 is a detailed implementation flow chart of another step in the neural network-based image recognition method provided in FIG. 1;

图4为本申请一实施例提供的基于神经网络的图像识别装置的模块示意图；4 is a schematic block diagram of an image recognition device based on a neural network provided by an embodiment of the present application;

图5为本申请一实施例提供的基于神经网络的图像识别方法的电子设备的内部结构示意图。FIG. 5 is a schematic diagram of an internal structure of an electronic device according to an image recognition method based on a neural network provided by an embodiment of the present application.

本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。The realization, functional characteristics and advantages of the purpose of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments.

具体实施方式Detailed ways

应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

本申请实施例提供一种基于神经网络的图像识别方法。所述基于神经网络的图像识别方法的执行主体包括但不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之，所述基于神经网络的图像识别方法可以由安装在终端设备或服务端设备的软件或硬件来执行，所述软件可以是区块链平台。所述服务端包括但不限于：单台服务器、服务器集群、云端服务器或云端服务器集群等。The embodiment of the present application provides an image recognition method based on a neural network. The execution body of the neural network-based image recognition method includes, but is not limited to, at least one of electronic devices that can be configured to execute the method provided by the embodiments of the present application, such as a server and a terminal. In other words, the neural network-based image recognition method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.

参照图1所示，为本申请一实施例提供的基于神经网络的图像识别方法的流程示意图。在本实施例中，所述基于神经网络的图像识别方法包括：Referring to FIG. 1 , it is a schematic flowchart of an image recognition method based on a neural network provided by an embodiment of the present application. In this embodiment, the neural network-based image recognition method includes:

S1、利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数。S1. Use the pre-built Dice loss function and Tversky loss function to construct a distance-aware loss function.

具体的，所述Dice损失函数及所述Tversky损失函数是为图像检测算法进行回归计算的损失函数。Specifically, the Dice loss function and the Tversky loss function are loss functions for performing regression calculation for the image detection algorithm.

其中，所述Dice损失算法可以分析目标物图像内每个区域中是否含有目标物的特征，但是常常忽视较小特征，造成目标物遗漏；所述Tversky损失函数对于模型的训练过程会出现过度训练的情况，对于图像检测过程中容易出现过拟合现象，导致出现将其他东西识别为目标物等假阳性现象。Among them, the Dice loss algorithm can analyze whether each area in the target image contains the features of the target, but often ignore the smaller features, resulting in the omission of the target; the Tversky loss function will cause overtraining in the training process of the model In the case of image detection, overfitting is easy to occur, resulting in false positives such as recognizing other things as targets.

本申请其中一个实施例中，所述目标物为肿瘤。In one embodiment of the present application, the target is a tumor.

本申请实施例中，将所述Dice损失函数及所述Tversky损失函数进行权重分配，构建所述距离感知损失函数，增加目标物图像识别的准确性。In the embodiment of the present application, the Dice loss function and the Tversky loss function are weighted to construct the distance perception loss function to increase the accuracy of target image recognition.

详细地，本申请实施例中，所述利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数，包括：In detail, in the embodiment of the present application, the distance-aware loss function constructed by using the pre-built Dice loss function and the Tversky loss function includes:

对所述Dice损失函数和所述Tversky损失函数进行加权求和，得到所述距离感知损失函数，其中，所述距离感知损失函数为：Weighted summation is performed on the Dice loss function and the Tversky loss function to obtain the distance-aware loss function, where the distance-aware loss function is:

L＝L _Tversky+λ×L _dis L=L _Tversky +λ×L _dis

其中，L _Tversky为所述Tversky损失函数，L _dis为所述Dice损失函数，p _k和y _k分别表示输入的CT图像中每个分割区域内出现目标物的概率值和对应的目标物的标注，λ ₁及λ ₂分别为召唤率∑p _k(1-y _k)及精确度∑(1-p _k)y _k的两个参数，d _k表示每个分割区域到标注为最近的存在目标物的分割区域的距离，Ω表示所述输入的CT图像中所有像素点的个数，λ为加权系数。 Among them, L _Tversky is the Tversky loss function, L _dis is the Dice loss function, p _k and y _k respectively represent the probability value of the target object appearing in each segmented area in the input CT image and the corresponding label of the target object , λ ₁ and λ ₂ are the two parameters of the summoning rate ∑p _k (1-y _k ) and the accuracy ∑ (1-p _k )y _k respectively, d _k represents each segmented area to the nearest existing target marked as is the distance of the segmented area of the object, Ω represents the number of all pixels in the input CT image, and λ is the weighting coefficient.

本申请实施例中加权系数λ，可以通过下述训练过程中输入层与隐藏层之间权重分析来得到，此处不加以赘述。The weighting coefficient λ in the embodiment of the present application can be obtained through the weight analysis between the input layer and the hidden layer in the following training process, and details are not described here.

S2、利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层。S2. Use the distance-aware loss function, a pre-built image detection algorithm, and a neural network model framework to construct a target object detection model to be trained. The neural network model framework includes an input layer, a hidden layer, and an output layer.

详细地，本申请实施例中，所述利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层，包括：In detail, in the embodiment of the present application, the target detection model to be trained is constructed by using the distance perception loss function, the pre-built image detection algorithm and the neural network model framework, and the neural network model framework includes an input layer and a hidden layer. and the output layer, including:

获取预构建的神经网络模型框架，所述神经网络模型框架包括输入层、隐藏层、输出层；Obtain a pre-built neural network model framework, where the neural network model framework includes an input layer, a hidden layer, and an output layer;

将所述距离感知函数和所述图像检测算法作为隐藏层激活函数添加至所述隐藏层；adding the distance-aware function and the image detection algorithm to the hidden layer as hidden layer activation functions;

获取预构建的Softmax函数；Get the pre-built Softmax function;

将所述Softmax函数作为输出层激活函数添加至所述输出层，得到所述待训练目标物检测模型。The Softmax function is added to the output layer as an output layer activation function to obtain the target object detection model to be trained.

具体的，本申请实施例中，所述神经网络模型框架为TransForm模型框架，其中所述TransForm模型框架包括所述输入层、所述隐藏层、所述输出层，且输入层、隐藏层和输出层都是由多个神经元构成，激活神经元便可进行数据传输、运算、处理等操作。Specifically, in the embodiment of the present application, the neural network model framework is a TransForm model framework, wherein the TransForm model framework includes the input layer, the hidden layer, and the output layer, and the input layer, the hidden layer, and the output layer The layers are composed of multiple neurons, and the activation of neurons can perform operations such as data transmission, calculation, and processing.

具体的，所述输入层用于将数据进行权重配置，使得当不同数量级的特征值输入所述隐藏层时，不同数量级的特征值都能起到相同级别的作用。所述隐藏层包括由所述图像检测算法及所述距离感知函数组成的激活函数，用于对所述输入层输入的数据进行处理。Specifically, the input layer is used for weight configuration of the data, so that when eigenvalues of different orders of magnitude are input to the hidden layer, the eigenvalues of different orders of magnitude can play a role of the same level. The hidden layer includes an activation function composed of the image detection algorithm and the distance perception function, and is used for processing the data input by the input layer.

本申请实施例中，所述输出层对检测到的目标物进行分类，并得到各个分类结果对应的概率。In the embodiment of the present application, the output layer classifies the detected objects, and obtains the probability corresponding to each classification result.

本申请实施例利用所述距离感知损失函数及所述图像检测算法修改隐藏层的损失函数及运算函数，利用Softmax函数修改所述输出层的激活函数，得到所述待训练目标物检测模型。In this embodiment of the present application, the distance sensing loss function and the image detection algorithm are used to modify the loss function and operation function of the hidden layer, and the Softmax function is used to modify the activation function of the output layer to obtain the target object detection model to be trained.

S3、获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型。S3. Acquire a target object image sample set, and use the target object image sample set to train the target object detection model to be trained to obtain a trained target object detection model.

本申请实施例中所述目标物图像样本集中包括各种目标物或普通组织的CT图像、磁共振图像等医学图像及与所述医学图像对应的图像分析标签。The target object image sample set in the embodiment of the present application includes medical images such as CT images and magnetic resonance images of various targets or common tissues, and image analysis tags corresponding to the medical images.

详细地，如下图2所示，本申请实施例中，所述利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型，包括：In detail, as shown in FIG. 2 below, in this embodiment of the present application, the target object detection model to be trained is trained by using the target object image sample set, and the trained target object detection model is obtained, including:

S31、将所述目标物图像样本集导入所述待训练目标物检测模型的输入层中，利用所述输入层中权重配置函数对所述目标物图像样本集中各个目标物图像特征进行权重分配。S31. Import the target image sample set into the input layer of the target detection model to be trained, and use the weight allocation function in the input layer to perform weight distribution on each target image feature in the target image sample set.

