WO2020118826A1 - Left ventricle image segmenting method and apparatus, and device and storage medium - Google Patents
Left ventricle image segmenting method and apparatus, and device and storage medium Download PDFInfo
- Publication number
- WO2020118826A1 WO2020118826A1 PCT/CN2019/071075 CN2019071075W WO2020118826A1 WO 2020118826 A1 WO2020118826 A1 WO 2020118826A1 CN 2019071075 W CN2019071075 W CN 2019071075W WO 2020118826 A1 WO2020118826 A1 WO 2020118826A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- layer
- network
- feature
- sampling
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30048—Heart; Cardiac
Definitions
- the invention belongs to the technical field of medical image processing, and particularly relates to a left ventricular image segmentation method, device, equipment and storage medium.
- the purpose of the present invention is to provide a method, device, equipment and storage medium for left ventricular image segmentation, aiming to solve the problem that the prior art cannot provide an effective left ventricular image segmentation method, resulting in low efficiency and effect of left ventricular image segmentation Bad question.
- the present invention provides a left ventricular image segmentation method.
- the method includes the following steps:
- the image segmentation network is a deep learning network
- the image segmentation network includes a downsampling part and an upsampling part
- the downsampling part includes a first A convolution layer and a down-sampling network layer
- the up-sampling part includes a second convolution layer and an up-sampling network layer;
- the left ventricular segmented image processed by the image segmentation network is obtained and output.
- the present invention provides a left ventricular image segmentation device, the device comprising:
- An image-to-be-divided image receiving unit used to receive the left ventricle image to be divided
- An image segmentation unit for inputting the left ventricle image into a pre-trained image segmentation network for segmentation the image segmentation network is a deep learning network, and the image segmentation network includes a downsampling part and an upsampling part, the The down-sampling section includes a first convolution layer and a down-sampling network layer, and the up-sampling section includes a second convolution layer and an up-sampling network layer;
- the divided image output unit is used to obtain and output the left ventricular divided image obtained by the image division network processing.
- the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, which is implemented when the processor executes the computer program
- a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, which is implemented when the processor executes the computer program
- the present invention also provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the computer program can be implemented as described in the above-mentioned left ventricular image segmentation method A step of.
- the invention receives the left ventricle image to be segmented, and the trained image segmentation network divides the left ventricular image to obtain the segmented left ventricular segmented image and outputs it.
- the image segmentation network is a deep learning network, including an upsampling part And the down-sampling part, the up-sampling part includes the first convolution layer and the down-sampling network layer, the up-sampling part includes the second convolution layer and the up-sampling network layer, so that the left ventricular image is automatically segmented by the image segmentation network of the above structure , Effectively improve the efficiency and effect of left ventricular image segmentation.
- FIG. 1 is an implementation flowchart of a left ventricular image segmentation method according to Embodiment 1 of the present invention
- FIG. 2 is a flowchart of an implementation of a left ventricular image segmentation method provided by Embodiment 2 of the present invention
- FIG. 3 is a schematic structural diagram of a left ventricular image segmentation device provided in Embodiment 3 of the present invention.
- FIG. 4 is a schematic diagram of a preferred structure of a left ventricular image segmentation device provided in Embodiment 3 of the present invention.
- FIG. 5 is a schematic structural diagram of a computer device according to Embodiment 4 of the present invention.
- FIG. 1 shows an implementation process of a method for segmenting a left ventricle image provided by Embodiment 1 of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown. The details are as follows:
- step S101 receive the left ventricle image to be segmented
- the embodiments of the present invention are applicable to devices such as computers and servers that support image processing.
- the left ventricular image to be segmented may be a left ventricular image obtained from a medical database published on the Internet, or a left ventricular image provided by a hospital or doctor, or a left ventricular image scanned by a medical scanning device such as CT or MRI.
- the embodiment of the present invention does not involve the scanning process of the left ventricle image, and will not be described here.
- the left ventricle image is input into a pre-trained image segmentation network for segmentation.
- the image segmentation network is a deep learning network, including a down-sampling part and an up-sampling part, and the down-sampling part includes a first convolutional layer and down-sampling For the network layer, the upsampling part includes a second convolution layer and an upsampling network layer.
- the image segmentation network is pre-trained, where the image segmentation network is a deep network, including a downsampling part and an upsampling part, and the downsampling part includes a first convolution layer and a downsampling network layer, and the upsampling part Including the second convolutional layer and the upsampling network layer.
- the left ventricular image After obtaining the left ventricular image, input the left ventricular image to the first convolutional layer to extract the image features of the left ventricular image, and then input the image features to the down-sampling network layer, which will be processed by each layer of the down-sampling network layer in turn
- the image features of the image are input to the upsampling network layer for processing to obtain the image features processed by each layer of the downsampling network layer and each layer of the downsampling network layer, and then the second convolution layer performs a convolution operation to realize the left ventricular image Of division.
- each down-sampling network layer includes a first feature convolution layer and a second feature convolution layer
- each up-sampling network layer includes a feature deconvolution layer and a first feature convolution layer, thereby passing different convolution layers
- each image features processed by the down-sampling network layer of each layer enter the first-layer up-sampling network layer, these image features are processed through the feature deconvolution layer in the first-layer up-sampling network layer, and then the The first feature convolutional layer in an up-sampling network layer processes the image features processed by the feature deconvolution layer.
- the downsampling part in the image segmentation network includes a first convolution layer and a three-layer downsampling network layer
- the upsampling part in the image segmentation network includes a three-layer upsampling network layer and a three-layer second convolution Layers
- the first and second convolution layers have different convolution kernel sizes.
- the first feature convolution layer and the second feature convolution layer have different step sizes to improve the image segmentation network. The processing effect of the left ventricular image features.
- the convolution kernel of the first convolutional layer has a size of 5*5
- the convolution kernel of the second convolutional layer has a size of 1*1
- the convolution kernel of the first feature convolutional layer has a size of 5*5 and
- the step size is 3
- the convolution kernel of the second feature convolutional layer is 5*5 in size and the step size is 1
- the convolution kernel size of the feature deconvolution layer is 4*4 and the step size is 3.
- step S103 the left ventricular segmented image obtained by the image segmentation network processing is obtained and output.
- the left ventricular segmented image processed by the image segmentation network is a left ventricular contour image segmented from the left ventricular image to be segmented, which can help the doctor visually observe the patient's left ventricular status.
- the convolution calculation formula is:
- I represents the left ventricle image to be segmented
- m and n are the width and height of the convolution kernel in the first convolution layer
- K l represents the lth convolution kernel in the first convolution layer
- i and j are The position of the image pixel in the left ventricular image.
- the formula for processing the image features output by the upper layer up-sampling network through the second convolution layer is also the above formula.
- I represents the image features output by the one-layer up-sampling network
- m and n are the second The width and height of the convolution kernel in the convolution layer
- K l represents the lth convolution kernel in the second convolution layer
- i and j are the positions of image pixels in the image feature.
- these image features are nonlinearly activated to improve the segmentation effect of the image segmentation network on the left ventricle image.
- the formula for nonlinear activation is:
- S l (i, j) is the image feature extracted from the first convolution layer
- z is the number of extracted image features
- relu() is the nonlinear activation function
- f(x) is the nonlinear activation function.
- the image features received by the first feature convolution layer in the down-sampling network layer, the second feature convolution layer in the down-sampling network layer, or the first feature convolution layer in the up-sampling network When processing, it includes the feature convolution operation and the non-linear change operation on the image features to improve the processing effect on the image features.
- feature convolution operations are performed on the image features input to the first feature convolution layer, and the routing coefficients are performed by the dynamic routing algorithm Update, and then input the image features processed by the feature convolution operation into a preset nonlinear change formula, and perform a nonlinear change operation to improve the processing effect of the first feature convolution on the image features.
- S xy is the image feature processed by the feature convolution operation
- N is the number of these image features
- p is the number of network layers in the image segmentation network where the current down-sampling network layer (or current up-sampling network layer) is located
- x and y are the image features in Position in the left ventricle image.
- V xy is the image feature processed by the nonlinear change operation.
