WO2019201204A1 - 一种影像结节检测的方法及装置 - Google Patents

一种影像结节检测的方法及装置 Download PDF

Info

Publication number
WO2019201204A1
WO2019201204A1 PCT/CN2019/082677 CN2019082677W WO2019201204A1 WO 2019201204 A1 WO2019201204 A1 WO 2019201204A1 CN 2019082677 W CN2019082677 W CN 2019082677W WO 2019201204 A1 WO2019201204 A1 WO 2019201204A1
Authority
WO
WIPO (PCT)
Prior art keywords
nodule
candidate
nodules
image
roi
Prior art date
Application number
PCT/CN2019/082677
Other languages
English (en)
French (fr)
Inventor
魏子昆
杨忠程
华铱炜
Original Assignee
杭州依图医疗技术有限公司
杭州依图网络科技有限公司
广州依图医疗技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 杭州依图医疗技术有限公司, 杭州依图网络科技有限公司, 广州依图医疗技术有限公司 filed Critical 杭州依图医疗技术有限公司
Publication of WO2019201204A1 publication Critical patent/WO2019201204A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user
    • G06T2207/20104—Interactive definition of region of interest [ROI]
    • 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

Definitions

  • Embodiments of the present invention relate to the field of machine learning technologies, and in particular, to a method and an apparatus for detecting image nodules.
  • nodules have caused widespread concern, such as pulmonary nodules, thyroid nodules, etc.
  • doctors generally observe the patient's nodules through medical imaging.
  • the patient's nodules may change over time, for example, increase, decrease, or grow new nodules and the like.
  • the way to find nodules from medical images is mainly to find the corresponding nodules in the medical images by doctors manually observing the medical images, but this situation will lead to the accuracy of the found nodules, and also It takes a lot of time and is subjective.
  • Embodiments of the present invention provide a method and apparatus for detecting image nodules, which are used to improve the efficiency of nodule detection and improve the accuracy of nodule detection.
  • ROI Region of Interest
  • the convolutional neural network is used to train the nodule image of the marked nodule region to obtain the nodule detection model
  • the ROI can be directly input to the nodule detection model to obtain the confidence of the corresponding candidate nodule, and the improved knot
  • the efficiency of the section detection, and the false-positive nodules are filtered out after the nodules are detected, thereby improving the accuracy of the nodule detection.
  • determining, according to the three-dimensional coordinates of the candidate nodule, the ROI of the candidate nodule from the nodule image including:
  • a spatial information channel is added to each pixel of the pixel cube to determine the ROI, and the spatial information channel is a distance between the pixel and the three-dimensional coordinates of the nodule.
  • the input value input to the nodule detection model can be obtained by the determined ROI, so that the input of the nodule detection model is applied, and the uniformity of the input values is improved.
  • the determining, according to the ROI and the nodule detection model, the confidence that the candidate nodule is included including:
  • the ROI is sequentially extracted by the M 3D convolution feature extraction modules to extract the feature image of the ROI, where M is greater than 0;
  • the extracted feature image of the ROI is input to the fully connected module, and the confidence of the candidate nodule is determined.
  • the confidence of the candidate nodule is detected by the nodule detection model, thereby improving the efficiency of nodule detection.
  • the candidate nodule according to the confidence level greater than the threshold, the segmentation result of the body part where the candidate nodule is located, and the three-dimensional coordinates and radius of the candidate nodule are filtered out, and the candidate nodule with the confidence greater than the threshold is filtered out.
  • Candidate nodules for false positives including:
  • the candidate nodule of the mediastinal false positive in the candidate nodule with the confidence greater than the threshold is filtered out.
  • the using the convolutional neural network to train the plurality of nodule effects of the labeled nodule region to determine the nodule detection model comprises:
  • Data enhancement is performed on candidate nodules in the candidate nodule set to obtain an enhanced candidate nodule set
  • the ROI of each candidate nodule in the enhanced candidate nodule set is trained by a preset 3D convolutional neural network model to obtain the nodule detection model.
  • the embodiment of the invention further provides an apparatus for detecting image nodules, comprising:
  • An acquiring unit configured to acquire a nodule image and three-dimensional coordinates of candidate nodules in the nodule image
  • a determining unit configured to determine, from the nodule image, an ROI including the candidate nodule according to the three-dimensional coordinates of the candidate nodule;
  • a detecting unit configured to determine a confidence level of the candidate nodule according to the ROI and a nodule detection model, wherein the nodule detection model uses a convolutional neural network to perform influence on multiple nodules of the labeled nodule region Determined after training;
  • a filtering unit configured to filter out false positives in the candidate nodules whose confidence is greater than a threshold according to a candidate nodule with a confidence greater than a threshold, a segmentation result of a body part where the candidate nodule is located, and a three-dimensional coordinate of the candidate nodule
  • Candidate nodules determine the nodules in the nodule image and the confidence level corresponding to the nodules.
  • the determining unit is specifically configured to:
  • a spatial information channel is added to each pixel of the pixel cube to determine the ROI, and the spatial information channel is a distance between the pixel and the three-dimensional coordinates of the nodule.
  • the detecting unit is specifically configured to:
  • the ROI is sequentially extracted by the M 3D convolution feature extraction modules to extract the feature image of the ROI, where M is greater than 0;
  • the extracted feature image of the ROI is input to the fully connected module, and the confidence of the candidate nodule is determined.
  • the filtering unit is specifically configured to:
  • the candidate nodule of the mediastinal false positive in the candidate nodule with the confidence greater than the threshold is filtered out.
  • the detecting unit is specifically configured to:
  • Data enhancement is performed on candidate nodules in the candidate nodule set to obtain an enhanced candidate nodule set
  • the ROI of each candidate nodule in the enhanced candidate nodule set is trained by a preset 3D convolutional neural network model to obtain the nodule detection model.
  • an embodiment of the present invention further provides a computer device, including:
  • a memory for storing program instructions
  • a processor configured to invoke a program instruction stored in the memory, and execute the method for detecting the image nodule according to the obtained program.
  • the embodiment of the present invention further provides a computer readable non-volatile storage medium, comprising computer readable instructions, when the computer device reads and executes the computer readable instructions, causing the computer device to execute the image image Method of section detection.