本申请实施例中，所述权重配置函数是一种逆向参数调整函数，即通过训练过后的计算结果的准确性，改变数值输入比例，重新进行训练，直至计算结果接近标准答案的运算函数。In the embodiment of the present application, the weight configuration function is an inverse parameter adjustment function, that is, an operation function that changes the numerical input ratio according to the accuracy of the calculation result after training, and retrains until the calculation result is close to the standard answer.

S32、根据权重分配结果，对所述目标物图像特征进行权重计算，得到权重特征值，并将所述权重特征值导入所述隐藏层。S32. According to the weight distribution result, perform weight calculation on the image feature of the target object to obtain a weight feature value, and import the weight feature value into the hidden layer.

S33、通过所述权重特征值触发所述激活函数的激活条件，使得所述距离感知损失函数根据所述权重特征值进行损失运算，得到最小化损失值，判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值。S33. Trigger the activation condition of the activation function through the weight eigenvalue, so that the distance-aware loss function performs a loss operation according to the weight eigenvalue, obtains a minimized loss value, and judges whether the minimized loss value converges, When it is determined that the minimized loss value is converged, the final loss value is obtained.

本申请实施例中所述激活函数为分段函数，当所述权重特征值得数值小于预设标准值，函数不激活，运算结果为0，当所述权重特征值得数值大于或等于所述预设标准值，函数激活对所述权重特征值进行目标物检测。In this embodiment of the present application, the activation function is a piecewise function. When the value of the weight feature value is less than the preset standard value, the function is not activated, and the operation result is 0. When the value of the weight feature value is greater than or equal to the preset value Standard value, the function activates target detection on the weight feature value.

进一步，本申请实施例中，所述判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值，包括：Further, in the embodiment of the present application, the judging whether the minimized loss value converges, and when it is judged that the minimized loss value converges, obtains a final loss value, including:

对产生的多个所述最小化损失值依次进行二维映射，得到损失值波动图，对所述损失值波动图中图线进行求导计算，得到求导结果；当所述求导结果小于预构建的预设数值时，判定小于所述预设数值的求导结果对应最小化损失值达到收敛，得到所述最终损失值。Perform two-dimensional mapping on a plurality of the generated minimized loss values in turn to obtain a loss value fluctuation graph, and perform derivation calculation on the graph line in the loss value fluctuation graph to obtain a derivation result; when the derivation result is less than When the preset value is pre-built, it is determined that the derivation result smaller than the preset value corresponds to the minimized loss value to reach convergence, and the final loss value is obtained.

本申请实施例中，在训练过程中，每次利用新的样本进行一次训练，都会产生一个最小化损失值。随着训练样本的逐渐增多，所述最小化损失值会随着训练过程逐渐变小，利用所述最小化损失值使得所述图像检测算法的准确度逐渐增加，且所述最小化损失值的求导结果会逐渐减小，当所述求导结果未达到所述预设数值时，利用目标物图像样本继续对所述目标物检测模型进行再一次训练，直至所述求导结果达到所述预设数值，表明所述最小化损失值的下降趋势消失，所述最小化损失值达到收敛状态，训练完成。In the embodiment of the present application, in the training process, each time a new sample is used for training, a minimum loss value will be generated. With the increasing number of training samples, the minimization loss value will gradually decrease with the training process, and the minimization loss value is used to gradually increase the accuracy of the image detection algorithm, and the minimization loss value is The derivation result will gradually decrease. When the derivation result does not reach the preset value, continue to train the target detection model again by using the target object image sample until the derivation result reaches the The preset value indicates that the downward trend of the minimized loss value disappears, the minimized loss value reaches a convergent state, and the training is completed.

S34、根据所述最终损失值配置所述隐藏层中激活函数的图像检测算法，完成训练的过程，得到训练完成的所述目标物检测模型。S34. Configure the image detection algorithm of the activation function in the hidden layer according to the final loss value, complete the training process, and obtain the trained target detection model.

本申请实施例通过所述S31至所述S34的训练过程，得到所述目标物检测模型。In this embodiment of the present application, the target detection model is obtained through the training process from S31 to S34.

S4、获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据。S4. Acquire a CT image to be detected, and perform quantization and denoising processing on the CT image to be detected to obtain denoised image data.

详细地，本申请实施例中，所述获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据，包括：In detail, in the embodiment of the present application, the obtaining of the CT image to be detected, and performing quantization and denoising processing on the CT image to be detected, to obtain denoised image data, including:

对所述待检测CT图像中各像素进行区域划分，并将划分好的像素块进行向量化处理，得到量化图像数据；Perform regional division on each pixel in the CT image to be detected, and perform vectorization processing on the divided pixel blocks to obtain quantized image data;

利用预构建的高斯滤波器将所述量化图像数据进行二维邻域的高斯卷积运算，得到去噪图像数据。The quantized image data is subjected to a Gaussian convolution operation of a two-dimensional neighborhood by using a pre-built Gaussian filter to obtain denoised image data.

本申请实施例以预设像素大小，如2*2个像素为基本单位对所述待检测CT图像进行分割，得到多个像素快，并对所述像素快进行向量化处理，得到所述量化图像数据，通过预构建的高斯滤波器，对方形范围内量化图像数据，如3*3的矩阵块进行运算，利用得到的运算结果代表所述3*3矩阵的收缩值，通过所述高斯滤波器中的卷积器对相邻3*3矩阵进行运算直至所述待检测CT图像遍历完成，得到所述去噪图像数据。In this embodiment of the present application, the CT image to be detected is segmented with a preset pixel size, such as 2*2 pixels as the basic unit, to obtain a plurality of pixel blocks, and vectorization processing is performed on the pixel blocks to obtain the quantization process. Image data, through the pre-built Gaussian filter, perform operations on quantized image data in a square range, such as a 3*3 matrix block, use the obtained operation result to represent the shrinkage value of the 3*3 matrix, and pass the Gaussian filter. The convolver in the device operates on adjacent 3*3 matrices until the traversal of the CT image to be detected is completed, and the denoised image data is obtained.

S5、利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。S5. Perform image recognition on the denoised image data by using the target detection model to obtain a target recognition result.

详细地，本申请实施例中，如下图4所示，所述利用所述目标物检测模型对所述去噪图像数据进行图像检测，得到目标物检测结果，包括：In detail, in the embodiment of the present application, as shown in FIG. 4 below, the image detection is performed on the denoised image data by using the target detection model to obtain a target detection result, including:

S51、对所述去噪图像数据进行特征提取，得到特征值；S51, perform feature extraction on the denoised image data to obtain feature values;

S52、将所述特征值导入所述隐藏层进行图像识别，得到目标物识别结果；S52, importing the feature value into the hidden layer for image recognition to obtain a target object recognition result;

S53、将所述目标物识别结果导入所述输出层，使得所述输出层激活函数根据预构建 的目标物分类标签，判定所述待检测CT图像中存在有目标物的概率及对应类别的概率。S53. Import the target object recognition result into the output layer, so that the output layer activation function determines the probability of a target object and the probability of the corresponding category in the CT image to be detected according to the pre-built target object classification label .

本申请实施例中的目标物为肿瘤，将所述去噪图像数据导入所述目标物检测模型中，所述输入层中的特征提取网络对所述去噪图像数据进行特征提取，并将提取结果通过神经网络与各种肿瘤细胞进行匹配，判断所述待检测CT图像中是否存在肿瘤，当存在肿瘤时，通过所述输出层对肿瘤的特征进行纹理分析及类别预测，准确判断出肿瘤类别/或各个类别的概率。The target in the embodiment of the present application is a tumor, the denoised image data is imported into the target detection model, the feature extraction network in the input layer performs feature extraction on the denoised image data, and the extracted Results Match with various tumor cells through the neural network to determine whether there is a tumor in the CT image to be detected. When there is a tumor, texture analysis and category prediction are performed on the characteristics of the tumor through the output layer to accurately determine the tumor type. / or probabilities for individual classes.