- routing coefficient When the routing coefficient is updated by the dynamic routing algorithm, it is updated iteratively, and the d-th iteration process is as follows:
- the image features input to the layer network are subjected to feature convolution processing, and the processing formula is:
- the left ventricular image is segmented by a trained image segmentation network to obtain the segmented left ventricular segmented image and output
- the image segmentation network is a deep learning network, including an upsampling part and a downsampling Partially, the upsampling part includes the first convolutional layer and the downsampling network layer, the upsampling part includes the second convolutional layer and the upsampling network layer, and the downsampling network layer includes the first feature convolutional layer and the second feature convolutional layer
- the up-sampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so that the left ventricular image is automatically segmented by the image segmentation network with the above structure, which effectively improves the efficiency and effect of left ventricular image segmentation.
- FIG. 2 shows an implementation flow of a method for segmenting a left ventricle image provided by Embodiment 2 of the present invention. For ease of description, only parts related to the embodiment of the present invention are shown, and details are as follows:
- step S201 the acquired left ventricular training image is acquired.
- step S202 the left ventricle training image is input into the image segmentation network, and the image segmentation network is trained through a preset optimization algorithm, which is an Adam learning rate adaptive optimization algorithm.
- a preset optimization algorithm which is an Adam learning rate adaptive optimization algorithm.
- the network structure of the image segmentation network has been described in detail in the first embodiment.
- the image segmentation network is constructed according to the above network results. Collect multiple left ventricular training images and use them as training samples for the image segmentation network, input them into the image segmentation network one by one, and use Adam (adaptive moment estimation) learning rate adaptive optimization algorithm to train the image segmentation network to obtain training Good image segmentation network.
- Adam adaptive moment estimation
- step S203 receive the left ventricle image to be segmented
- step S204 the left ventricular image is input into a pre-trained image segmentation network for segmentation.
- the image segmentation network includes a downsampling part and an upsampling part.
- the downsampling part includes a first convolutional layer and a downsampling network layer.
- Upsampling Part includes the second convolution layer and the up-sampling network layer;
- step S205 the left ventricular segmented image obtained by the image segmentation network processing is obtained and output.
- the image segmentation network is trained by the Adam learning rate adaptive optimization algorithm, and the trained image segmentation network segments the left ventricle image to obtain the segmented left ventricular segmented image and output it.
- the image segmentation The network is a deep learning network, including an upsampling part and a downsampling part.
- the upsampling part includes a first convolutional layer and a downsampling network layer.
- the upsampling part includes a second convolutional layer and an upsampling network layer.
- the downsampling network layer includes The first feature convolution layer and the second feature convolution layer, the up-sampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so as to automatically optimize the left ventricular image segmentation and effectively improve the left ventricular image Efficiency and effect of segmentation.
- FIG. 3 shows a structure of a left ventricle image segmentation device provided in Embodiment 3 of the present invention. For ease of explanation, only parts related to the embodiment of the present invention are shown, including:
- the image-to-be-divided receiving unit 31 is configured to receive the left ventricle image to be divided.
- the image segmentation unit 32 is used to input the left ventricle image into a pre-trained image segmentation network for segmentation.
- the image segmentation network is a deep learning network.
- the image segmentation network includes a downsampling part and an upsampling part.
- the downsampling part includes the first volume For the accumulation layer and the down-sampling network layer
- the up-sampling part includes the second convolution layer and the up-sampling network layer.
- the image segmentation network is pre-trained. After obtaining the left ventricular image, input the left ventricular image to the first convolutional layer to extract the image features of the left ventricular image, and then input the image features to the down-sampling network layer, which will be processed by each layer of the down-sampling network layer in turn The image features of the image are input to the upsampling network layer for processing to obtain the image features processed by each layer of the downsampling network layer and each layer of the downsampling network layer, and then the second convolution layer performs a convolution operation to realize the left ventricular image Of division.
- each down-sampling network layer includes a first feature convolution layer and a second feature convolution layer
- each up-sampling network layer includes a feature deconvolution layer and a first feature convolution layer, thereby passing different convolution layers
- each image features processed by the down-sampling network layer of each layer enter the first-layer up-sampling network layer, these image features are processed through the feature deconvolution layer in the first-layer up-sampling network layer, and then the The first feature convolutional layer in an up-sampling network layer processes the image features processed by the feature deconvolution layer.
- the downsampling part in the image segmentation network includes a first convolution layer and a three-layer downsampling network layer
- the upsampling part in the image segmentation network includes a three-layer upsampling network layer and a three-layer second convolution Layers
- the first and second convolution layers have different convolution kernel sizes.
- the first feature convolution layer and the second feature convolution layer have different step sizes to improve the image segmentation network. The processing effect of the left ventricular image features.
- the divided image output unit 33 is used to obtain and output a left ventricular divided image obtained by image segmentation network processing.
- the left ventricular segmented image processed by the image segmentation network is a left ventricular contour image segmented from the left ventricular image to be segmented, which can help the doctor visually observe the patient's left ventricular status.
- the convolution calculation formula is:
- I represents the left ventricle image to be segmented
- m and n are the width and height of the convolution kernel in the first convolution layer
- K l represents the lth convolution kernel in the first convolution layer
- i and j are The position of the image pixel in the left ventricular image.
- the formula for processing the image features output by the upper layer up-sampling network through the second convolution layer is also the above formula.
- I represents the image features output by the one-layer up-sampling network
- m and n are the second The width and height of the convolution kernel in the convolution layer
- K l represents the lth convolution kernel in the second convolution layer
- i and j are the positions of image pixels in the image feature.
- these image features are non-linearly activated to improve the segmentation effect of the image segmentation network on the left ventricle image.
- the formula for nonlinear activation is:
- S l (i, j) is the image feature extracted from the first convolution layer
- z is the number of extracted image features
- relu() is the nonlinear activation function
- f(x) is the nonlinear activation function.
- the image features received by the first feature convolution layer in the down-sampling network layer, the second feature convolution layer in the down-sampling network layer, or the first feature convolution layer in the up-sampling network When processing, it includes the feature convolution operation and the non-linear change operation on the image features to improve the processing effect on the image features.
- feature convolution operations are performed on the image features input to the first feature convolution layer, and the routing coefficients are performed by the dynamic routing algorithm Update, and then input the image features processed by the feature convolution operation into a preset nonlinear change formula, and perform a nonlinear change operation to improve the processing effect of the first feature convolution on the image features.
- S xy is the image feature processed by the feature convolution operation
- N is the number of these image features
- p is the number of network layers in the image segmentation network where the current down-sampling network layer (or current up-sampling network layer) is located
- x and y are the image features in Position in the left ventricle image.
- V xy is the image feature processed by the nonlinear change operation.
- routing coefficient When the routing coefficient is updated by the dynamic routing algorithm, it is updated iteratively, and the d-th iteration process is as follows:
- the image features input to the layer network are subjected to feature convolution processing, and the processing formula is:
- the image segmentation unit 32 further includes:
- the image feature extraction unit 421 is configured to perform feature extraction on the left ventricular image through the first convolution layer to generate image features corresponding to the left ventricular image;
- the image feature processing unit 422 is used to input the image features to the down-sampling network layer connected to the first convolutional layer, and sequentially process through each layer of the down-sampling network layer, each layer of the up-sampling network layer, and the second convolutional layer to obtain Split image of left ventricle.
- an image segmentation network is constructed according to the above network results.
- Collect multiple left ventricular training images and use them as training samples for the image segmentation network input them into the image segmentation network one by one, and use Adam (adaptive moment estimation) learning rate adaptive optimization algorithm to train the image segmentation network to obtain training A good image segmentation network, so as to improve the automatic segmentation effect of the image segmentation network on the left ventricle image through the adaptive optimization algorithm.
- Adam adaptive moment estimation
- the image segmentation network is trained by the Adam learning rate adaptive optimization algorithm, and the trained image segmentation network segments the left ventricle image to obtain the segmented left ventricular segmented image and output it.
- the image segmentation The network is a deep learning network, including an upsampling part and a downsampling part.
- the upsampling part includes a first convolutional layer and a downsampling network layer.
- the upsampling part includes a second convolutional layer and an upsampling network layer.
- the downsampling network layer includes The first feature convolution layer and the second feature convolution layer, the up-sampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so as to automatically optimize the left ventricular image segmentation and effectively improve the left ventricular image Efficiency and effect of segmentation.