  • an embodiment of the present invention further provides a computer program product, the computer program product comprising a computer program stored on a computer readable non-volatile storage medium, the computer program comprising program instructions, when the program When the instructions are executed by the computer device, the computer device is caused to perform the method of image nodule detection described above.
  • the convolutional neural network is used to train the nodule image of the marked nodule region to obtain a nodule detection model, thereby directly inputting the ROI into the nodule detection model to obtain a confidence of the corresponding candidate nodule. Degree, improved efficiency of nodule detection, and filtering out false positive nodules after detection of nodules, thereby improving the accuracy of nodule detection.
  • FIG. 1 is a schematic diagram of a system architecture according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of a method for detecting image nodules according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram of a nodule image according to an embodiment of the present invention.
  • FIG. 4 is a schematic flowchart of an apparatus for detecting image nodules according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
  • FIG. 1 is a system architecture applicable to a method for detecting image nodules according to an embodiment of the present invention.
  • the system architecture can be server 100, including processor 110, communication interface 120, and memory 130.
  • the communication interface 120 is used for communication by a terminal device applied by a doctor, and transmits and receives information transmitted by the terminal device to implement communication.
  • the processor 110 is a control center of the server 100 that connects various portions of the entire server 100 using various interfaces and lines, by running or executing software programs and/or modules stored in the memory 130, and recalling data stored in the memory 130, Various functions and processing data of the server 100 are executed.
  • processor 110 may include one or more processing units.
  • the memory 130 can be used to store software programs and modules, and the processor 110 executes various functional applications and data processing by running software programs and modules stored in the memory 130.
  • the memory 130 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function, and the like; the storage data area may store data created according to business processing and the like.
  • memory 130 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
  • FIG. 1 is only an example, which is not limited by the embodiment of the present invention.
  • FIG. 2 exemplarily shows a flow of image nodule detection provided by an embodiment of the present invention, which may be performed by a device for detecting image nodules.
  • the process specifically includes:
  • Step 201 Acquire a nodule image and three-dimensional coordinates of candidate nodules in the nodule image.
  • the nodule image is a three-dimensional image, and the three-dimensional coordinates of the candidate nodule may be the three-dimensional coordinates of the point within the candidate nodule (such as the three-dimensional coordinates of the nodule center point), or may be the three-dimensional coordinates of the point of the candidate nodule surface.
  • candidate nodules include, but are not limited to, pulmonary nodules, thyroid nodules, and breast nodules.
  • the nodule image may be a Computed Tomography (CT) image, a Magnetic Resonance Imaging (MRI) image, or the like.
  • CT Computed Tomography
  • MRI Magnetic Resonance Imaging
  • Step 202 Determine an ROI of the candidate nodule from the nodule image according to the three-dimensional coordinates of the candidate nodule.
  • the preset distance may be extended to the periphery by using the three-dimensional coordinates of the candidate nodule as a center, and the pixel cube including the candidate nodule is determined, wherein the preset distance is a preset multiple of the radius of the candidate nodule, such as a candidate.
  • the radius of the nodule is 1.25 times.
  • a spatial information channel is added to each pixel in the pixel cube to output an ROI, and the spatial information channel is the distance between the pixel cube and the three-dimensional coordinates of the candidate nodule.
  • Step 203 Determine a confidence level of the candidate nodule according to the ROI and the nodule detection model.
  • the nodule detection model is obtained by using a convolutional neural network to train a plurality of nodules in the marked nodule region, and specifically: obtaining a candidate for filtering a false positive result first.
  • the nodule set and the doctor determine the candidate nodules in the candidate nodule set, and the candidate nodule set of the false positive result to be filtered is obtained by collecting a large number of chest CT images and using other programs, and then passing through multiple doctors.
  • the candidate nodules in the candidate nodule set are determined to determine whether it is a nodule.
  • the candidate nodules in the candidate nodule set are then data enhanced to obtain an enhanced candidate nodule set.
  • the amount of data can be increased to the previous K times.
  • the possible way is to enhance the data amount by random horizontal mirroring, random rotation of arbitrary angles, random up and down and left and right translation of 0 to 5 pixels, and randomization of 0.85 to 1.15 times. K times before.
  • the ROI of each candidate nodule in the enhanced candidate nodule set is determined from the nodule image according to the enhanced candidate nodule set and the three-dimensional coordinates of each candidate nodule. For the specific determination method, refer to step 203. Narration.
  • the ROI of each candidate nodule in the enhanced candidate nodule set is trained by a preset 3D convolutional neural network model to obtain a nodule detection model.
  • the nod confidence of the 3D convolutional neural network model output and the label of the training sample can be cross-entropy as a loss function, and trained by the back propagation method.
  • the training optimization algorithm is SGD.
  • the nodule detection model obtained by the above steps includes M 3D convolution feature extraction models and a fully connected module.
  • Each 3D convolution feature extraction model also includes a 3D convolutional layer of J*J*J and a max_pool layer of H*H*H.
  • a fully connected model can include two fully connected layers.
  • the ROI obtained in the above step 202 may be sequentially extracted by the M 3D convolution feature extraction module to extract the feature image of the ROI, and then the extracted ROI feature image is input to the fully connected module to determine the candidate.
  • Step 204 Filter out candidate for false positive in the candidate nodule with the confidence greater than the threshold according to the candidate nodule with the confidence greater than the threshold, the segmentation result of the body part where the candidate nodule is located, and the three-dimensional coordinate of the candidate nodule Nodule.