本申请实施例通过对Dice损失函数和Tversky损失函数构建距离感知损失函数，由于Dice损失函数训练的模型容易导致忽视微小特征，而Tversky函数容易训练训练过度，导致将一些其他东西错认为目标物。将Dice损失函数和Tversky损失函数进行结合，有利于增加模型的训练效果。因此，通过Dice损失函数和Tversky损失函数构建距离感知损失函数，并利用该感知损失函数、图像检测算法及神经网络模型框架构建待训练目标物检测模型，并对该待训练目标物检测模型进行训练，可以更准确地进行目标物的识别，通过训练完成的目标物检测模型处理待检测的CT图像，能够准确地对待检测的CT图像进行目标物识别。因此，本申请实施例能够实现提高目标物图像识别的精确度的目的。In this embodiment of the present application, a distance-aware loss function is constructed for the Dice loss function and the Tversky loss function. Since the model trained by the Dice loss function tends to ignore tiny features, the Tversky function tends to be overtrained and misunderstood as a target. Combining the Dice loss function and the Tversky loss function is beneficial to increase the training effect of the model. Therefore, the distance perception loss function is constructed through the Dice loss function and the Tversky loss function, and the perceptual loss function, the image detection algorithm and the neural network model framework are used to construct the target object detection model to be trained, and the target object detection model to be trained is trained. , the target can be identified more accurately, and the CT image to be detected can be processed by the trained target detection model, and the target can be accurately identified on the CT image to be detected. Therefore, the embodiments of the present application can achieve the purpose of improving the accuracy of target image recognition.

如图4所示，是本申请实施例提供的一种基于神经网络的图像识别装置的模块示意图。As shown in FIG. 4 , it is a schematic block diagram of an image recognition apparatus based on a neural network provided by an embodiment of the present application.

本申请所述基于神经网络的图像识别装置100可以安装于电子设备中。根据实现的功能，所述基于神经网络的图像识别装置可以包括模型构建模块101、模型训练模块102、目标物预测模块103。本申请所述模块也可以称之为单元，是指一种能够被电子设备处理器所执行，并且能够完成固定功能的一系列计算机程序段，其存储在电子设备的存储器中。The image recognition apparatus 100 based on the neural network described in this application can be installed in an electronic device. According to the realized functions, the neural network-based image recognition apparatus may include a model building module 101 , a model training module 102 , and a target object prediction module 103 . The modules described in this application may also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of an electronic device and can perform fixed functions, and are stored in the memory of the electronic device.

在本实施例中，关于各模块/单元的功能如下：In this embodiment, the functions of each module/unit are as follows:

所述模型构建模块101，用于利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数，及利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层。The model building module 101 is used to construct a distance-aware loss function using the pre-built Dice loss function and the Tversky loss function, and use the distance-aware loss function, a pre-built image detection algorithm and a neural network model framework to construct a target to be trained Object detection model, the neural network model framework includes an input layer, a hidden layer and an output layer.

本申请装置项中，所述模型构建模块101包括：算法构建单元及模型构建单元。In the device item of the present application, the model building module 101 includes: an algorithm building unit and a model building unit.

所述算法构建单元，用于利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数。The algorithm construction unit is used for constructing a distance-aware loss function using the pre-built Dice loss function and the Tversky loss function.

具体的，所述Dice损失函数及所述Tversky损失函数是为图像检测算法进行回归计算的损失函数。Specifically, the Dice loss function and the Tversky loss function are loss functions for performing regression calculation for the image detection algorithm.

其中，所述Dice损失算法可以分析目标物图像内每个区域中是否含有目标物的特征，但是常常忽视较小特征，造成目标物遗漏；所述Tversky损失函数对于模型的训练过程会出现过度训练的情况，对于图像检测过程中容易出现过拟合现象，导致出现将其他东西识别为目标物等假阳性现象。Among them, the Dice loss algorithm can analyze whether each area in the target image contains the features of the target, but often ignore the smaller features, resulting in the omission of the target; the Tversky loss function will cause overtraining in the training process of the model In the case of image detection, overfitting is easy to occur, resulting in false positives such as recognizing other things as targets.

本申请其中一个实施例中，所述目标物为肿瘤。In one embodiment of the present application, the target is a tumor.

本申请实施例中，将所述Dice损失函数及所述Tversky损失函数进行权重分配，构建所述距离感知损失函数，增加目标物图像识别的准确性。In the embodiment of the present application, the Dice loss function and the Tversky loss function are weighted to construct the distance perception loss function to increase the accuracy of target image recognition.

详细地，本申请实施例中，所述利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数，所述算法构建单元详细用于：In detail, in the embodiment of the present application, the distance-aware loss function is constructed by using the pre-built Dice loss function and the Tversky loss function, and the algorithm construction unit is used in detail for:

对所述Dice损失函数和所述Tversky损失函数进行加权求和，得到所述距离感知损失函数，其中，所述距离感知损失函数为：Weighted summation is performed on the Dice loss function and the Tversky loss function to obtain the distance-aware loss function, where the distance-aware loss function is:

L＝L _Tversky+λ×L _dis L=L _Tversky +λ×L _dis

其中，L _Tversky为所述Tversky损失函数，L _dis为所述Dice损失函数，p _k和y _k分别表示输入的CT图像中每个分割区域内出现目标物的概率值和对应的目标物的标注，λ ₁及λ ₂分别为召唤率∑p _k(1-y _k)及精确度∑(1-p _k)y _k的两个参数，d _k表示每个分割区域到标注为最近的存在目标物的分割区域的距离，Ω表示所述输入的CT图像中所有像素点的个数，λ为加权系数。 Among them, L _Tversky is the Tversky loss function, L _dis is the Dice loss function, p _k and y _k respectively represent the probability value of the target object appearing in each segmented area in the input CT image and the corresponding label of the target object , λ ₁ and λ ₂ are the two parameters of the summoning rate ∑p _k (1-y _k ) and the accuracy ∑ (1-p _k )y _k respectively, d _k represents each segmented area to the nearest existing target marked as is the distance of the segmented area of the object, Ω represents the number of all pixels in the input CT image, and λ is the weighting coefficient.

本申请实施例中加权系数λ，可以通过下述训练过程中输入层与隐藏层之间权重分析来得到，此处不加以赘述。The weighting coefficient λ in the embodiment of the present application can be obtained through the weight analysis between the input layer and the hidden layer in the following training process, and details are not described here.

所述模型构建单元，用于利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层。The model construction unit is used to construct a target object detection model to be trained by using the distance perception loss function, the pre-built image detection algorithm and the neural network model framework, and the neural network model framework includes an input layer, a hidden layer and an output layer .

详细地，本申请实施例中，所述利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层，所述模型构建单元具体用于：In detail, in the embodiment of the present application, the target detection model to be trained is constructed by using the distance perception loss function, the pre-built image detection algorithm and the neural network model framework, and the neural network model framework includes an input layer and a hidden layer. and the output layer, the model building unit is specifically used to:

获取预构建的神经网络模型框架，所述神经网络模型框架包括输入层、隐藏层、输出层；Obtain a pre-built neural network model framework, where the neural network model framework includes an input layer, a hidden layer, and an output layer;

将所述距离感知函数和所述图像检测算法作为隐藏层激活函数添加至所述隐藏层；adding the distance-aware function and the image detection algorithm to the hidden layer as hidden layer activation functions;

获取预构建的Softmax函数；Get the pre-built Softmax function;

将所述Softmax函数作为输出层激活函数添加至所述输出层，得到所述待训练目标物检测模型。The Softmax function is added to the output layer as an output layer activation function to obtain the target object detection model to be trained.

具体的，本申请实施例中，所述神经网络模型框架为TransForm模型框架，其中所述TransForm模型框架包括所述输入层、所述隐藏层、所述输出层，且输入层、隐藏层和输出层都是由多个神经元构成，激活神经元便可进行数据传输、运算、处理等操作。Specifically, in the embodiment of the present application, the neural network model framework is a TransForm model framework, wherein the TransForm model framework includes the input layer, the hidden layer, and the output layer, and the input layer, the hidden layer, and the output layer The layers are composed of multiple neurons, and the activation of neurons can perform operations such as data transmission, calculation, and processing.

具体的，所述输入层用于将数据进行权重配置，使得当不同数量级的特征值输入所述隐藏层时，不同数量级的特征值都能起到相同级别的作用。所述隐藏层包括由所述图像检测算法及所述距离感知函数组成的激活函数，用于对所述输入层输入的数据进行处理。Specifically, the input layer is used for weight configuration of the data, so that when eigenvalues of different orders of magnitude are input to the hidden layer, the eigenvalues of different orders of magnitude can play a role of the same level. The hidden layer includes an activation function composed of the image detection algorithm and the distance perception function, and is used for processing the data input by the input layer.

本申请实施例中，所述输出层对检测到的目标物进行分类，并得到各个分类结果对应的概率。In the embodiment of the present application, the output layer classifies the detected objects, and obtains the probability corresponding to each classification result.

本申请实施例利用所述距离感知损失函数及所述图像检测算法修改隐藏层的损失函数及运算函数，利用Softmax函数修改所述输出层的激活函数，得到所述待训练目标物检测模型。In this embodiment of the present application, the distance sensing loss function and the image detection algorithm are used to modify the loss function and operation function of the hidden layer, and the Softmax function is used to modify the activation function of the output layer to obtain the target object detection model to be trained.