- each unit of a left ventricular image segmentation device may be implemented by a corresponding hardware or software unit, and each unit may be an independent software and hardware unit, or may be integrated into one software and hardware unit, which is not used here To limit the invention.
- FIG. 5 shows a structure of a computer device provided by Embodiment 5 of the present invention. For convenience of description, only parts related to the embodiment of the present invention are shown.
- the automobile 5 of the embodiment of the present invention includes a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50.
- the processor 50 executes the computer program 52, the steps in the above method embodiments are implemented, for example, steps S101 to S103 shown in FIG. 1.
- the processor 50 executes the computer program 52, the functions of the units in the foregoing device embodiments are realized, for example, the functions of the units 31 to 33 shown in FIG.
- the left ventricular image is segmented by a trained image segmentation network to obtain the segmented left ventricular segmented image and output
- the image segmentation network is a deep learning network, including an upsampling part and a downsampling Partially, the upsampling part includes the first convolutional layer and the downsampling network layer, the upsampling part includes the second convolutional layer and the upsampling network layer, and the downsampling network layer includes the first feature convolutional layer and the second feature convolutional layer
- the up-sampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so that the left ventricular image is automatically segmented by the image segmentation network with the above structure, which effectively improves the efficiency and effect of left ventricular image segmentation.
- a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented, for example, FIG. 1 Steps S101 to S103 shown.
- the functions of the units in the foregoing device embodiments are realized, for example, the functions of the units 31 to 33 shown in FIG. 3.
- the left ventricular image is segmented by the trained image segmentation network to obtain the segmented left ventricular segmented image and output.
- the image segmentation network is a deep learning network, including an upsampling part and a downsampling Partially, the upsampling part includes the first convolutional layer and the downsampling network layer, the upsampling part includes the second convolutional layer and the upsampling network layer, and the downsampling network layer includes the first feature convolutional layer and the second feature convolutional layer
- the upsampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so that the left ventricular image is automatically segmented by the image segmentation network with the above structure, which effectively improves the efficiency and effect of left ventricular image segmentation.
- the computer-readable storage medium in the embodiments of the present invention may include any entity or device capable of carrying computer program code, and a recording medium, such as ROM/RAM, magnetic disk, optical disk, flash memory, and other memories.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
A left ventricle image segmenting method and apparatus, and a device and a storage medium. The method comprises: receiving a left ventricle image to be segmented (S101); inputting the left ventricle image into a trained image segmentation network for segmentation, wherein the image segmentation network is a deep learning network and comprises a down-sampling section and an up-sampling section, the down-sampling section comprises a first convolutional layer and a down-sampling network layer, and the up-sampling section comprises a second convolutional layer and an up-sampling network layer (S102); obtaining a left ventricle segmented image obtained by image segmentation network processing and outputting same (S103). Therefore, automatic segmentation of the left ventricle image is achieved, the efficiency and the effect of left ventricle image segmentation are improved, and the method is suitable for the technical field of medical image processing.
Description
本发明属于医学图像处理技术领域，尤其涉及一种左心室图像分割方法、装置、设备及存储介质。The invention belongs to the technical field of medical image processing, and particularly relates to a left ventricular image segmentation method, device, equipment and storage medium.
在心血管疾病的早期诊断中，需要对患者心脏进行扫描成像，并在扫描到的图像上对相应的左心室轮廓进行分割。扫描过程中，血液流动会带来成像伪影，加上人体结构的复杂性、软组织的不规则性，如何对左心室图像进行准确分割有着非常重要的临床价值。In the early diagnosis of cardiovascular disease, it is necessary to scan and image the heart of the patient, and segment the corresponding left ventricular contour on the scanned image. During the scanning process, blood flow will bring imaging artifacts, coupled with the complexity of the human body structure and the irregularity of soft tissue, how to accurately segment the left ventricle image has very important clinical value.
传统对左心室图像进行分割的方式是由专业医生进行手动分割，操作繁琐，效率不高，而且手动分割容易受人工主观影响，导致左心室图像分割的准确度不高。The traditional way of segmenting left ventricular images is manual segmentation by professional doctors, which is tedious and inefficient. Manual segmentation is easily affected by manual subjective, resulting in low accuracy of left ventricular image segmentation.
发明内容Summary of the invention
本发明的目的在于提供一种左心室图像分割方法、装置、设备及存储介质，旨在解决由于现有技术无法提供一种有效的左心室图像分割方法，导致左心室图像分割效率不高且效果不佳的问题。The purpose of the present invention is to provide a method, device, equipment and storage medium for left ventricular image segmentation, aiming to solve the problem that the prior art cannot provide an effective left ventricular image segmentation method, resulting in low efficiency and effect of left ventricular image segmentation Bad question.
一方面，本发明提供了一种左心室图像分割方法，所述方法包括下述步骤：In one aspect, the present invention provides a left ventricular image segmentation method. The method includes the following steps:
接收待分割的左心室图像；Receive the left ventricle image to be segmented;
将所述左心室图像输入预先训练好的图像分割网络中进行分割，所述图像分割网络为深度学习网络，所述图像分割网络包括下采样部分和上采样部分，所述下采样部分包括第一卷积层和下采样网络层，所述上采样部分包括第二卷积层和上采样网络层；Input the left ventricular image into a pre-trained image segmentation network for segmentation, the image segmentation network is a deep learning network, the image segmentation network includes a downsampling part and an upsampling part, and the downsampling part includes a first A convolution layer and a down-sampling network layer, the up-sampling part includes a second convolution layer and an up-sampling network layer;
获得所述图像分割网络处理得到的左心室分割图像并输出。The left ventricular segmented image processed by the image segmentation network is obtained and output.
另一方面，本发明提供了一种左心室图像分割装置，所述装置包括：In another aspect, the present invention provides a left ventricular image segmentation device, the device comprising:
待分割图像接收单元，用于接收待分割的左心室图像；An image-to-be-divided image receiving unit, used to receive the left ventricle image to be divided;
图像分割单元，用于将所述左心室图像输入预先训练好的图像分割网络中进行分割，所述图像分割网络为深度学习网络，所述图像分割网络包括下采样部分和上采样部分，所述下采样部分包括第一卷积层和下采样网络层，所述上采样部分包括第二卷积层和上采样网络层；以及An image segmentation unit for inputting the left ventricle image into a pre-trained image segmentation network for segmentation, the image segmentation network is a deep learning network, and the image segmentation network includes a downsampling part and an upsampling part, the The down-sampling section includes a first convolution layer and a down-sampling network layer, and the up-sampling section includes a second convolution layer and an up-sampling network layer; and
分割图像输出单元，用于获得所述图像分割网络处理得到的左心室分割图像并输出。The divided image output unit is used to obtain and output the left ventricular divided image obtained by the image division network processing.
另一方面，本发明还提供了一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如上述一种左心室图像分割方法所述的步骤。On the other hand, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, which is implemented when the processor executes the computer program The steps are as described above for a method of segmenting left ventricle images.
另一方面，本发明还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现如上述一种左心室图像分割方法所述的步骤。On the other hand, the present invention also provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the computer program can be implemented as described in the above-mentioned left ventricular image segmentation method A step of.
本发明接收待分割的左心室图像，由训练好的图像分割网络对左心室图像进行分割，获得分割后得到的左心室分割图像并输出，其中，图像分割网络为深度学习网络，包括上采样部分和下采样部分，上采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层，从而借助上述结构的图像分割网络对左心室图像进行自动分割，有效地提高左心室图像分割的效率和效果。The invention receives the left ventricle image to be segmented, and the trained image segmentation network divides the left ventricular image to obtain the segmented left ventricular segmented image and outputs it. The image segmentation network is a deep learning network, including an upsampling part And the down-sampling part, the up-sampling part includes the first convolution layer and the down-sampling network layer, the up-sampling part includes the second convolution layer and the up-sampling network layer, so that the left ventricular image is automatically segmented by the image segmentation network of the above structure , Effectively improve the efficiency and effect of left ventricular image segmentation.