  • the body part may be a body part such as a lung, a thyroid gland, a breast, or the like, which is not limited in the embodiment of the present invention.
  • the candidate nodules of the skeleton-like false positives in the candidate nodules whose confidence is greater than the threshold may be filtered according to the three-dimensional coordinates of the candidate nodules and the pixels in the preset region where the candidate nodules are located.
  • This threshold can be set empirically. For example, three-dimensional coordinates from the beginning of the nodule candidate, Imm extended to the surrounding area, a total area I * I * Imm 3 a. Then, the pixels with CT values greater than 400 in the statistical region can be regarded as candidate nodules of false positives of the bones if they occupy a larger proportion than the first threshold, so that they can be filtered out.
  • the candidate nodules of the diaphragmatic false positives in the candidate nodules with confidence greater than the threshold may also be filtered according to the three-dimensional coordinates and radius of the candidate nodules and the segmentation results of the body parts where the candidate nodules are located. For example, starting from the three-dimensional coordinates of the candidate nodule, the area block of the diameter is expanded to the periphery, and the number of pixels in the lung and the lung outside the block is counted, if the number of pixels in the lung and the number of pixels outside the lung are in the nodule image. The proportions occupied are similar, and basically in the middle of the image, it can be regarded as a candidate nodule of the diaphragmatic false positive, which can be filtered out.
  • Candidate nodules of mediastinal false positives in candidate nodules with confidence greater than the threshold can also be filtered out according to the three-dimensional coordinates of the candidate nodules and the segmentation results of the body parts where the candidate nodules are located. For example, if the center of the candidate nodule is outside the lung, and the vertical direction does not exceed the lung range, and the central position, it can be said that the relative position on the X-axis is between 0.45 and 0.55, then it can be regarded as a mediastinum. Positive candidate nodule.
  • the above embodiment shows that by acquiring the nodule image and the three-dimensional coordinates of the candidate nodule in the nodule image, the ROI containing the candidate nodule is determined from the nodule image according to the three-dimensional coordinates of the candidate nodule, and is determined according to the ROI and the nodule detection model. Based on the confidence of the candidate nodule, the nodule detection model is determined by using a convolutional neural network to train the effects of multiple nodules in the labeled nodule region. According to the candidate nodule with the confidence greater than the threshold, the candidate nodule is located.
  • the segmentation result of the body part and the three-dimensional coordinates of the candidate nodule filtering out the candidate nodule of the false positive in the candidate nodule with the confidence greater than the threshold, determining the nodule in the nodule image and the confidence corresponding to the nodule . Since the convolutional neural network is used to train the nodule image of the marked nodule region to obtain the nodule detection model, the ROI can be directly input to the nodule detection model to obtain the confidence of the corresponding candidate nodule, and the improved knot The efficiency of the section detection, and the false-positive nodules are filtered out after the nodules are detected, thereby improving the accuracy of the nodule detection.
  • FIG. 4 exemplarily shows an apparatus for detecting image nodules according to an embodiment of the present invention, which can perform a process of image nodule detection.
  • the device specifically includes:
  • An obtaining unit 401 configured to acquire a nodule image and three-dimensional coordinates of candidate nodules in the nodule image
  • a determining unit 402 configured to determine, according to the three-dimensional coordinates of the candidate nodule, an ROI including the candidate nodule from the nodule image;
  • a detecting unit 403 configured to determine a confidence level of the candidate nodule according to the ROI and a nodule detection model, wherein the nodule detection model uses a convolutional neural network to affect multiple nodules of the labeled nodule region Determined after training;
  • the filtering unit 404 is configured to filter out the false candidate in the candidate nodule with the confidence greater than the threshold according to the candidate nodule with the confidence greater than the threshold, the segmentation result of the body part where the candidate nod is located, and the three-dimensional coordinate of the candidate nodule A positive candidate nodule determines the nodule in the nodule image and the confidence level corresponding to the nodule.
  • the determining unit 402 is specifically configured to:
  • a spatial information channel is added to each pixel of the pixel cube to determine the ROI, and the spatial information channel is a distance between the pixel and the three-dimensional coordinates of the nodule.
  • the detecting unit 403 is specifically configured to:
  • the ROI is sequentially extracted by the M 3D convolution feature extraction modules to extract the feature image of the ROI, where M is greater than 0;
  • the extracted feature image of the ROI is input to the fully connected module, and the confidence of the candidate nodule is determined.
  • the filtering unit 404 is specifically configured to:
  • the candidate nodule of the mediastinal false positive in the candidate nodule with the confidence greater than the threshold is filtered out.
  • the detecting unit 403 is specifically configured to:
  • Data enhancement is performed on candidate nodules in the candidate nodule set to obtain an enhanced candidate nodule set
  • the ROI of each candidate nodule in the enhanced candidate nodule set is trained by a preset 3D convolutional neural network model to obtain the nodule detection model.
  • an embodiment of the present invention further provides a computer device, as shown in FIG. 5, including:
  • a memory 501 configured to store program instructions
  • the processor 502 is configured to invoke a program instruction stored in the memory 501, and execute the method for detecting the image nodule according to the obtained program.
  • an embodiment of the present invention further provides a computer readable non-volatile storage medium, comprising computer readable instructions, when the computer device reads and executes the computer readable instructions, causing the computer device to execute The above method of image nodule detection.
  • an embodiment of the present invention further provides a computer program product, the computer program product comprising a computer program stored on a computer readable non-volatile storage medium, the computer program comprising program instructions The method of causing the computer device to perform the image nodule detection described above when the program instructions are executed by a computer device.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