所述模型训练模块102，用于获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型。The model training module 102 is configured to acquire a target object image sample set, and use the target object image sample set to train the target object detection model to be trained to obtain a trained target object detection model.

本申请实施例中所述目标物图像样本集中包括各种目标物或普通组织的CT图像、磁共振图像等医学图像及与所述医学图像对应的图像分析标签。The target object image sample set in the embodiment of the present application includes medical images such as CT images and magnetic resonance images of various targets or common tissues, and image analysis tags corresponding to the medical images.

详细地，如下图2所示，本申请实施例中，所述利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型，所述模型训练模块102具体用于：In detail, as shown in FIG. 2 below, in the embodiment of the present application, the target object detection model to be trained is trained by using the target object image sample set, and the trained target object detection model is obtained. The model training module 102 Specifically for:

将所述目标物图像样本集导入所述待训练目标物检测模型的输入层中，利用所述输入层中权重配置函数对所述目标物图像样本集中各个目标物图像特征进行权重分配。The target image sample set is imported into the input layer of the target detection model to be trained, and the weight allocation function in the input layer is used to allocate weights to each target image feature in the target image sample set.

本申请实施例中，所述权重配置函数是一种逆向参数调整函数，即通过训练过后的计算结果的准确性，改变数值输入比例，重新进行训练，直至计算结果接近标准答案的运算函数。In the embodiment of the present application, the weight configuration function is an inverse parameter adjustment function, that is, an operation function that changes the numerical input ratio according to the accuracy of the calculation result after training, and retrains until the calculation result is close to the standard answer.

根据权重分配结果，对所述肿瘤图像特征进行权重计算，得到权重特征值，并将所述权重特征值导入所述隐藏层。According to the weight distribution result, weight calculation is performed on the tumor image feature to obtain a weight feature value, and the weight feature value is imported into the hidden layer.

通过所述权重特征值触发所述激活函数的激活条件，使得所述距离感知损失函数根据 所述权重特征值进行损失运算，得到最小化损失值，判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值。The activation condition of the activation function is triggered by the weight eigenvalue, so that the distance-aware loss function performs a loss operation according to the weight eigenvalue to obtain a minimized loss value, and judges whether the minimized loss value converges. When the minimized loss value converges, the final loss value is obtained.

本申请实施例中所述激活函数为分段函数，当所述权重特征值得数值小于预设标准值，函数不激活，运算结果为0，当所述权重特征值得数值大于或等于所述预设标准值，函数激活对所述权重特征值进行目标物检测。In this embodiment of the present application, the activation function is a piecewise function. When the value of the weight feature value is less than the preset standard value, the function is not activated, and the operation result is 0. When the value of the weight feature value is greater than or equal to the preset value Standard value, the function activates target detection on the weight feature value.

进一步，本申请实施例中，所述判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值，包括：Further, in the embodiment of the present application, the judging whether the minimized loss value converges, and when it is judged that the minimized loss value converges, obtains a final loss value, including:

对产生的多个所述最小化损失值依次进行二维映射，得到损失值波动图，对所述损失值波动图中图线进行求导计算，得到求导结果；当所述求导结果小于预构建的预设数值时，判定小于所述预设数值的求导结果对应最小化损失值达到收敛，得到所述最终损失值。Perform two-dimensional mapping on a plurality of the generated minimized loss values in turn to obtain a loss value fluctuation graph, and perform derivation calculation on the graph line in the loss value fluctuation graph to obtain a derivation result; when the derivation result is less than When the preset value is pre-built, it is determined that the derivation result smaller than the preset value corresponds to the minimized loss value to reach convergence, and the final loss value is obtained.

本申请实施例中，在训练过程中，每次利用新的样本进行一次训练，都会产生一个最小化损失值。随着训练样本的逐渐增多，所述最小化损失值会随着训练过程逐渐变小，利用所述最小化损失值使得所述图像检测算法的准确度逐渐增加，且所述最小化损失值的求导结果会逐渐减小，当所述求导结果未达到所述预设数值时，利用目标物图像样本继续对所述目标物检测模型进行再一次训练，直至所述求导结果达到所述预设数值，表明所述最小化损失值的下降趋势消失，所述最小化损失值达到收敛状态，训练完成。In the embodiment of the present application, in the training process, each time a new sample is used for training, a minimized loss value will be generated. With the increasing number of training samples, the minimization loss value will gradually decrease with the training process, and the minimization loss value is used to gradually increase the accuracy of the image detection algorithm, and the minimization loss value is The derivation result will gradually decrease. When the derivation result does not reach the preset value, continue to train the target detection model again by using the target object image sample until the derivation result reaches the The preset value indicates that the downward trend of the minimized loss value disappears, the minimized loss value reaches a convergent state, and the training is completed.

根据所述最终损失值配置所述隐藏层中激活函数的图像检测算法，完成训练的过程，得到训练完成的所述目标物检测模型。The image detection algorithm of the activation function in the hidden layer is configured according to the final loss value, the training process is completed, and the trained target detection model is obtained.

所述目标物预测模块103，用于获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据，及利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。The target object prediction module 103 is used to obtain the CT image to be detected, perform quantization and denoising processing on the CT image to be detected, obtain denoised image data, and use the target object detection model to denoise the noise. The image data is used for image recognition, and the target object recognition result is obtained.

其中，本申请装置项中，所述目标物预测模块103，包括：检测单元、判断单元。Among them, in the device item of the present application, the target object prediction module 103 includes: a detection unit and a judgment unit.

所述检测单元，用于获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据。The detection unit is used for acquiring a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected to obtain denoised image data.

详细地，本申请实施例中，所述获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据，所述检测单元具体用于：In detail, in the embodiment of the present application, the acquisition of the CT image to be detected, and the quantization and denoising processing of the CT image to be detected are performed to obtain denoised image data, and the detection unit is specifically used for:

对所述待检测CT图像中各像素进行区域划分，并将划分好的像素块进行向量化处理，得到量化图像数据；Perform regional division on each pixel in the CT image to be detected, and perform vectorization processing on the divided pixel blocks to obtain quantized image data;

利用预构建的高斯滤波器将所述量化图像数据进行二维邻域的高斯卷积运算，得到去噪图像数据。The quantized image data is subjected to a Gaussian convolution operation of a two-dimensional neighborhood by using a pre-built Gaussian filter to obtain denoised image data.

本申请实施例以预设像素大小，如2*2个像素为基本单位对所述待检测CT图像进行分割，得到多个像素快，并对所述像素快进行向量化处理，得到所述量化图像数据，通过预构建的高斯滤波器，对方形范围内量化图像数据，如3*3的矩阵块进行运算，利用得到的运算结果代表所述3*3矩阵的收缩值，通过所述高斯滤波器中的卷积器对相邻3*3矩阵进行运算直至所述待检测CT图像遍历完成，得到所述去噪图像数据。In this embodiment of the present application, a preset pixel size, such as 2*2 pixels, is used as the basic unit to segment the CT image to be detected, to obtain a plurality of pixel blocks, and perform vectorization processing on the pixel blocks to obtain the quantization process. Image data, through the pre-built Gaussian filter, perform operations on the quantized image data in the square range, such as a 3*3 matrix block, use the obtained operation result to represent the shrinkage value of the 3*3 matrix, and pass the Gaussian filter through the Gaussian filter. The convolver in the device operates on adjacent 3*3 matrices until the traversal of the CT image to be detected is completed, and the denoised image data is obtained.

所述判断单元，用于利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。The judging unit is configured to perform image recognition on the denoised image data by using the target detection model to obtain a target recognition result.

详细地，本申请实施例中，如下图4所示，所述利用所述目标物检测模型对所述去噪图像数据进行检测，得到目标物检测结果，所述判断单元具体用于：In detail, in the embodiment of the present application, as shown in FIG. 4 below, the target detection model is used to detect the denoised image data to obtain a target detection result, and the judgment unit is specifically used for:

对所述去噪图像数据进行特征提取，得到特征值；performing feature extraction on the denoised image data to obtain feature values;

将所述特征值导入所述隐藏层进行目标物图像识别，得到识别结果；importing the feature value into the hidden layer to perform target image recognition to obtain a recognition result;

将所述识别结果导入所述输出层，使得所述输出层激活函数根据预构建的目标物的分类标签，判定所述待检测CT图像中存在有目标物的概率及对应类别的概率。The recognition result is imported into the output layer, so that the output layer activation function determines the probability of the target object and the probability of the corresponding category in the CT image to be detected according to the pre-built classification label of the target object.