图1是本发明实施例一提供的一种左心室图像分割方法的实现流程图；FIG. 1 is an implementation flowchart of a left ventricular image segmentation method according to Embodiment 1 of the present invention;
图2是本发明实施例二提供的一种左心室图像分割方法的实现流程图；2 is a flowchart of an implementation of a left ventricular image segmentation method provided by Embodiment 2 of the present invention;
图3是本发明实施例三提供的一种左心室图像分割装置的结构示意图；3 is a schematic structural diagram of a left ventricular image segmentation device provided in Embodiment 3 of the present invention;
图4是本发明实施例三提供的一种左心室图像分割装置的优选结构示意图；以及4 is a schematic diagram of a preferred structure of a left ventricular image segmentation device provided in Embodiment 3 of the present invention; and
图5是本发明实施例四提供的计算机设备的结构示意图。5 is a schematic structural diagram of a computer device according to Embodiment 4 of the present invention.
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not intended to limit the present invention.
以下结合具体实施例对本发明的具体实现进行详细描述：The following describes the specific implementation of the present invention in detail with reference to specific embodiments:
实施例一：Example one:
图1示出了本发明实施例一提供的一种左心室图像分割方法的实现流程，为了便于说明，仅示出了与本发明实施例相关的部分，详述如下：FIG. 1 shows an implementation process of a method for segmenting a left ventricle image provided by Embodiment 1 of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown. The details are as follows:
在步骤S101中，接收待分割的左心室图像；In step S101, receive the left ventricle image to be segmented;
本发明实施例适用于计算机、服务器等支持图像处理的设备。待分割的左心室图像可为从网上公开的医学数据库中获取的左心室图像，也可以为医院或医生提供的左心室图像，或者由CT、MRI等医学扫描设备扫描到的左心室图像。本发明实施例并不涉及左心室图像的扫描过程，在此不作描述。The embodiments of the present invention are applicable to devices such as computers and servers that support image processing. The left ventricular image to be segmented may be a left ventricular image obtained from a medical database published on the Internet, or a left ventricular image provided by a hospital or doctor, or a left ventricular image scanned by a medical scanning device such as CT or MRI. The embodiment of the present invention does not involve the scanning process of the left ventricle image, and will not be described here.
在步骤S102中，将左心室图像输入预先训练好的图像分割网络中进行分割，图像分割网络为深度学习网络，包括下采样部分和上采样部分，下采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层。In step S102, the left ventricle image is input into a pre-trained image segmentation network for segmentation. The image segmentation network is a deep learning network, including a down-sampling part and an up-sampling part, and the down-sampling part includes a first convolutional layer and down-sampling For the network layer, the upsampling part includes a second convolution layer and an upsampling network layer.
在本发明实施例中，预先训练好图像分割网络，其中，图像分割网络为深度网络，包括下采样部分和上采样部分，下采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层。在获得左心室图像后，将左心室图像输入至第一卷积层，提取得到左心室图像的图像特征，再将图像特征输入至下采样网络层，将依次经每层下采样网络层处理后的图像特征输入 至上采样网络层进行处理，获得依次将每层下采样网络层、每层下采样网络层处理后的图像特征，再由第二卷积层进行卷积操作，实现对左心室图像的分割。In the embodiment of the present invention, the image segmentation network is pre-trained, where the image segmentation network is a deep network, including a downsampling part and an upsampling part, and the downsampling part includes a first convolution layer and a downsampling network layer, and the upsampling part Including the second convolutional layer and the upsampling network layer. After obtaining the left ventricular image, input the left ventricular image to the first convolutional layer to extract the image features of the left ventricular image, and then input the image features to the down-sampling network layer, which will be processed by each layer of the down-sampling network layer in turn The image features of the image are input to the upsampling network layer for processing to obtain the image features processed by each layer of the downsampling network layer and each layer of the downsampling network layer, and then the second convolution layer performs a convolution operation to realize the left ventricular image Of division.
优选地，每层下采样网络层包括第一特征卷积层和第二特征卷积层，每层上采样网络层包括特征反卷积层和第一特征卷积层，从而通过不同卷积层的结合，提高图像分割网络对左心室图像特征的处理效果。其中，将每层下采样网络层处理后的图像特征进入第一层上采样网络层时，先通过第一层上采样网络层中的特征反卷积层对这些图像特征进行处理，再由第一层上采样网络层中的第一特征卷积层对该特征反卷积层处理的图像特征进行处理。Preferably, each down-sampling network layer includes a first feature convolution layer and a second feature convolution layer, and each up-sampling network layer includes a feature deconvolution layer and a first feature convolution layer, thereby passing different convolution layers To improve the processing effect of image segmentation network on left ventricular image features. Among them, when the image features processed by the down-sampling network layer of each layer enter the first-layer up-sampling network layer, these image features are processed through the feature deconvolution layer in the first-layer up-sampling network layer, and then the The first feature convolutional layer in an up-sampling network layer processes the image features processed by the feature deconvolution layer.
进一步优选地，图像分割网络中的下采样部分包括一层第一卷积层和三层下采样网络层，图像分割网络中的上采样部分包括三层上采样网络层和三层第二卷积层，第一卷积层和第二卷积层的卷积核大小不同，在上采样网络层中，第一特征卷积层与第二特征卷积层的步长不同，以提高图像分割网络对左心室图像特征的处理效果。作为示例地，第一卷积层的卷积核为5*5大小，第二卷积层的卷积核为1*1大小，第一特征卷积层的卷积核为5*5大小且步长为3，第二特征卷积层的卷积核为5*5大小且步长为1，特征反卷积层的卷积核大小为4*4且步长为3。Further preferably, the downsampling part in the image segmentation network includes a first convolution layer and a three-layer downsampling network layer, and the upsampling part in the image segmentation network includes a three-layer upsampling network layer and a three-layer second convolution Layers, the first and second convolution layers have different convolution kernel sizes. In the upsampling network layer, the first feature convolution layer and the second feature convolution layer have different step sizes to improve the image segmentation network. The processing effect of the left ventricular image features. As an example, the convolution kernel of the first convolutional layer has a size of 5*5, the convolution kernel of the second convolutional layer has a size of 1*1, and the convolution kernel of the first feature convolutional layer has a size of 5*5 and The step size is 3, the convolution kernel of the second feature convolutional layer is 5*5 in size and the step size is 1, the convolution kernel size of the feature deconvolution layer is 4*4 and the step size is 3.
在步骤S103中，获得图像分割网络处理得到的左心室分割图像并输出。In step S103, the left ventricular segmented image obtained by the image segmentation network processing is obtained and output.
在本发明实施例中，由图像分割网络处理得到的左心室分割图像，为待分割的左心室图像中分割出左心室轮廓图像，可帮助医生直观地观察到患者的左心室状况。In the embodiment of the present invention, the left ventricular segmented image processed by the image segmentation network is a left ventricular contour image segmented from the left ventricular image to be segmented, which can help the doctor visually observe the patient's left ventricular status.
优选地，在通过第一卷积层对到待分割的左心室图像进行处理时，卷积计算公式为：Preferably, when the left ventricle image to be divided is processed through the first convolution layer, the convolution calculation formula is:
进一步优选地，在获得经过第一卷积层提取到的图像特征后，对这些图像特征进行非线性激活，以提高图像分割网络对左心室图像的分割效果。其中，非线性激活的公式为：Further preferably, after the image features extracted through the first convolution layer are obtained, these image features are nonlinearly activated to improve the segmentation effect of the image segmentation network on the left ventricle image. Among them, the formula for nonlinear activation is:
优选地，在通过下采样网络层中的第一特征卷积层、下采样网络层中的第二特征卷积层、或者上采样网络中的第一特征卷积层对其接收到的图像特征进行处理时，包括对图像特征进行特征卷积操作和非线性变化操作，以提高对图像特征的处理效果。Preferably, the image features received by the first feature convolution layer in the down-sampling network layer, the second feature convolution layer in the down-sampling network layer, or the first feature convolution layer in the up-sampling network When processing, it includes the feature convolution operation and the non-linear change operation on the image features to improve the processing effect on the image features.