一种影像结节检测的方法及装置，该方法包括通过获取结节影像以及结节影像中候选结节的三维坐标（201），根据候选结节的三维坐标从结节影像中确定包含候选结节的ROI（202），根据ROI以及结节检测模型确定出候选结节的置信度（203），根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和候选结节的三维坐标，过滤掉置信度大于阈值的候选结节中的假阳性的候选结节，确定出结节影像中的结节以及结节对应的置信度（204）。由于采用卷积神经网络对已标记结节区域的结节影像进行训练得到结节检测模型，将ROI输入至结节检测模型得到候选结节的置信度，提高的结节检测的效率，并在检测出结节后再过滤掉假阳性的结节，从而提高了结节检测的准确率。

Description

一种影像结节检测的方法及装置
本申请要求在2018年04月17日提交中国专利局、申请号为201810345297.3、申请名称为“一种影像结节检测的方法及装置”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。
技术领域
本发明实施例涉及机器学习技术领域，尤其涉及一种影像结节检测的方法及装置。
背景技术
目前，结节己引起广泛关注，例如肺结节、甲状腺结节等等，医生一般通过医学影像手段观察患者结节的情况。由于随着时间的增长，患者的结节可能发生变化，例如，增大、减小，或者，长出新的结节等等。目前从医学影像中找出结节的方式主要是通过医生人工观察医学影像来查找出医学影像中对应的存在的结节，但是这种情况会导致找出的结节准确性不高，同时也会耗费大量的时间，并且存在较大的主观性。
发明内容
本发明实施例提供一种影像结节检测的方法及装置，用以提高结节检测的效率，以及提高结节检测的准确率。
本发明实施例提供的一种影像结节检测的方法，包括：
获取结节影像以及所述结节影像中候选结节的三维坐标；
根据所述候选结节的三维坐标从所述结节影像中确定包含所述候选结节的感兴趣区域(Region of Interest，简称ROI)；
根据所述ROI以及结节检测模型确定出所述候选结节的置信度，所述结节检测模型是采用卷积神经网络对已标记结节区域的多个结节影响进行训练 后确定的；
根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和所述候选结节的三维坐标，过滤掉所述置信度大于阈值的候选结节中的假阳性的候选结节，确定出所述结节影像中的结节以及所述结节对应的置信度。
由于采用卷积神经网络对已标记结节区域的结节影像进行训练得到结节检测模型，从而可以将ROI直接输入至结节检测模型就可以得到对应的候选结节的置信度，提高的结节检测的效率，并且在检测出结节后再过滤掉假阳性的结节，从而提高了结节检测的准确率。
可选的，所述根据所述候选结节的三维坐标从所述结节影像中确定所述候选结节的感兴趣区域ROI，包括：
以所述候选结节的三维坐标为中心，向周围扩展预设距离，确定包含所述候选结节的像素立方体，所述预设距离为所述候选结节的半径的预设倍数；
对所述像素立方体中每一个像素附加一个空间信息通道，确定所述ROI，所述空间信息通道为所述像素与所述结节的三维坐标之间的距离。
通过确定的ROI可以得到输入至结节检测模型的输入值，从而适用结节检测模型的输入，提高输入值的统一。
可选的，所述根据所述ROI以及结节检测模型确定出包含所述候选结节的置信度，包括：
将所述ROI依次通过M个3D卷积特征提取模块提取所述ROI的特征图像，M大于0；
将提取的所述ROI的特征图像输入至全连接模块，确定出所述候选结节的置信度。
通过结节检测模型检测出候选结节的置信度，从而提高了结节检测的效率。
可选的，所述根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和所述候选结节的三维坐标及半径，过滤掉所述置信度大于阈值的候选结节中的假阳性的候选结节，包括：
根据所述候选结节的三维坐标和所述候选结节所在预设区域内的像素，过滤掉所述置信度大于阈值的候选结节中的骨骼类假阳性的候选结节；或
根据所述候选结节的三维坐标及半径、所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中膈肌类假阳性的候选结节；或
根据所述候选结节的三维坐标和所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中纵膈类假阳性的候选结节。
通过过滤掉假阳性的结节，可以提高结节检测的准确率。
可选的，所述采用卷积神经网络对已标记结节区域的多个结节影响进行训练后确定所述结节检测模型，包括：
获取待过滤掉假阳性结果的候选结节集和医生对所述候选结节集中各候选结节的判定结果；
对所述候选结节集中的候选结节进行数据增强，得到增强后的候选结节集；
根据增强后的候选结节集以及各候选结节的三维坐标，从结节影像中确定所述增强后的候选结节集中各候选结节的ROI；
将所述增强后的候选结节集中各候选结节的ROI通过预设的3D卷积神经网络模型进行训练，得到所述结节检测模型。
相应的，本发明实施例还提供了一种影像结节检测的装置，包括：
获取单元，用于获取结节影像以及所述结节影像中候选结节的三维坐标；
确定单元，用于根据所述候选结节的三维坐标从所述结节影像中确定包含所述候选结节的ROI；
检测单元，用于根据所述ROI以及结节检测模型确定出所述候选结节的置信度，所述结节检测模型是采用卷积神经网络对已标记结节区域的多个结节影响进行训练后确定的；
过滤单元，用于根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和所述候选结节的三维坐标，过滤掉所述置信度大于阈值的候 选结节中的假阳性的候选结节，确定出所述结节影像中的结节以及所述结节对应的置信度。
可选的，所述确定单元具体用于：
以所述候选结节的三维坐标为中心，向周围扩展预设距离，确定包含所述候选结节的像素立方体，所述预设距离为所述候选结节的半径的预设倍数；
对所述像素立方体中每一个像素附加一个空间信息通道，确定所述ROI，所述空间信息通道为所述像素与所述结节的三维坐标之间的距离。
可选的，所述检测单元具体用于：
将所述ROI依次通过M个3D卷积特征提取模块提取所述ROI的特征图像，M大于0；
将提取的所述ROI的特征图像输入至全连接模块，确定出所述候选结节的置信度。
可选的，所述过滤单元具体用于：
根据所述候选结节的三维坐标和所述候选结节所在预设区域内的像素，过滤掉所述置信度大于阈值的候选结节中的骨骼类假阳性的候选结节；或