本申请实施例将所述去噪图像数据导入所述目标物检测模型中，所述输入层中的特征提取网络对所述去噪图像数据进行特征提取，并将提取结果通过神经网络与各种肿瘤细胞 进行匹配，判断所述待检测CT图像中是否存在肿瘤，当存在肿瘤时，通过所述输出层对肿瘤的特征进行纹理分析及类别预测，准确判断出肿瘤类别/或各个类别的概率。In this embodiment of the present application, the denoised image data is imported into the target detection model, the feature extraction network in the input layer performs feature extraction on the denoised image data, and the extraction results are combined with various The tumor cells are matched to determine whether there is a tumor in the CT image to be detected. When there is a tumor, texture analysis and category prediction are performed on the characteristics of the tumor through the output layer to accurately determine the tumor category/or the probability of each category.

本申请实施例通过对Dice损失函数和Tversky损失函数构建距离感知损失函数，由于Dice损失函数训练的模型容易导致忽视微小特征，而Tversky函数容易训练训练过度，导致将一些其他东西错认为目标物。将Dice损失函数和Tversky损失函数进行结合，有利于增加模型的训练效果。因此，通过Dice损失函数和Tversky损失函数构建距离感知损失函数，并利用该感知损失函数、图像检测算法及神经网络模型框架构建待训练目标物检测模型，并对该待训练目标物检测模型进行训练，可以更准确地进行目标物的识别，通过训练完成的目标物检测模型处理待检测的CT图像，能够准确地对待检测的CT图像进行目标物识别。因此，本申请实施例能够实现提高目标物图像识别的精确度的目的。In this embodiment of the present application, a distance-aware loss function is constructed for the Dice loss function and the Tversky loss function. Since the model trained by the Dice loss function tends to ignore tiny features, the Tversky function tends to be overtrained and misunderstood as a target. Combining the Dice loss function and the Tversky loss function is beneficial to increase the training effect of the model. Therefore, the distance perception loss function is constructed through the Dice loss function and the Tversky loss function, and the perceptual loss function, the image detection algorithm and the neural network model framework are used to construct the target object detection model to be trained, and the target object detection model to be trained is trained. , the target can be identified more accurately, and the CT image to be detected can be processed by the trained target detection model, and the target can be accurately identified on the CT image to be detected. Therefore, the embodiments of the present application can achieve the purpose of improving the accuracy of target image recognition.

如图5所示，是本申请实施例提供的实现基于神经网络的图像识别方法的电子设备的结构示意图。As shown in FIG. 5 , it is a schematic structural diagram of an electronic device for implementing an image recognition method based on a neural network provided by an embodiment of the present application.

所述电子设备1可以包括处理器10、存储器11和总线，还可以包括存储在所述存储器11中并可在所述处理器10上运行的计算机程序，如基于神经网络的图像识别方法程序12。The electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program stored in the memory 11 and running on the processor 10, such as a neural network-based image recognition method program 12 .

其中，所述存储器11至少包括一种类型的可读存储介质，所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如：SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器11在一些实施例中可以是电子设备1的内部存储单元，例如该电子设备1的移动硬盘。所述存储器11在另一些实施例中也可以是电子设备1的外部存储设备，例如电子设备1上配备的插接式移动硬盘、智能存储卡(Smart Media Card，SMC)、安全数字(Secure Digital，SD)卡、闪存卡(Flash Card)等。进一步地，所述存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。所述存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据，例如基于神经网络的图像识别方法程序12的代码等，还可以用于暂时地存储已经输出或者将要输出的数据。Wherein, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1 . In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital) equipped on the electronic device 1. , SD) card, flash memory card (Flash Card), etc. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various data installed in the electronic device 1, such as the code of the neural network-based image recognition method program 12, etc., but also can be used to temporarily store the data that has been output or will be output. .

所述处理器10在一些实施例中可以由集成电路组成，例如可以由单个封装的集成电路所组成，也可以是由多个相同功能或不同功能封装的集成电路所组成，包括一个或者多个中央处理器(Central Processing unit，CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器10是所述电子设备的控制核心(Control Unit)，利用各种接口和线路连接整个电子设备的各个部件，通过运行或执行存储在所述存储器11内的程序或者模块(例如执行基于神经网络的图像识别方法程序等)，以及调用存储在所述存储器11内的数据，以执行电子设备1的各种功能和处理数据。In some embodiments, the processor 10 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more integrated circuits. Central Processing Unit (CPU), microprocessor, digital processing chip, graphics processor and combination of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, by running or executing the program or module (for example, executing the program) stored in the memory 11. Image recognition method program based on neural network, etc.), and call the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

所述总线可以是外设部件互连标准(peripheral component interconnect，简称PCI)总线或扩展工业标准结构(extended industry standard architecture，简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器11以及至少一个处理器10等之间的连接通信。The bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (Extended industry standard architecture, EISA for short) bus or the like. The bus can be divided into address bus, data bus, control bus and so on. The bus is configured to implement connection communication between the memory 11 and at least one processor 10 and the like.

图5仅示出了具有部件的电子设备，本领域技术人员可以理解的是，图5示出的结构并不构成对所述电子设备1的限定，可以包括比图示更少或者更多的部件，或者组合某些部件，或者不同的部件布置。FIG. 5 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 5 does not constitute a limitation on the electronic device 1, and may include fewer or more components than those shown in the drawings. components, or a combination of certain components, or a different arrangement of components.

例如，尽管未示出，所述电子设备1还可以包括给各个部件供电的电源(比如电池)，优选地，电源可以通过电源管理装置与所述至少一个处理器10逻辑相连，从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备1还可以包括多种传感器、蓝牙模块、Wi-Fi模块等，在此不再赘述。For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) for powering the various components, preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that the power management The device implements functions such as charge management, discharge management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components. The electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

进一步地，所述电子设备1还可以包括网络接口，可选地，所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等)，通常用于在该电子设备1与其他电子 设备之间建立通信连接。Further, the electronic device 1 may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.

可选地，该电子设备1还可以包括用户接口，用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard))，可选地，用户接口还可以是标准的有线接口、无线接口。可选地，在一些实施例中，显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode，有机发光二极管)触摸器等。其中，显示器也可以适当的称为显示屏或显示单元，用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。Optionally, the electronic device 1 may further include a user interface, and the user interface may be a display (Display), an input unit (eg, a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like. The display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.

应该了解，所述实施例仅为说明之用，在专利申请范围上并不受此结构的限制。It should be understood that the embodiments are only used for illustration, and are not limited by this structure in the scope of the patent application.

所述电子设备1中的所述存储器11存储的基于神经网络的图像识别方法程序12是多个计算机程序的组合，在所述处理器10中运行时，可以实现：The neural network-based image recognition method program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple computer programs, and when running in the processor 10, can realize:

利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数；Use the pre-built Dice loss function and Tversky loss function to build a distance-aware loss function;

利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层；Use the distance perception loss function, the pre-built image detection algorithm and the neural network model framework to construct the target object detection model to be trained, and the neural network model framework includes an input layer, a hidden layer and an output layer;

获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型；Obtaining a target object image sample set, and using the target object image sample set to train the target object detection model to be trained, to obtain a trained target object detection model;

获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据；Obtaining a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected to obtain denoised image data;

利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。Image recognition is performed on the denoised image data by using the target detection model to obtain a target recognition result.

进一步地，所述电子设备1集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。所述计算机可读存储介质可以是易失性的，也可以是非易失性的。例如，所述计算机可读存储介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)。Further, if the modules/units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. The computer-readable storage medium may be volatile or non-volatile. For example, the computer-readable storage medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) Only Memory).

进一步地，所述计算机可读存储介质可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作***、至少一个功能所需的应用程序等；存储数据区可存储根据区块链节点的使用所创建的数据等。Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function, and the like; The data created by the use of the node, etc.

本申请还提供一种计算机可读存储介质，所述可读存储介质存储有计算机程序，所述计算机程序在被电子设备的处理器所执行时，可以实现：The present application also provides a computer-readable storage medium, where the readable storage medium stores a computer program, and when executed by a processor of an electronic device, the computer program can realize:

利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数；Use the pre-built Dice loss function and Tversky loss function to build a distance-aware loss function;

利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层；Use the distance perception loss function, the pre-built image detection algorithm and the neural network model framework to construct the target object detection model to be trained, and the neural network model framework includes an input layer, a hidden layer and an output layer;

获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型；Obtaining a target object image sample set, and using the target object image sample set to train the target object detection model to be trained, to obtain a trained target object detection model;

获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据；Obtaining a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected to obtain denoised image data;

利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。Image recognition is performed on the denoised image data by using the target detection model to obtain a target recognition result.

在本申请所提供的几个实施例中，应该理解到，所揭露的设备，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。In the several embodiments provided in this application, it should be understood that the disclosed apparatus, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division manners in actual implementation.