进一步优选地，根据第一特征卷积层对应的网络权重和动态路由算法中的路由系数，对输入至该第一特征卷积层的图像特征进行特征卷积操作，路由系数通过动态路由算法进行更新，再将特征卷积操作处理后的图像特征输入预设的非线性变化公式，进行非线性变化操作，以提高第一特征卷积对图像特征的处理效果。Further preferably, according to the network weights corresponding to the first feature convolution layer and the routing coefficients in the dynamic routing algorithm, feature convolution operations are performed on the image features input to the first feature convolution layer, and the routing coefficients are performed by the dynamic routing algorithm Update, and then input the image features processed by the feature convolution operation into a preset nonlinear change formula, and perform a nonlinear change operation to improve the processing effect of the first feature convolution on the image features.
其中，特征卷积操作的公式为：Among them, the formula of feature convolution operation is:
其中，非线性变化公式为：Among them, the nonlinear change formula is:
在通过动态路由算法更新路由系数时，通过迭代方式进行更新，其中第d次迭代过程如下：When the routing coefficient is updated by the dynamic routing algorithm, it is updated iteratively, and the d-th iteration process is as follows:
(1)获取位于图像分割网络p层的下采样网络(或上采样网络)的路由系数：(1) Obtain the routing coefficient of the down-sampling network (or up-sampling network) at the p-layer of the image segmentation network:
(2)在位于图像分割网络p+1层的下采样网络(或上采样网络)中，对输入该层网络的图像特征进行特征卷积处理，处理公式为：(2) In the down-sampling network (or up-sampling network) located in the p+1 layer of the image segmentation network, the image features input to the layer network are subjected to feature convolution processing, and the processing formula is:
(3)在位于图像分割网络p+1层的下采样网络(或上采样网络)中，对经特征卷积处理的图像特征进行非线性变化操作，公式为：(3) In the down-sampling network (or up-sampling network) located in the p+1 layer of the image segmentation network, the non-linear change operation is performed on the image features subjected to feature convolution processing, the formula is:
(4)更新参数
更新公式如下：
(4) Update parameters The update formula is as follows:
在本发明实施例中，由训练好的图像分割网络对左心室图像进行分割，获得分割后得到的左心室分割图像并输出，其中，图像分割网络为深度学习网络，包括上采样部分和下采样部分，上采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层，下采样网络层包括第一特征卷积层和第二特征卷积层，上采样网络层包括特征反卷积层和第一特征反卷积层，从而借助上述结构的图像分割网络对左心室图像进行自动分割，有效地提高左心室图像分割的效率和效果。In the embodiment of the present invention, the left ventricular image is segmented by a trained image segmentation network to obtain the segmented left ventricular segmented image and output, wherein the image segmentation network is a deep learning network, including an upsampling part and a downsampling Partially, the upsampling part includes the first convolutional layer and the downsampling network layer, the upsampling part includes the second convolutional layer and the upsampling network layer, and the downsampling network layer includes the first feature convolutional layer and the second feature convolutional layer The up-sampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so that the left ventricular image is automatically segmented by the image segmentation network with the above structure, which effectively improves the efficiency and effect of left ventricular image segmentation.
实施例二：Example 2:
图2示出了本发明实施例二提供的一种左心室图像分割方法的实现流程，为了便于说明，仅示出了与本发明实施例相关的部分，详述如下：FIG. 2 shows an implementation flow of a method for segmenting a left ventricle image provided by Embodiment 2 of the present invention. For ease of description, only parts related to the embodiment of the present invention are shown, and details are as follows:
在步骤S201中，获取采集到的左心室训练图像。In step S201, the acquired left ventricular training image is acquired.
在步骤S202中，将左心室训练图像输入图像分割网络中，并通过预设的优化算法对图像分割网络进行训练，优化算法为Adam学习率自适应优化算法。In step S202, the left ventricle training image is input into the image segmentation network, and the image segmentation network is trained through a preset optimization algorithm, which is an Adam learning rate adaptive optimization algorithm.
在本发明实施例中，在实施例一中已详细描述了图像分割网络的网络结构，在训练之前，按照上述网络结果构建图像分割网络。采集多张左心室训练图像，用作图像分割网络的训练样本，一一输入图像分割网络之中，并采用Adam(适应性矩估计)学习率自适应优化算法对图像分割网络进行训练，获得训练好的图像分割网络。In the embodiment of the present invention, the network structure of the image segmentation network has been described in detail in the first embodiment. Before training, the image segmentation network is constructed according to the above network results. Collect multiple left ventricular training images and use them as training samples for the image segmentation network, input them into the image segmentation network one by one, and use Adam (adaptive moment estimation) learning rate adaptive optimization algorithm to train the image segmentation network to obtain training Good image segmentation network.
在步骤S203中，接收待分割的左心室图像；In step S203, receive the left ventricle image to be segmented;
在步骤S204中，将左心室图像输入预先训练好的图像分割网络中进行分割，图像分割网络包括下采样部分和上采样部分，下采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层；In step S204, the left ventricular image is input into a pre-trained image segmentation network for segmentation. The image segmentation network includes a downsampling part and an upsampling part. The downsampling part includes a first convolutional layer and a downsampling network layer. Upsampling Part includes the second convolution layer and the up-sampling network layer;
在步骤S205中，获得图像分割网络处理得到的左心室分割图像并输出。In step S205, the left ventricular segmented image obtained by the image segmentation network processing is obtained and output.
在本发明实施例中，步骤S203～步骤S205可参照实施例一中相应步骤的详细描述，在此不再赘述。In this embodiment of the present invention, for steps S203 to S205, reference may be made to the detailed description of the corresponding steps in Embodiment 1, and details are not described herein again.
在本发明实施例中，通过Adam学习率自适应优化算法训练图像分割网络，由训练好的图像分割网络对左心室图像进行分割，获得分割后得到的左心室分割图像并输出，其中，图像分割网络为深度学习网络，包括上采样部分和下采样部分，上采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层，下采样网络层包括第一特征卷积层和第二特征卷积层，上采样网络层包括特征反卷积层和第一特征反卷积层，从而实现对左心室图像进行自动优化分割，有效地提高左心室图像分割的效率和效果。In the embodiment of the present invention, the image segmentation network is trained by the Adam learning rate adaptive optimization algorithm, and the trained image segmentation network segments the left ventricle image to obtain the segmented left ventricular segmented image and output it. Among them, the image segmentation The network is a deep learning network, including an upsampling part and a downsampling part. The upsampling part includes a first convolutional layer and a downsampling network layer. The upsampling part includes a second convolutional layer and an upsampling network layer. The downsampling network layer includes The first feature convolution layer and the second feature convolution layer, the up-sampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so as to automatically optimize the left ventricular image segmentation and effectively improve the left ventricular image Efficiency and effect of segmentation.
实施例三：Example three:
图3示出了本发明实施例三提供的一种左心室图像分割装置的结构，为了便于说明，仅示出了与本发明实施例相关的部分，其中包括：FIG. 3 shows a structure of a left ventricle image segmentation device provided in Embodiment 3 of the present invention. For ease of explanation, only parts related to the embodiment of the present invention are shown, including:
待分割图像接收单元31，用于接收待分割的左心室图像。The image-to-be-divided receiving unit 31 is configured to receive the left ventricle image to be divided.
图像分割单元32，用于将左心室图像输入预先训练好的图像分割网络中进行分割，图像分割网络为深度学习网络，图像分割网络包括下采样部分和上采样部分，下采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层。The image segmentation unit 32 is used to input the left ventricle image into a pre-trained image segmentation network for segmentation. The image segmentation network is a deep learning network. The image segmentation network includes a downsampling part and an upsampling part. The downsampling part includes the first volume For the accumulation layer and the down-sampling network layer, the up-sampling part includes the second convolution layer and the up-sampling network layer.
在本发明实施例中，预先训练好图像分割网络。在获得左心室图像后，将左心室图像输入至第一卷积层，提取得到左心室图像的图像特征，再将图像特征输入至下采样网络层，将依次经每层下采样网络层处理后的图像特征输入至上采样网络层进行处理，获得依次将每层下采样网络层、每层下采样网络层处理后的图像特征，再由第二卷积层进行卷积操作，实现对左心室图像的分割。In the embodiment of the present invention, the image segmentation network is pre-trained. After obtaining the left ventricular image, input the left ventricular image to the first convolutional layer to extract the image features of the left ventricular image, and then input the image features to the down-sampling network layer, which will be processed by each layer of the down-sampling network layer in turn The image features of the image are input to the upsampling network layer for processing to obtain the image features processed by each layer of the downsampling network layer and each layer of the downsampling network layer, and then the second convolution layer performs a convolution operation to realize the left ventricular image Of division.