根据所述候选结节的三维坐标及半径、所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中膈肌类假阳性的候选结节；或
根据所述候选结节的三维坐标和所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中纵膈类假阳性的候选结节。
可选的，所述检测单元具体用于：
获取待过滤掉假阳性结果的候选结节集和医生对所述候选结节集中各候选结节的判定结果；
对所述候选结节集中的候选结节进行数据增强，得到增强后的候选结节集；
根据增强后的候选结节集以及各候选结节的三维坐标，从结节影像中确定所述增强后的候选结节集中各候选结节的ROI；
将所述增强后的候选结节集中各候选结节的ROI通过预设的3D卷积神经网络模型进行训练，得到所述结节检测模型。
相应的，本发明实施例还提供了一种计算机设备，包括：
存储器，用于存储程序指令；
处理器，用于调用所述存储器中存储的程序指令，按照获得的程序执行上述影像结节检测的方法。
相应的，本发明实施例还提供了一种计算机可读非易失性存储介质，包括计算机可读指令，当计算机设备读取并执行所述计算机可读指令时，使得计算机设备执行上述影像结节检测的方法。
相应的，本发明实施例还提供了一种计算机程序产品，所述计算机程序产品包括存储在计算机可读非易失性存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机设备执行时，使所述计算机设备执行上述影像结节检测的方法。
本发明实施例中，由于采用卷积神经网络对已标记结节区域的结节影像进行训练得到结节检测模型，从而将ROI直接输入至结节检测模型就可以得到对应的候选结节的置信度，提高的结节检测的效率，并且在检测出结节后再过滤掉假阳性的结节，从而提高了结节检测的准确率。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简要介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域的普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例提供的一种***架构的示意图；
图2为本发明实施例提供的一种影像结节检测的方法的流程示意图；
图3为本发明实施例提供的一种结节影像的示意图；
图4为本发明实施例提供的一种影像结节检测的装置的流程示意图；
图5为本发明实施例提供的一种计算机设备的结构示意图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作进一步地详细描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
图1为本发明实施例提供的影像结节检测的方法所适用的***架构。参考图1所示，该***架构可以为服务器100，包括处理器110、通信接口120和存储器130。
其中，通信接口120用于医生适用的终端设备进行通信，收发该终端设备传输的信息，实现通信。
处理器110是服务器100的控制中心，利用各种接口和线路连接整个服务器100的各个部分，通过运行或执行存储在存储器130内的软件程序/或模块，以及调用存储在存储器130内的数据，执行服务器100的各种功能和处理数据。可选地，处理器110可以包括一个或多个处理单元。
存储器130可用于存储软件程序以及模块，处理器110通过运行存储在存储器130的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器130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业务处理所创建的数据等。此外，存储器130可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
需要说明的是，上述图1所示的结构仅是一种示例，本发明实施例对此不做限定。
基于上述描述，图2示例性的示出了本发明实施例提供的一种影像结节 检测的流程，该流程可以由影像结节检测的装置执行。
如图2所示，该流程具体包括：
步骤201，获取结节影像以及所述结节影像中候选结节的三维坐标。
结节影像为三维图像，候选结节的三维坐标可以为候选结节内的点的三维坐标(比如结节中心点的三维坐标)，也可以是候选结节表面的点的三维坐标。候选结节包括但不限于肺结节、甲状腺结节、乳腺结节。结节影像可以是计算机体层摄影(Computed Tomography，简称CT)影像、磁共振成像(Magnetic Resonance Imaging，简称MRI)影像等等，为了更清楚的描述结节影像，图3示例性示出了一名患者的肺部CT影像。
步骤202，根据所述候选结节的三维坐标从所述结节影像中确定所述候选结节的ROI。
具体的，可以以候选结节的三维坐标为中心，向周围扩展预设距离，确定包含该候选结节的像素立方体，其中，该预设距离为候选结节的半径的预设倍数，比如候选结节半径的1.25倍。然后截取此像素立方体，并插值缩放到一定的大小。之后再对该像素立方体中每一个像素附加一个空间信息通道，输出ROI，空间信息通道为像素立方体与候选结节的三维坐标之间的距离。举例来说，这里可以是以候选结节的三维坐标为中心，向三个坐标轴各方向延伸L像素，就可以选取一个2L*2L*2L大小的像素立方体。
步骤203，根据所述ROI以及结节检测模型确定出所述候选结节的置信度。
在本发明实施例中，该结节检测模型是采用卷积神经网络对已标记结节区域的多个结节影响进行训练后得到的，具体可以为：先获取待过滤掉假阳性结果的候选结节集和医生对所述候选结节集中各候选结节的判定结果，该待过滤假阳性结果的候选结节集是收集了大量胸部CT影像后使用其他方案获取的，再通过多名医生对候选结节集中的候选结节进行判定，判定是不是结节。
然后对该候选结节集中的候选结节进行数据增强，得到增强后的候选结 节集。例如可以将数据量增强到之前的K倍，可能的方式可以为通过随机水平镜像，随机旋转任意角度、随机上下左右平移0～5像素、随机说吧0.85～1.15倍等方式来将数据量增强到之前的K倍。
再根据增强后的候选结节集以及各候选结节的三维坐标，从结节影像中确定出增强后的候选结节集中各候选结节的ROI，具体的确定方法可以参见步骤203，不再赘述。
最后将增强后的候选结节集中各候选结节的ROI通过预设的3D卷积神经网络模型进行训练，得到结节检测模型。在训练时，可以将3D卷积神经网络模型输出的结节置信度，和训练样本的label做交叉熵，作为loss函数，并通过反向传播的方法进行训练，训练的优化算法为SGD。