所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。The modules described as separate components may or may not be physically separated, and components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

另外，在本申请各个实施例中的各功能模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能模块的形式实现。In addition, each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.

对于本领域技术人员而言，显然本申请不限于上述示范性实施例的细节，而且在不背离本申请的精神或基本特征的情况下，能够以其他的具体形式实现本申请。It will be apparent to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, but that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本申请的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图表记视为限制所涉及的权利要求。Accordingly, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the application is to be defined by the appended claims rather than the foregoing description, which is therefore intended to fall within the scope of the claims. All changes within the meaning and scope of the equivalents of , are included in this application. Any accompanying reference signs in the claims should not be construed as limiting the involved claims.

本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain)，本质上是一个去中心化的数据库，是一串使用密码学方法相关联产生的数据块，每一个数据块中包含了一批次网络交易的信息，用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。The blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

此外，显然“包括”一词不排除其他单元或步骤，单数不排除复数。***权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称，而并不表示任何特定的顺序。Furthermore, it is clear that the word "comprising" does not exclude other units or steps and the singular does not exclude the plural. Several units or means recited in the system claims can also be realized by one unit or means by means of software or hardware. Second-class terms are used to denote names and do not denote any particular order.

最后应说明的是，以上实施例仅用以说明本申请的技术方案而非限制，尽管参照较佳实施例对本申请进行了详细说明，本领域的普通技术人员应当理解，可以对本申请的技术方案进行修改或等同替换，而不脱离本申请技术方案的精神和范围。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application rather than limitations. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be Modifications or equivalent substitutions can be made without departing from the spirit and scope of the technical solutions of the present application.

Claims (22)

1. 一种基于神经网络的图像识别方法，其中，所述方法包括：A neural network-based image recognition method, wherein the method comprises:

   利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数；Use the pre-built Dice loss function and Tversky loss function to build a distance-aware loss function;

   利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层；Use the distance perception loss function, the pre-built image detection algorithm and the neural network model framework to construct the target object detection model to be trained, and the neural network model framework includes an input layer, a hidden layer and an output layer;

   获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型；Obtaining a target object image sample set, and using the target object image sample set to train the target object detection model to be trained, to obtain a trained target object detection model;

   获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据；Obtaining a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected to obtain denoised image data;

   利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。Image recognition is performed on the denoised image data by using the target detection model to obtain a target recognition result.
2. 如权利要求1所述的基于神经网络的图像识别方法，其中，所述利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数，包括：The image recognition method based on neural network as claimed in claim 1, wherein, constructing a distance-aware loss function by using a pre-built Dice loss function and a Tversky loss function, comprising:

   对所述Dice损失函数和所述Tversky损失函数进行加权求和，得到所述距离感知损失函数，其中，所述距离感知损失函数为：Weighted summation is performed on the Dice loss function and the Tversky loss function to obtain the distance-aware loss function, where the distance-aware loss function is:

   

   

   

   

   L＝L _Tversky+λ×L _dis L=L _Tversky +λ×L _dis

   其中，L _Tversky为所述Tversky损失函数，L _dis为所述Dice损失函数，p _k和y _k分别表示输入的CT图像中每个分割区域内出现目标物的概率值和对应的目标物的标注，λ ₁及λ ₂分别为召唤率∑p _k(1-y _k)及精确度∑(1-p _k)y _k的两个参数，d _k表示每个分割区域到标注为最近的存在目标物的分割区域的距离，Ω表示所述输入的CT图像中所有像素点的个数，λ为加权系数。 Among them, L _Tversky is the Tversky loss function, L _dis is the Dice loss function, p _k and y _k respectively represent the probability value of the target object appearing in each segmented area in the input CT image and the corresponding label of the target object , λ ₁ and λ ₂ are the two parameters of the summoning rate ∑p _k (1-y _k ) and the accuracy ∑ (1-p _k )y _k respectively, d _k represents each segmented area to the nearest existing target marked as is the distance of the segmented area of the object, Ω represents the number of all pixels in the input CT image, and λ is the weighting coefficient.
3. 如权利要求1所述的基于神经网络的图像识别方法，其中，所述利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层，包括：The image recognition method based on a neural network according to claim 1, wherein the target object detection model to be trained is constructed by using the distance perception loss function, a pre-built image detection algorithm and a neural network model framework, and the neural network The model framework includes input layer, hidden layer and output layer, including:

   获取预构建的神经网络模型框架，所述神经网络模型框架包括输入层、隐藏层、输出层；Obtain a pre-built neural network model framework, where the neural network model framework includes an input layer, a hidden layer, and an output layer;

   将所述距离感知函数和所述图像检测算法作为隐藏层激活函数添加至所述隐藏层；adding the distance-aware function and the image detection algorithm to the hidden layer as hidden layer activation functions;

   获取预构建的Softmax函数；Get the pre-built Softmax function;

   将所述Softmax函数作为输出层激活函数添加至所述输出层，得到所述待训练目标物检测模型。The Softmax function is added to the output layer as an output layer activation function to obtain the target object detection model to be trained.
4. 如权利要求1至3中任意一项所述的基于神经网络的图像识别方法，其中，所述利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型，包括：The image recognition method based on a neural network according to any one of claims 1 to 3, wherein the target object detection model to be trained is trained by using the target object image sample set, and the trained target object detection model is obtained models, including:

   将所述目标物图像样本集导入所述待训练目标物检测模型的输入层中，利用所述输入层中权重配置函数对所述目标物图像样本集中各个目标物图像特征进行权重分配；Importing the target image sample set into the input layer of the target detection model to be trained, and using the weight configuration function in the input layer to perform weight distribution on each target image feature in the target image sample set;

   根据权重分配结果，对所述目标物图像特征进行权重计算，得到权重特征值，并将所述权重特征值导入所述隐藏层；According to the weight distribution result, weight calculation is performed on the image feature of the target object to obtain a weight feature value, and the weight feature value is imported into the hidden layer;

   通过所述权重特征值触发所述激活函数的激活条件，使得所述距离感知损失函数根据所述权重特征值进行损失运算，得到最小化损失值，判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值；The activation condition of the activation function is triggered by the weight eigenvalue, so that the distance-aware loss function performs a loss operation according to the weight eigenvalue to obtain a minimized loss value, and judges whether the minimized loss value converges. When the minimum loss value converges, the final loss value is obtained;

   根据所述最终损失值配置所述隐藏层中激活函数的图像检测算法，完成训练的过程，得到训练完成的所述目标物检测模型。The image detection algorithm of the activation function in the hidden layer is configured according to the final loss value, the training process is completed, and the trained target detection model is obtained.
5. 如权利要求4所述的基于神经网络的图像识别方法，其中，所述判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值，包括：The image recognition method based on a neural network according to claim 4, wherein the judging whether the minimized loss value is convergent, and when it is judged that the minimized loss value is convergent, obtains a final loss value, comprising:

   对产生的多个所述最小化损失值依次进行二维映射，得到损失值波动图，对所述损失值波动图中图线进行求导计算，得到求导结果；Perform two-dimensional mapping on a plurality of the generated minimized loss values in turn to obtain a loss value fluctuation graph, and perform derivation calculation on the graph line in the loss value fluctuation graph to obtain a derivation result;

   当所述求导结果小于预构建的预设数值时，判定小于所述预设数值的求导结果对应最小化损失值达到收敛，得到所述最终损失值。When the derivation result is smaller than the pre-built preset value, it is determined that the derivation result smaller than the preset value corresponds to the minimized loss value and reaches convergence, and the final loss value is obtained.
6. 如权利要求1所述的基于神经网络的图像识别方法，其中，所述获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据，包括：The image recognition method based on a neural network according to claim 1, wherein said acquiring a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected, to obtain denoised image data, comprising:

   对所述待检测CT图像中各像素进行区域划分，并将划分好的像素块进行向量化处理，得到量化图像数据；Perform regional division on each pixel in the CT image to be detected, and perform vectorization processing on the divided pixel blocks to obtain quantized image data;

   利用预构建的高斯滤波器将所述量化图像数据进行二维邻域的高斯卷积运算，得到去噪图像数据。The quantized image data is subjected to a Gaussian convolution operation of a two-dimensional neighborhood by using a pre-built Gaussian filter to obtain denoised image data.
7. 如权利要求1所述的基于神经网络的图像识别方法，其中，所述利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果，包括：The image recognition method based on a neural network according to claim 1, wherein the performing image recognition on the denoised image data by using the target object detection model to obtain a target object recognition result comprises:

   对所述去噪图像数据进行特征提取，得到特征值；performing feature extraction on the denoised image data to obtain feature values;

   将所述特征值导入所述隐藏层进行图像识别，得到目标物识别结果；importing the feature value into the hidden layer for image recognition to obtain a target object recognition result;