优选地，每层下采样网络层包括第一特征卷积层和第二特征卷积层，每层上采样网络层包括特征反卷积层和第一特征卷积层，从而通过不同卷积层的结合，提高图像分割网络对左心室图像特征的处理效果。其中，将每层下采样网络层处理后的图像特征进入第一层上采样网络层时，先通过第一层上采样网络层中的特征反卷积层对这些图像特征进行处理，再由第一层上采样网络层中的第一特征卷积层对该特征反卷积层处理的图像特征进行处理。Preferably, each down-sampling network layer includes a first feature convolution layer and a second feature convolution layer, and each up-sampling network layer includes a feature deconvolution layer and a first feature convolution layer, thereby passing different convolution layers To improve the processing effect of image segmentation network on left ventricular image features. Among them, when the image features processed by the down-sampling network layer of each layer enter the first-layer up-sampling network layer, these image features are processed through the feature deconvolution layer in the first-layer up-sampling network layer, and then the The first feature convolutional layer in an up-sampling network layer processes the image features processed by the feature deconvolution layer.
进一步优选地，图像分割网络中的下采样部分包括一层第一卷积层和三层下采样网络层，图像分割网络中的上采样部分包括三层上采样网络层和三层第二卷积层，第一卷积层和第二卷积层的卷积核大小不同，在上采样网络层中，第一特征卷积层与第二特征卷积层的步长不同，以提高图像分割网络对左心室图像特征的处理效果。Further preferably, the downsampling part in the image segmentation network includes a first convolution layer and a three-layer downsampling network layer, and the upsampling part in the image segmentation network includes a three-layer upsampling network layer and a three-layer second convolution Layers, the first and second convolution layers have different convolution kernel sizes. In the upsampling network layer, the first feature convolution layer and the second feature convolution layer have different step sizes to improve the image segmentation network. The processing effect of the left ventricular image features.
分割图像输出单元33，用于获得图像分割网络处理得到的左心室分割图像并输出。The divided image output unit 33 is used to obtain and output a left ventricular divided image obtained by image segmentation network processing.
在本发明实施例中，由图像分割网络处理得到的左心室分割图像，为待分割的左心室图像中分割出左心室轮廓图像，可帮助医生直观地观察到患者的左心室状况。In the embodiment of the present invention, the left ventricular segmented image processed by the image segmentation network is a left ventricular contour image segmented from the left ventricular image to be segmented, which can help the doctor visually observe the patient's left ventricular status.
优选地，在通过第一卷积层对到待分割的左心室图像进行处理时，卷积计算公式为：Preferably, when the left ventricle image to be divided is processed through the first convolution layer, the convolution calculation formula is:
进一步优选地，在获得经过第一卷积层提取到的图像特征后，对这些图像 特征进行非线性激活，以提高图像分割网络对左心室图像的分割效果。其中，非线性激活的公式为：Further preferably, after the image features extracted through the first convolution layer are obtained, these image features are non-linearly activated to improve the segmentation effect of the image segmentation network on the left ventricle image. Among them, the formula for nonlinear activation is:
优选地，在通过下采样网络层中的第一特征卷积层、下采样网络层中的第二特征卷积层、或者上采样网络中的第一特征卷积层对其接收到的图像特征进行处理时，包括对图像特征进行特征卷积操作和非线性变化操作，以提高对图像特征的处理效果。Preferably, the image features received by the first feature convolution layer in the down-sampling network layer, the second feature convolution layer in the down-sampling network layer, or the first feature convolution layer in the up-sampling network When processing, it includes the feature convolution operation and the non-linear change operation on the image features to improve the processing effect on the image features.
进一步优选地，根据第一特征卷积层对应的网络权重和动态路由算法中的路由系数，对输入至该第一特征卷积层的图像特征进行特征卷积操作，路由系数通过动态路由算法进行更新，再将特征卷积操作处理后的图像特征输入预设的非线性变化公式，进行非线性变化操作，以提高第一特征卷积对图像特征的处理效果。Further preferably, according to the network weights corresponding to the first feature convolution layer and the routing coefficients in the dynamic routing algorithm, feature convolution operations are performed on the image features input to the first feature convolution layer, and the routing coefficients are performed by the dynamic routing algorithm Update, and then input the image features processed by the feature convolution operation into a preset nonlinear change formula, and perform a nonlinear change operation to improve the processing effect of the first feature convolution on the image features.
其中，特征卷积操作的公式为：Among them, the formula of feature convolution operation is:
其中，非线性变化公式为：Among them, the nonlinear change formula is:
在通过动态路由算法更新路由系数时，通过迭代方式进行更新，其中第d次迭代过程如下：When the routing coefficient is updated by the dynamic routing algorithm, it is updated iteratively, and the d-th iteration process is as follows:
(1)获取位于图像分割网络p层的下采样网络(或上采样网络)的路由系数：(1) Obtain the routing coefficient of the down-sampling network (or up-sampling network) at the p-layer of the image segmentation network:
(2)在位于图像分割网络p+1层的下采样网络(或上采样网络)中，对输入该层网络的图像特征进行特征卷积处理，处理公式为：(2) In the down-sampling network (or up-sampling network) located in the p+1 layer of the image segmentation network, the image features input to the layer network are subjected to feature convolution processing, and the processing formula is:
(3)在位于图像分割网络p+1层的下采样网络(或上采样网络)中，对经特征卷积处理的图像特征进行非线性变化操作，公式为：(3) In the down-sampling network (or up-sampling network) located in the p+1 layer of the image segmentation network, the non-linear change operation is performed on the image features subjected to feature convolution processing, the formula is:
(4)更新参数
更新公式如下：
(4) Update parameters The update formula is as follows:
优选地，如图4所示，图像分割单元32还包括：Preferably, as shown in FIG. 4, the image segmentation unit 32 further includes:
图像特征提取单元421，用于通过第一卷积层对左心室图像进行特征提取，生成左心室图像对应的图像特征；以及The image feature extraction unit 421 is configured to perform feature extraction on the left ventricular image through the first convolution layer to generate image features corresponding to the left ventricular image; and
图像特征处理单元422，用于将图像特征输入与第一卷积层连接的下采样网络层，依次经过每层下采样网络层、每层上采样网络层和第二卷积层的处理，获得左心室分割图像。The image feature processing unit 422 is used to input the image features to the down-sampling network layer connected to the first convolutional layer, and sequentially process through each layer of the down-sampling network layer, each layer of the up-sampling network layer, and the second convolutional layer to obtain Split image of left ventricle.
优选地，在训练之前，按照上述网络结果构建图像分割网络。采集多张左心室训练图像，用作图像分割网络的训练样本，一一输入图像分割网络之中，并采用Adam(适应性矩估计)学习率自适应优化算法对图像分割网络进行训练，获得训练好的图像分割网络，从而通过自适应优化算法提高图像分割网络对左心室图像的自动分割效果。Preferably, before training, an image segmentation network is constructed according to the above network results. Collect multiple left ventricular training images and use them as training samples for the image segmentation network, input them into the image segmentation network one by one, and use Adam (adaptive moment estimation) learning rate adaptive optimization algorithm to train the image segmentation network to obtain training A good image segmentation network, so as to improve the automatic segmentation effect of the image segmentation network on the left ventricle image through the adaptive optimization algorithm.
在本发明实施例中，通过Adam学习率自适应优化算法训练图像分割网络，由训练好的图像分割网络对左心室图像进行分割，获得分割后得到的左心室分割图像并输出，其中，图像分割网络为深度学习网络，包括上采样部分和下采样部分，上采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层，下采样网络层包括第一特征卷积层和第二特征卷积层，上采样网络层包括特征反卷积层和第一特征反卷积层，从而实现对左心室图像进行自动优化分割，有效地提高左心室图像分割的效率和效果。In the embodiment of the present invention, the image segmentation network is trained by the Adam learning rate adaptive optimization algorithm, and the trained image segmentation network segments the left ventricle image to obtain the segmented left ventricular segmented image and output it. Among them, the image segmentation The network is a deep learning network, including an upsampling part and a downsampling part. The upsampling part includes a first convolutional layer and a downsampling network layer. The upsampling part includes a second convolutional layer and an upsampling network layer. The downsampling network layer includes The first feature convolution layer and the second feature convolution layer, the up-sampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so as to automatically optimize the left ventricular image segmentation and effectively improve the left ventricular image Efficiency and effect of segmentation.