通过上述步骤得到的结节检测模型包括M个3D卷积特征提取模型和一个全连接模块。而每个3D卷积特征提取模型还包括一个J*J*J的3D卷积层和一个H*H*H的max_pool层。全连接模型可以包括两个全连接层。
在具体使用结节检测模型时，可以将上述步骤202得到的ROI依次通过M个3D卷积特征提取模块提取ROI的特征图像，然后将提取的ROI的特征图像输入至全连接模块，确定出候选结节的置信度，从而得到对应的候选结节，提高了候选结节检测的效率。
步骤204，根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和所述候选结节的三维坐标，过滤掉所述置信度大于阈值的候选结节中的假阳性的候选结节。
为了得到更准确的候选结节，还需要对步骤203中得到的候选结节进行过滤筛选。其中，候选结节所在身体部位的分割结果是通过其他途径获得的。该身体部分可以为肺、甲状腺、乳腺等身体部位，本发明实施例对此不做限制。
在具体过滤的过程中，可以根据候选结节的三维坐标和候选结节所在预设区域内的像素，过滤掉置信度大于阈值的候选结节中的骨骼类假阳性的候选结节。该阈值可以依据经验进行设置。例如，可以从候选结节的三维坐标 开始，向四周扩展Imm区域，共I*I*Imm 3的区域。然后统计区域内CT值大于400的像素，如果占据的比例大于第一阈值，则就可以视为骨骼类假阳性的候选结节，从而可以过滤掉。
也可以根据候选结节的三维坐标及半径、候选结节所在身体部位的分割结果，过滤掉置信度大于阈值的候选结节中膈肌类假阳性的候选结节。例如，从候选结节的三维坐标开始，向四周扩展直径大小的区域块，统计区域块中肺内与肺外的像素的数目，如果肺内像素数目和肺外像素的数目在结节图像中占据的比例相似，且基本在图像的中间位置，则就可以视为是膈肌类假阳性的候选结节，从而可以过滤掉。
还可以根据候选结节的三维坐标和候选结节所在身体部位的分割结果，过滤掉置信度大于阈值的候选结节中纵膈类假阳性的候选结节。例如，如果候选结节的中心在肺外，且垂直方向不超过肺范围，且在中央位置，也可以说X轴上相对位置在0.45～0.55之间，则就可以视为是纵膈类假阳性的候选结节。
通过上述过滤方法，过滤掉假阳性的候选结节后，得到的就是最终的结节的置信度，从而可以提高结节检测的准确度。
上述实施例表明，通过获取结节影像以及结节影像中候选结节的三维坐标，根据候选结节的三维坐标从结节影像中确定包含候选结节的ROI，根据ROI以及结节检测模型确定出候选结节的置信度，结节检测模型是采用卷积神经网络对已标记结节区域的多个结节影响进行训练后确定的，根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和候选结节的三维坐标，过滤掉置信度大于阈值的候选结节中的假阳性的候选结节，确定出结节影像中的结节以及所述结节对应的置信度。由于采用卷积神经网络对已标记结节区域的结节影像进行训练得到结节检测模型，从而可以将ROI直接输入至结节检测模型就可以得到对应的候选结节的置信度，提高的结节检测的效率，并且在检测出结节后再过滤掉假阳性的结节，从而提高了结节检测的准确率。
基于相同的技术构思，图4示例性的示出了本发明实施例提供的一种影像结节检测的装置，该装置可以执行影像结节检测的流程。
如图4所示，该装置具体包括：
获取单元401，用于获取结节影像以及所述结节影像中候选结节的三维坐标；
确定单元402，用于根据所述候选结节的三维坐标从所述结节影像中确定包含所述候选结节的ROI；
检测单元403，用于根据所述ROI以及结节检测模型确定出所述候选结节的置信度，所述结节检测模型是采用卷积神经网络对已标记结节区域的多个结节影响进行训练后确定的；
过滤单元404，用于根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和所述候选结节的三维坐标，过滤掉所述置信度大于阈值的候选结节中的假阳性的候选结节，确定出所述结节影像中的结节以及所述结节对应的置信度。
可选的，所述确定单元402具体用于：
以所述候选结节的三维坐标为中心，向周围扩展预设距离，确定包含所述候选结节的像素立方体，所述预设距离为所述候选结节的半径的预设倍数；
对所述像素立方体中每一个像素附加一个空间信息通道，确定所述ROI，所述空间信息通道为所述像素与所述结节的三维坐标之间的距离。
可选的，所述检测单元403具体用于：
将所述ROI依次通过M个3D卷积特征提取模块提取所述ROI的特征图像，M大于0；
将提取的所述ROI的特征图像输入至全连接模块，确定出所述候选结节的置信度。
可选的，所述过滤单元404具体用于：
根据所述候选结节的三维坐标和所述候选结节所在预设区域内的像素，过滤掉所述置信度大于阈值的候选结节中的骨骼类假阳性的候选结节；或
根据所述候选结节的三维坐标及半径、所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中膈肌类假阳性的候选结节；或
根据所述候选结节的三维坐标和所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中纵膈类假阳性的候选结节。
可选的，所述检测单元403具体用于：
获取待过滤掉假阳性结果的候选结节集和医生对所述候选结节集中各候选结节的判定结果；
对所述候选结节集中的候选结节进行数据增强，得到增强后的候选结节集；
根据增强后的候选结节集以及各候选结节的三维坐标，从结节影像中确定所述增强后的候选结节集中各候选结节的ROI；
将所述增强后的候选结节集中各候选结节的ROI通过预设的3D卷积神经网络模型进行训练，得到所述结节检测模型。
基于相同的技术构思，本发明实施例还提供了一种计算机设备，如图5所示，包括：
存储器501，用于存储程序指令；
处理器502，用于调用所述存储器501中存储的程序指令，按照获得的程序执行上述影像结节检测的方法。
基于相同的技术构思，本发明实施例还提供了一种计算机可读非易失性存储介质，包括计算机可读指令，当计算机设备读取并执行所述计算机可读指令时，使得计算机设备执行上述影像结节检测的方法。
基于相同的技术构思，本发明实施例还提供了一种计算机程序产品，所述计算机程序产品包括存储在计算机可读非易失性存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机设备执行时，使所述计算机设备执行上述影像结节检测的方法。
本发明是参照根据本发明实施例的方法、设备(***)、和计算机程序产 品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。