   将所述目标物识别结果导入所述输出层，使得所述输出层激活函数根据预构建的目标物分类标签，判定所述待检测CT图像中存在目标物的概率及对应类别的概率。The target object recognition result is imported into the output layer, so that the output layer activation function determines the probability of the target object and the probability of the corresponding category in the CT image to be detected according to the pre-built target object classification label.
8. 一种基于神经网络的图像识别装置，其中，所述装置包括：A neural network-based image recognition device, wherein the device comprises:

   模型构建模块，用于利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数，及利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层；The model building module is used to construct a distance-aware loss function using the pre-built Dice loss function and the Tversky loss function, and use the distance-aware loss function, the pre-built image detection algorithm and the neural network model framework to construct a target object detection model to be trained , the neural network model framework includes an input layer, a hidden layer and an output layer;

   模型训练模块，用于获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型；a model training module, configured to obtain a target object image sample set, and use the target object image sample set to train the target object detection model to be trained, and obtain a trained target object detection model;

   目标物预测模块，用于获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据，及利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。The target object prediction module is used to obtain the CT image to be detected, perform quantization and denoising processing on the CT image to be detected, obtain denoised image data, and use the target detection model to perform the denoising image data on the denoised image data. Image recognition to obtain target recognition results.
9. 一种电子设备，其中，所述电子设备包括：An electronic device, wherein the electronic device comprises:

   至少一个处理器；以及，at least one processor; and,

   与所述至少一个处理器通信连接的存储器；其中，a memory communicatively coupled to the at least one processor; wherein,

   所述存储器存储有可被所述至少一个处理器执行的计算机程序指令，所述计算机程序指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如下步骤：The memory stores computer program instructions executable by the at least one processor, the computer program instructions being executed by the at least one processor to enable the at least one processor to perform the steps of:

   利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数；Use the pre-built Dice loss function and Tversky loss function to build a distance-aware loss function;

   利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层；Use the distance perception loss function, the pre-built image detection algorithm and the neural network model framework to construct the target object detection model to be trained, and the neural network model framework includes an input layer, a hidden layer and an output layer;

   获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型；Obtaining a target object image sample set, and using the target object image sample set to train the target object detection model to be trained, to obtain a trained target object detection model;

   获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据；Obtaining a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected to obtain denoised image data;

   利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。Image recognition is performed on the denoised image data by using the target detection model to obtain a target recognition result.
10. 如权利要求9所述的电子设备，其中，所述利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数，包括：The electronic device according to claim 9, wherein the distance-aware loss function is constructed by using a pre-built Dice loss function and a Tversky loss function, comprising:

    对所述Dice损失函数和所述Tversky损失函数进行加权求和，得到所述距离感知损失 函数，其中，所述距离感知损失函数为：The weighted summation is performed on the Dice loss function and the Tversky loss function to obtain the distance-aware loss function, wherein the distance-aware loss function is:

    

    

    

    

    L＝L _Tversky+λ×L _dis L=L _Tversky +λ×L _dis

    其中，L _Tversky为所述Tversky损失函数，L _dis为所述Dice损失函数，p _k和y _k分别表示输入的CT图像中每个分割区域内出现目标物的概率值和对应的目标物的标注，λ ₁及λ ₂分别为召唤率∑p _k(1-y _k)及精确度∑(1-p _k)y _k的两个参数，d _k表示每个分割区域到标注为最近的存在目标物的分割区域的距离，Ω表示所述输入的CT图像中所有像素点的个数，λ为加权系数。 Among them, L _Tversky is the Tversky loss function, L _dis is the Dice loss function, p _k and y _k respectively represent the probability value of the target object appearing in each segmented area in the input CT image and the corresponding label of the target object , λ ₁ and λ ₂ are the two parameters of the summoning rate ∑p _k (1-y _k ) and the accuracy ∑ (1-p _k )y _k respectively, d _k represents each segmented area to the nearest existing target marked as is the distance of the segmented area of the object, Ω represents the number of all pixels in the input CT image, and λ is the weighting coefficient.
11. 如权利要求9所述的电子设备，其中，所述利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层，包括：The electronic device according to claim 9, wherein the target object detection model to be trained is constructed by using the distance perception loss function, a pre-built image detection algorithm and a neural network model framework, and the neural network model framework includes an input layer , hidden layers, and output layers, including:

    获取预构建的神经网络模型框架，所述神经网络模型框架包括输入层、隐藏层、输出层；Obtain a pre-built neural network model framework, where the neural network model framework includes an input layer, a hidden layer, and an output layer;

    将所述距离感知函数和所述图像检测算法作为隐藏层激活函数添加至所述隐藏层；adding the distance-aware function and the image detection algorithm to the hidden layer as hidden layer activation functions;

    获取预构建的Softmax函数；Get the pre-built Softmax function;

    将所述Softmax函数作为输出层激活函数添加至所述输出层，得到所述待训练目标物检测模型。The Softmax function is added to the output layer as an output layer activation function to obtain the target object detection model to be trained.
12. 如权利要求9至11中任意一项所述的电子设备，其中，所述利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型，包括：The electronic device according to any one of claims 9 to 11, wherein the training of the target detection model to be trained by using the target image sample set to obtain a trained target detection model comprises:

    将所述目标物图像样本集导入所述待训练目标物检测模型的输入层中，利用所述输入层中权重配置函数对所述目标物图像样本集中各个目标物图像特征进行权重分配；Importing the target image sample set into the input layer of the target detection model to be trained, and using the weight configuration function in the input layer to perform weight distribution on each target image feature in the target image sample set;

    根据权重分配结果，对所述目标物图像特征进行权重计算，得到权重特征值，并将所述权重特征值导入所述隐藏层；According to the weight distribution result, weight calculation is performed on the image feature of the target object to obtain a weight feature value, and the weight feature value is imported into the hidden layer;

    通过所述权重特征值触发所述激活函数的激活条件，使得所述距离感知损失函数根据所述权重特征值进行损失运算，得到最小化损失值，判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值；The activation condition of the activation function is triggered by the weight eigenvalue, so that the distance-aware loss function performs a loss operation according to the weight eigenvalue to obtain a minimized loss value, and judges whether the minimized loss value converges. When the minimum loss value converges, the final loss value is obtained;

    根据所述最终损失值配置所述隐藏层中激活函数的图像检测算法，完成训练的过程，得到训练完成的所述目标物检测模型。The image detection algorithm of the activation function in the hidden layer is configured according to the final loss value, the training process is completed, and the trained target detection model is obtained.
13. 如权利要求12所述的电子设备，其中，所述判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值，包括：The electronic device according to claim 12, wherein the judging whether the minimized loss value converges, and when it is judged that the minimized loss value converges, obtaining a final loss value, comprising:

    对产生的多个所述最小化损失值依次进行二维映射，得到损失值波动图，对所述损失值波动图中图线进行求导计算，得到求导结果；Perform two-dimensional mapping on a plurality of the generated minimized loss values in turn to obtain a loss value fluctuation graph, and perform derivation calculation on the graph line in the loss value fluctuation graph to obtain a derivation result;

    当所述求导结果小于预构建的预设数值时，判定小于所述预设数值的求导结果对应最小化损失值达到收敛，得到所述最终损失值。When the derivation result is smaller than the pre-built preset value, it is determined that the derivation result smaller than the preset value corresponds to the minimized loss value and reaches convergence, and the final loss value is obtained.
14. 如权利要求9所述的电子设备，其中，所述获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据，包括：The electronic device according to claim 9, wherein the acquiring a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected, to obtain denoised image data, comprising:

    对所述待检测CT图像中各像素进行区域划分，并将划分好的像素块进行向量化处理，得到量化图像数据；Perform regional division on each pixel in the CT image to be detected, and perform vectorization processing on the divided pixel blocks to obtain quantized image data;

    利用预构建的高斯滤波器将所述量化图像数据进行二维邻域的高斯卷积运算，得到去噪图像数据。The quantized image data is subjected to a Gaussian convolution operation of a two-dimensional neighborhood by using a pre-built Gaussian filter to obtain denoised image data.
15. 如权利要求9所述的电子设备，其中，所述利用所述目标物检测模型对所述去噪 图像数据进行图像识别，得到目标物识别结果，包括：The electronic device according to claim 9, wherein the image recognition is performed on the denoised image data using the target detection model to obtain a target recognition result, comprising:

    对所述去噪图像数据进行特征提取，得到特征值；performing feature extraction on the denoised image data to obtain feature values;

    将所述特征值导入所述隐藏层进行图像识别，得到目标物识别结果；importing the feature value into the hidden layer for image recognition to obtain a target object recognition result;