在本发明实施例中，一种左心室图像分割装置的各单元可由相应的硬件或软件单元实现，各单元可以为独立的软、硬件单元，也可以集成为一个软、硬件单元，在此不用以限制本发明。In the embodiment of the present invention, each unit of a left ventricular image segmentation device may be implemented by a corresponding hardware or software unit, and each unit may be an independent software and hardware unit, or may be integrated into one software and hardware unit, which is not used here To limit the invention.
实施例四：Example 4:
图5示出了本发明实施例五提供的一种计算机设备的结构，为了便于说明，仅示出了与本发明实施例相关的部分。FIG. 5 shows a structure of a computer device provided by Embodiment 5 of the present invention. For convenience of description, only parts related to the embodiment of the present invention are shown.
本发明实施例的汽车5包括处理器50、存储器51以及存储在存储器51中并可在处理器50上运行的计算机程序52。该处理器50执行计算机程序52时实现上述各个方法实施例中的步骤，例如图1所示的步骤S101至S103。或者，处理器50执行计算机程序52时实现上述各装置实施例中各单元的功能，例如图3所示单元31至33的功能。The automobile 5 of the embodiment of the present invention includes a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50. When the processor 50 executes the computer program 52, the steps in the above method embodiments are implemented, for example, steps S101 to S103 shown in FIG. 1. Alternatively, when the processor 50 executes the computer program 52, the functions of the units in the foregoing device embodiments are realized, for example, the functions of the units 31 to 33 shown in FIG.
在本发明实施例中，由训练好的图像分割网络对左心室图像进行分割，获得分割后得到的左心室分割图像并输出，其中，图像分割网络为深度学习网络，包括上采样部分和下采样部分，上采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层，下采样网络层包括第一特征卷积层和第二特征卷积层，上采样网络层包括特征反卷积层和第一特征反卷积层，从而借助上述结构的图像分割网络对左心室图像进行自动分割，有效地提高左心室图像分割的效率和效果。In the embodiment of the present invention, the left ventricular image is segmented by a trained image segmentation network to obtain the segmented left ventricular segmented image and output, wherein the image segmentation network is a deep learning network, including an upsampling part and a downsampling Partially, the upsampling part includes the first convolutional layer and the downsampling network layer, the upsampling part includes the second convolutional layer and the upsampling network layer, and the downsampling network layer includes the first feature convolutional layer and the second feature convolutional layer The up-sampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so that the left ventricular image is automatically segmented by the image segmentation network with the above structure, which effectively improves the efficiency and effect of left ventricular image segmentation.
实施例五：Example 5:
在本发明实施例中，提供了一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，该计算机程序被处理器执行时实现上述各个方法实施例中的步骤，例如，图1所示的步骤S101至S103。或者，该计算机程序被处理器执行时实现上述各装置实施例中各单元的功能，例如图3所示单元31至33的功能。In an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented, for example, FIG. 1 Steps S101 to S103 shown. Alternatively, when the computer program is executed by the processor, the functions of the units in the foregoing device embodiments are realized, for example, the functions of the units 31 to 33 shown in FIG. 3.
在本发明实施例中，由训练好的图像分割网络对左心室图像进行分割，获得分割后得到的左心室分割图像并输出，其中，图像分割网络为深度学习网络，包括上采样部分和下采样部分，上采样部分包括第一卷积层和下采样网络层，上采样部分包括第二卷积层和上采样网络层，下采样网络层包括第一特征卷积层和第二特征卷积层，上采样网络层包括特征反卷积层和第一特征反卷积层，从而借助上述结构的图像分割网络对左心室图像进行自动分割，有效地提高左心室图像分割的效率和效果。In the embodiment of the present invention, the left ventricular image is segmented by the trained image segmentation network to obtain the segmented left ventricular segmented image and output. The image segmentation network is a deep learning network, including an upsampling part and a downsampling Partially, the upsampling part includes the first convolutional layer and the downsampling network layer, the upsampling part includes the second convolutional layer and the upsampling network layer, and the downsampling network layer includes the first feature convolutional layer and the second feature convolutional layer The upsampling network layer includes a feature deconvolution layer and a first feature deconvolution layer, so that the left ventricular image is automatically segmented by the image segmentation network with the above structure, which effectively improves the efficiency and effect of left ventricular image segmentation.
本发明实施例的计算机可读存储介质可以包括能够携带计算机程序代码的 任何实体或装置、记录介质，例如，ROM/RAM、磁盘、光盘、闪存等存储器。The computer-readable storage medium in the embodiments of the present invention may include any entity or device capable of carrying computer program code, and a recording medium, such as ROM/RAM, magnetic disk, optical disk, flash memory, and other memories.
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modification, equivalent replacement and improvement made within the spirit and principle of the present invention should be included in the protection of the present invention Within range.
Claims (10)
- 一种左心室图像分割方法，其特征在于，所述方法包括下述步骤：A left ventricular image segmentation method, characterized in that the method includes the following steps:接收待分割的左心室图像；Receive the left ventricle image to be segmented;将所述左心室图像输入预先训练好的图像分割网络中进行分割，所述图像分割网络为深度学习网络，所述图像分割网络包括下采样部分和上采样部分，所述下采样部分包括第一卷积层和下采样网络层，所述上采样部分包括第二卷积层和上采样网络层；Input the left ventricular image into a pre-trained image segmentation network for segmentation, the image segmentation network is a deep learning network, the image segmentation network includes a downsampling part and an upsampling part, and the downsampling part includes a first A convolution layer and a down-sampling network layer, the up-sampling part includes a second convolution layer and an up-sampling network layer;获得所述图像分割网络处理得到的左心室分割图像并输出。The left ventricular segmented image processed by the image segmentation network is obtained and output.
- 如权利要求1所述的方法，其特征子在于，将所述左心室图像输入预先训练好的图像分割网络中进行分割的步骤，包括：The method of claim 1, wherein the step of inputting the left ventricular image into a pre-trained image segmentation network for segmentation includes:通过所述第一卷积层对所述左心室图像进行特征提取，生成所述左心室图像对应的图像特征；Performing feature extraction on the left ventricular image through the first convolution layer to generate image features corresponding to the left ventricular image;将所述图像特征输入与所述第一卷积层连接的下采样网络层，依次经过每层所述下采样网络层、每层所述上采样网络层和所述第二卷积层的处理，获得所述左心室分割图像。Input the image feature to the down-sampling network layer connected to the first convolutional layer, and sequentially pass through the processing of each layer of the down-sampling network layer, each layer of the up-sampling network layer and the second convolutional layer To obtain the left ventricular segmented image.
- 如权利要求2所述的方法，其特征在于，每层所述下采样网络层包括第一特征卷积层和第二特征卷积层，每层所述上采样层包括特征反卷积层和所述第一特征卷积层。The method of claim 2, wherein each layer of the down-sampling network layer includes a first feature convolution layer and a second feature convolution layer, and each layer of the up-sampling layer includes a feature deconvolution layer and The first feature convolution layer.
- 如权利要求3所述的方法，其特征在于，所述第一特征卷积层和所述第二特征卷积层包括特征卷积操作和非线性变换操作。The method of claim 3, wherein the first feature convolution layer and the second feature convolution layer include a feature convolution operation and a nonlinear transformation operation.
- 如权利要求4所述的方法，其特征在于，将所述图像特征输入与所述第一卷积层连接的下采样网络层的步骤，包括：The method according to claim 4, wherein the step of inputting the image feature to the down-sampling network layer connected to the first convolution layer includes:在所述下采样网络层中，根据所述第一特征卷积层对应的网络权重和动态路由算法中的路由系数，对输入至所述第一特征卷积层的图像特征进行所述特征卷积操作，所述路由系数通过所述动态路由算法进行更新；In the down-sampling network layer, according to the network weight corresponding to the first feature convolution layer and the routing coefficient in the dynamic routing algorithm, perform the feature roll on the image features input to the first feature convolution layer Product operation, the routing coefficient is updated by the dynamic routing algorithm;将经所述特征卷积操作处理后的图像特征输入预设的非线性变换公式，进 行所述非线性变化操作。The image feature processed by the feature convolution operation is input into a preset nonlinear transformation formula to perform the nonlinear change operation.