Claims (13)

  1. 一种影像结节检测的方法，其特征在于，包括：
    获取结节影像以及所述结节影像中候选结节的三维坐标；
    根据所述候选结节的三维坐标从所述结节影像中确定包含所述候选结节的感兴趣区域ROI；
    根据所述ROI以及结节检测模型确定出所述候选结节的置信度，所述结节检测模型是采用卷积神经网络对已标记结节区域的多个结节影响进行训练后确定的；
    根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和所述候选结节的三维坐标，过滤掉所述置信度大于阈值的候选结节中的假阳性的候选结节，确定出所述结节影像中的结节以及所述结节对应的置信度。
  2. 如权利要求1所述的方法，其特征在于，所述根据所述候选结节的三维坐标从所述结节影像中确定包含所述候选结节的ROI，包括：
    以所述候选结节的三维坐标为中心，向周围扩展预设距离，确定包含所述候选结节的像素立方体，所述预设距离为所述候选结节的半径的预设倍数；
    对所述像素立方体中每一个像素附加一个空间信息通道，确定所述ROI，所述空间信息通道为所述像素与所述结节的三维坐标之间的距离。
  3. 如权利要求1所述的方法，其特征在于，所述根据所述ROI以及结节检测模型确定出所述候选结节的置信度，包括：
    将所述ROI依次通过M个3D卷积特征提取模块提取所述ROI的特征图像，M大于0；
    将提取的所述ROI的特征图像输入至全连接模块，确定出所述候选结节的置信度。
  4. 如权利要求1所述的方法，其特征在于，所述根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和所述候选结节的三维坐标及半径，过滤掉所述置信度大于阈值的候选结节中的假阳性的候选结节，包括：
    根据所述候选结节的三维坐标和所述候选结节所在预设区域内的像素，过滤掉所述置信度大于阈值的候选结节中的骨骼类假阳性的候选结节；或
    根据所述候选结节的三维坐标及半径、所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中膈肌类假阳性的候选结节；或
    根据所述候选结节的三维坐标和所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中纵膈类假阳性的候选结节。
  5. 如权利要求1所述的方法，其特征在于，所述采用卷积神经网络对已标记结节区域的多个结节影响进行训练后确定所述结节检测模型，包括：
    获取待过滤掉假阳性结果的候选结节集和医生对所述候选结节集中各候选结节的判定结果；
    对所述候选结节集中的候选结节进行数据增强，得到增强后的候选结节集；
    根据增强后的候选结节集以及各候选结节的三维坐标，从结节影像中确定所述增强后的候选结节集中各候选结节的ROI；
    将所述增强后的候选结节集中各候选结节的ROI通过预设的3D卷积神经网络模型进行训练，得到所述结节检测模型。
  6. 一种影像结节检测的装置，其特征在于，包括：
    获取单元，用于获取结节影像以及所述结节影像中候选结节的三维坐标；
    确定单元，用于根据所述候选结节的三维坐标从所述结节影像中确定包含所述候选结节的感兴趣区域ROI；
    检测单元，用于根据所述ROI以及结节检测模型确定出所述候选结节的置信度，所述结节检测模型是采用卷积神经网络对已标记结节区域的多个结节影响进行训练后确定的；
    过滤单元，用于根据置信度大于阈值的候选结节、候选结节所在身体部位的分割结果和所述候选结节的三维坐标，过滤掉所述置信度大于阈值的候选结节中的假阳性的候选结节，确定出所述结节影像中的结节以及所述结节 对应的置信度。
  7. 如权利要求6所述的装置，其特征在于，所述确定单元具体用于：
    以所述候选结节的三维坐标为中心，向周围扩展预设距离，确定包含所述候选结节的像素立方体，所述预设距离为所述候选结节的半径的预设倍数；
    对所述像素立方体中每一个像素附加一个空间信息通道，确定所述ROI，所述空间信息通道为所述像素与所述结节的三维坐标之间的距离。
  8. 如权利要求6所述的装置，其特征在于，所述检测单元具体用于：
    将所述ROI依次通过M个3D卷积特征提取模块提取所述ROI的特征图像，M大于0；
    将提取的所述ROI的特征图像输入至全连接模块，确定出所述候选结节的置信度。
  9. 如权利要求6所述的装置，其特征在于，所述过滤单元具体用于：
    根据所述候选结节的三维坐标和所述候选结节所在预设区域内的像素，过滤掉所述置信度大于阈值的候选结节中的骨骼类假阳性的候选结节；或
    根据所述候选结节的三维坐标及半径、所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中膈肌类假阳性的候选结节；或
    根据所述候选结节的三维坐标和所述候选结节所在身体部位的分割结果，过滤掉所述置信度大于阈值的候选结节中纵膈类假阳性的候选结节。
  10. 如权利要求6所述的装置，其特征在于，所述检测单元具体用于：
    获取待过滤掉假阳性结果的候选结节集和医生对所述候选结节集中各候选结节的判定结果；
    对所述候选结节集中的候选结节进行数据增强，得到增强后的候选结节集；
    根据增强后的候选结节集以及各候选结节的三维坐标，从结节影像中确定所述增强后的候选结节集中各候选结节的ROI；
    将所述增强后的候选结节集中各候选结节的ROI通过预设的3D卷积神 经网络模型进行训练，得到所述结节检测模型。
  11. 一种计算机设备，其特征在于，包括：
    存储器，用于存储程序指令；
    处理器，用于调用所述存储器中存储的程序指令，按照获得的程序执行权利要求1至5任一项所述的方法。
  12. 一种计算机可读非易失性存储介质，其特征在于，包括计算机可读指令，当计算机设备读取并执行所述计算机可读指令时，使得计算机设备执行如权利要求1至5任一项所述的方法。
  13. 一种计算机程序产品，其特征在于，包括存储在计算机可读非易失性存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机设备执行时，使所述计算机设备执行如权利要求1至5任一项所述的方法。
PCT/CN2019/082677 2018-04-17 2019-04-15 一种影像结节检测的方法及装置 WO2019201204A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810345297.3 2018-04-17
CN201810345297.3A CN108648178A (zh) 2018-04-17 2018-04-17 一种影像结节检测的方法及装置