    将所述目标物识别结果导入所述输出层，使得所述输出层激活函数根据预构建的目标物分类标签，判定所述待检测CT图像中存在目标物的概率及对应类别的概率。The target object recognition result is imported into the output layer, so that the output layer activation function determines the probability of the target object and the probability of the corresponding category in the CT image to be detected according to the pre-built target object classification label.
16. 一种计算机可读存储介质，包括存储数据区和存储程序区，存储数据区存储创建的数据，存储程序区存储有计算机程序；其中，所述计算机程序被处理器执行时实现如下步骤：A computer-readable storage medium, comprising a storage data area and a storage program area, the storage data area stores data created, and the storage program area stores a computer program; wherein, the computer program is executed by a processor The following steps are implemented:

    利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数；Use the pre-built Dice loss function and Tversky loss function to build a distance-aware loss function;

    利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层；Use the distance perception loss function, the pre-built image detection algorithm and the neural network model framework to construct the target object detection model to be trained, and the neural network model framework includes an input layer, a hidden layer and an output layer;

    获取目标物图像样本集，并利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型；Obtaining a target object image sample set, and using the target object image sample set to train the target object detection model to be trained, to obtain a trained target object detection model;

    获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据；Obtaining a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected to obtain denoised image data;

    利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果。Image recognition is performed on the denoised image data by using the target detection model to obtain a target recognition result.
17. 如权利要求16所述的计算机可读存储介质，其中，所述利用预构建的Dice损失函数和Tversky损失函数构建距离感知损失函数，包括：The computer-readable storage medium of claim 16, wherein the constructing a distance-aware loss function using a pre-built Dice loss function and a Tversky loss function comprises:

    对所述Dice损失函数和所述Tversky损失函数进行加权求和，得到所述距离感知损失函数，其中，所述距离感知损失函数为：Weighted summation is performed on the Dice loss function and the Tversky loss function to obtain the distance-aware loss function, where the distance-aware loss function is:

    

    

    

    

    L＝L _Tversky+λ×L _dis L=L _Tversky +λ×L _dis

    其中，L _Tversky为所述Tversky损失函数，L _dis为所述Dice损失函数，p _k和y _k分别表示输入的CT图像中每个分割区域内出现目标物的概率值和对应的目标物的标注，λ ₁及λ ₂分别为召唤率∑p _k(1-y _k)及精确度∑(1-p _k)y _k的两个参数，d _k表示每个分割区域到标注为最近的存在目标物的分割区域的距离，Ω表示所述输入的CT图像中所有像素点的个数，λ为加权系数。 Among them, L _Tversky is the Tversky loss function, L _dis is the Dice loss function, p _k and y _k respectively represent the probability value of the target object appearing in each segmented area in the input CT image and the corresponding label of the target object , λ ₁ and λ ₂ are the two parameters of the summoning rate ∑p _k (1-y _k ) and the accuracy ∑ (1-p _k )y _k respectively, d _k represents each segmented area to the nearest existing target marked as is the distance of the segmented area of the object, Ω represents the number of all pixels in the input CT image, and λ is the weighting coefficient.
18. 如权利要求16所述的计算机可读存储介质，其中，所述利用所述距离感知损失函数、预构建的图像检测算法及神经网络模型框架构建待训练目标物检测模型，所述神经网络模型框架包括输入层、隐藏层和输出层，包括：The computer-readable storage medium of claim 16, wherein the target object detection model to be trained is constructed by using the distance-aware loss function, a pre-built image detection algorithm and a neural network model framework, and the neural network model framework Including input layer, hidden layer and output layer, including:

    获取预构建的神经网络模型框架，所述神经网络模型框架包括输入层、隐藏层、输出层；Obtain a pre-built neural network model framework, where the neural network model framework includes an input layer, a hidden layer, and an output layer;

    将所述距离感知函数和所述图像检测算法作为隐藏层激活函数添加至所述隐藏层；adding the distance-aware function and the image detection algorithm to the hidden layer as hidden layer activation functions;

    获取预构建的Softmax函数；Get the pre-built Softmax function;

    将所述Softmax函数作为输出层激活函数添加至所述输出层，得到所述待训练目标物检测模型。The Softmax function is added to the output layer as an output layer activation function to obtain the target object detection model to be trained.
19. 如权利要求16至18中任意一项所述的计算机可读存储介质，其中，所述利用所述目标物图像样本集训练所述待训练目标物检测模型，得到训练完成的目标物检测模型，包括：The computer-readable storage medium according to any one of claims 16 to 18, wherein the target object detection model to be trained is trained by using the target object image sample set to obtain a trained target object detection model, include:

    将所述目标物图像样本集导入所述待训练目标物检测模型的输入层中，利用所述输入层中权重配置函数对所述目标物图像样本集中各个目标物图像特征进行权重分配；Importing the target image sample set into the input layer of the target detection model to be trained, and using the weight configuration function in the input layer to perform weight distribution on each target image feature in the target image sample set;

    根据权重分配结果，对所述目标物图像特征进行权重计算，得到权重特征值，并将所述权重特征值导入所述隐藏层；According to the weight distribution result, weight calculation is performed on the image feature of the target object to obtain a weight feature value, and the weight feature value is imported into the hidden layer;

    通过所述权重特征值触发所述激活函数的激活条件，使得所述距离感知损失函数根据所述权重特征值进行损失运算，得到最小化损失值，判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值；The activation condition of the activation function is triggered by the weight eigenvalue, so that the distance-aware loss function performs a loss operation according to the weight eigenvalue to obtain a minimized loss value, and judges whether the minimized loss value converges. When the minimum loss value converges, the final loss value is obtained;

    根据所述最终损失值配置所述隐藏层中激活函数的图像检测算法，完成训练的过程，得到训练完成的所述目标物检测模型。The image detection algorithm of the activation function in the hidden layer is configured according to the final loss value, the training process is completed, and the trained target detection model is obtained.
20. 如权利要求19所述的计算机可读存储介质，其中，所述判断所述最小化损失值是否收敛，当判定所述最小化损失值为收敛时，得到最终损失值，包括：The computer-readable storage medium of claim 19, wherein the determining whether the minimized loss value is converged, and when determining that the minimized loss value is converged, obtaining a final loss value, comprising:

    对产生的多个所述最小化损失值依次进行二维映射，得到损失值波动图，对所述损失值波动图中图线进行求导计算，得到求导结果；Perform two-dimensional mapping on a plurality of the generated minimized loss values in turn to obtain a loss value fluctuation graph, and perform derivation calculation on the graph line in the loss value fluctuation graph to obtain a derivation result;

    当所述求导结果小于预构建的预设数值时，判定小于所述预设数值的求导结果对应最小化损失值达到收敛，得到所述最终损失值。When the derivation result is smaller than the pre-built preset value, it is determined that the derivation result smaller than the preset value corresponds to the minimized loss value and reaches convergence, and the final loss value is obtained.
21. 如权利要求16所述的计算机可读存储介质，其中，所述获取待检测CT图像，并对所述待检测CT图像进行量化、去噪处理，得到去噪图像数据，包括：The computer-readable storage medium according to claim 16, wherein the acquiring a CT image to be detected, and performing quantization and denoising processing on the CT image to be detected, to obtain denoised image data, comprising:

    对所述待检测CT图像中各像素进行区域划分，并将划分好的像素块进行向量化处理，得到量化图像数据；Perform regional division on each pixel in the CT image to be detected, and perform vectorization processing on the divided pixel blocks to obtain quantized image data;

    利用预构建的高斯滤波器将所述量化图像数据进行二维邻域的高斯卷积运算，得到去噪图像数据。The quantized image data is subjected to a Gaussian convolution operation of a two-dimensional neighborhood by using a pre-built Gaussian filter to obtain denoised image data.
22. 如权利要求16所述的计算机可读存储介质，其中，所述利用所述目标物检测模型对所述去噪图像数据进行图像识别，得到目标物识别结果，包括：The computer-readable storage medium according to claim 16 , wherein the performing image recognition on the denoised image data by using the target object detection model to obtain a target object recognition result comprises:

    对所述去噪图像数据进行特征提取，得到特征值；performing feature extraction on the denoised image data to obtain feature values;

    将所述特征值导入所述隐藏层进行图像识别，得到目标物识别结果；importing the feature value into the hidden layer for image recognition to obtain a target object recognition result;

    将所述目标物识别结果导入所述输出层，使得所述输出层激活函数根据预构建的目标物分类标签，判定所述待检测CT图像中存在目标物的概率及对应类别的概率。The target object recognition result is imported into the output layer, so that the output layer activation function determines the probability of the target object and the probability of the corresponding category in the CT image to be detected according to the pre-built target object classification label.

Images