- 如权利要求1所述的方法，其特征在于，接收待分割的左心室图像的步骤之前，所述方法还包括：The method according to claim 1, wherein before the step of receiving the left ventricle image to be segmented, the method further comprises:获取采集到的左心室训练图像；Obtain the collected training images of the left ventricle;将所述左心室训练图像输入所述图像分割网络中，并通过预设的优化算法对所述图像分割网络进行训练，所述优化算法为Adam学习率自适应优化算法。The left ventricle training image is input into the image segmentation network, and the image segmentation network is trained by a preset optimization algorithm, and the optimization algorithm is an Adam learning rate adaptive optimization algorithm.
- 一种左心室图像分割装置，其特征在于，所述装置包括：A left ventricular image segmentation device, characterized in that the device includes:待分割图像接收单元，用于接收待分割的左心室图像；An image to-be-divided receiving unit, used to receive the left ventricle image to be divided图像分割单元，用于将所述左心室图像输入预先训练好的图像分割网络中进行分割，所述图像分割网络为深度学习网络，所述图像分割网络包括下采样部分和上采样部分，所述下采样部分包括第一卷积层和下采样网络层，所述上采样部分包括第二卷积层和上采样网络层；以及An image segmentation unit for inputting the left ventricular image into a pre-trained image segmentation network for segmentation, the image segmentation network is a deep learning network, and the image segmentation network includes a downsampling portion and an upsampling portion, the The down-sampling section includes a first convolution layer and a down-sampling network layer, and the up-sampling section includes a second convolution layer and an up-sampling network layer; and分割图像输出单元，用于获得所述图像分割网络处理得到的左心室分割图像并输出。The divided image output unit is used to obtain and output the left ventricular divided image obtained by the image division network processing.
- 如权利要求7所述的装置，其特征在于，所述图像分割单元包括：The apparatus of claim 7, wherein the image segmentation unit comprises:图像特征提取单元，用于通过所述第一卷积层对所述左心室图像进行特征提取，生成所述左心室图像对应的图像特征；以及An image feature extraction unit for extracting features of the left ventricular image through the first convolutional layer to generate image features corresponding to the left ventricular image; and图像特征处理单元，用于将所述图像特征输入与所述第一卷积层连接的下采样网络层，依次经过每层所述下采样网络层、每层所述上采样网络层和所述第二卷积层的处理，获得所述左心室分割图像。An image feature processing unit for inputting the image feature to a down-sampling network layer connected to the first convolutional layer, sequentially passing through each layer of the down-sampling network layer, each layer of the up-sampling network layer, and the The second convolutional layer is processed to obtain the left ventricular segmented image.
- 一种计算机设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至6任一项所述方法的步骤。A computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, claims 1 to 6. The steps of any one of the methods.
- 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至6任一项所述方法的步骤。A computer-readable storage medium storing a computer program, characterized in that when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811535090.9 | 2018-12-14 | ||
| CN201811535090.9A CN109685803B (en) | 2018-12-14 | 2018-12-14 | Left ventricle image segmentation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020118826A1 true WO2020118826A1 (en) | 2020-06-18 |
Family
ID=66187805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/071075 WO2020118826A1 (en) | 2018-12-14 | 2019-01-10 | Left ventricle image segmenting method and apparatus, and device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109685803B (en) |
| WO (1) | WO2020118826A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110136111B (en) * | 2019-05-14 | 2021-08-10 | 深圳大学 | Heart motion estimation method, system and terminal equipment |
| CN110731777B (en) * | 2019-09-16 | 2023-07-25 | 平安科技（深圳）有限公司 | Left ventricle measurement method and device based on image recognition and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062543A (en) * | 2018-01-16 | 2018-05-22 | 中车工业研究院有限公司 | A kind of face recognition method and device |
| CN108537801A (en) * | 2018-03-29 | 2018-09-14 | 山东大学 | Based on the retinal angiomatous image partition method for generating confrontation network |
| CN108664974A (en) * | 2018-04-03 | 2018-10-16 | 华南理工大学 | A kind of semantic segmentation method based on RGBD images Yu Complete Disability difference network |
| CN108921850A (en) * | 2018-04-16 | 2018-11-30 | 博云视觉（北京）科技有限公司 | A kind of extracting method of the image local feature based on image Segmentation Technology |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9760807B2 (en) * | 2016-01-08 | 2017-09-12 | Siemens Healthcare Gmbh | Deep image-to-image network learning for medical image analysis |
| CN108806793A (en) * | 2018-04-17 | 2018-11-13 | 平安科技（深圳）有限公司 | Lesion monitoring method, device, computer equipment and storage medium |
-
2018
- 2018-12-14 CN CN201811535090.9A patent/CN109685803B/en active Active
-
2019
- 2019-01-10 WO PCT/CN2019/071075 patent/WO2020118826A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062543A (en) * | 2018-01-16 | 2018-05-22 | 中车工业研究院有限公司 | A kind of face recognition method and device |
| CN108537801A (en) * | 2018-03-29 | 2018-09-14 | 山东大学 | Based on the retinal angiomatous image partition method for generating confrontation network |
| CN108664974A (en) * | 2018-04-03 | 2018-10-16 | 华南理工大学 | A kind of semantic segmentation method based on RGBD images Yu Complete Disability difference network |
| CN108921850A (en) * | 2018-04-16 | 2018-11-30 | 博云视觉（北京）科技有限公司 | A kind of extracting method of the image local feature based on image Segmentation Technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109685803B (en) | 2020-10-23 |
| CN109685803A (en) | 2019-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102581685B1 (en) | Classification and 3D modeling of 3D oral and maxillofacial structures using deep learning | |
| CN110706246B (en) | Blood vessel image segmentation method and device, electronic equipment and storage medium | |
| CN108537794B (en) | Medical image data processing method, apparatus and computer readable storage medium | |
| WO2019200753A1 (en) | Lesion detection method, device, computer apparatus and storage medium | |
| CN112424835B (en) | System and method for image reconstruction | |
| Tang et al. | CT image enhancement using stacked generative adversarial networks and transfer learning for lesion segmentation improvement | |
| JP6505124B2 (en) | Automatic contour extraction system and method in adaptive radiation therapy | |
| CN111062947B (en) | X-ray chest radiography focus positioning method and system based on deep learning | |
| JP2017535353A (en) | Simulation of dose increase by multiscale noise reduction based on noise model | |
| WO2020019740A1 (en) | Left ventricle myocardium segmentation method and device, and computer readable storage medium | |
| WO2021017006A1 (en) | Image processing method and apparatus, neural network and training method, and storage medium | |
| CN111166362B (en) | Medical image display method and device, storage medium and electronic equipment | |
| WO2020118826A1 (en) | Left ventricle image segmenting method and apparatus, and device and storage medium | |
| WO2021017168A1 (en) | Image segmentation method, apparatus, device, and storage medium | |
| US20110122146A1 (en) | Systems and methods for matching medical images | |
| JPH1094538A (en) | Method and apparatus for detecting abnormal shade candidate | |
| JP2012245085A (en) | Image processing program, method and device | |
| CN108038840B (en) | Image processing method and device, image processing equipment and storage medium | |
| CN110599530B (en) | MVCT image texture enhancement method based on double regular constraints | |
| US20200074623A1 (en) | Image processing apparatus , image processing method, and computer readable recording medium storing program | |
| US9454814B2 (en) | PACS viewer and a method for identifying patient orientation | |
| WO2022027216A1 (en) | Image denoising method and application thereof | |
| CN111339993A (en) | X-ray image metal detection method and system | |
| CN113538419B (en) | Image processing method and system | |
| CN116029934A (en) | Low-dose DR image and CT image denoising method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19896720 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 03.11.2021) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19896720 Country of ref document: EP Kind code of ref document: A1 |