Publications (1)

Publication Number Publication Date
WO2019201204A1 true WO2019201204A1 (zh) 2019-10-24

Family

ID=63746380

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/082677 WO2019201204A1 (zh) 2018-04-17 2019-04-15 一种影像结节检测的方法及装置

Country Status (2)

Country Link
CN (1) CN108648178A (zh)
WO (1) WO2019201204A1 (zh)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108648178A (zh) * 2018-04-17 2018-10-12 杭州依图医疗技术有限公司 一种影像结节检测的方法及装置
CN109363698B (zh) * 2018-10-16 2022-07-12 杭州依图医疗技术有限公司 一种乳腺影像征象识别的方法及装置
CN109492547B (zh) * 2018-10-24 2022-03-08 腾讯科技（深圳）有限公司 一种结节识别方法、装置和存储介质
CN109816655B (zh) * 2019-02-01 2021-05-28 华院计算技术(上海)股份有限公司 基于ct图像的肺结节图像特征检测方法
CN110136253B (zh) * 2019-05-22 2022-08-23 珠海横琴圣澳云智科技有限公司 一种结节三维立体展示装置及设备
CN111062947B (zh) * 2019-08-14 2023-04-25 深圳市智影医疗科技有限公司 一种基于深度学习的x光胸片病灶定位方法及***
CN110580948A (zh) * 2019-09-12 2019-12-17 杭州依图医疗技术有限公司 医学影像的显示方法及显示设备
CN111179247A (zh) * 2019-12-27 2020-05-19 上海商汤智能科技有限公司 三维目标检测方法及其模型的训练方法及相关装置、设备
CN111513765B (zh) * 2020-04-26 2022-08-09 深圳华声医疗技术股份有限公司 呼吸肌组织的超声测量方法、超声测量装置及存储介质
CN111768845B (zh) * 2020-06-30 2023-08-11 重庆大学 一种基于最优多尺度感知的肺结节辅助检测方法
CN111951293A (zh) * 2020-06-30 2020-11-17 杭州依图医疗技术有限公司 根据置信度显示结节的方法及计算设备
CN112002406A (zh) * 2020-07-10 2020-11-27 杭州依图医疗技术有限公司 基于置信度的结节显示方法及计算设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8224057B2 (en) * 2007-10-18 2012-07-17 Siemens Aktiengesellschaft Method and system for nodule feature extraction using background contextual information in chest x-ray images
CN106504232A (zh) * 2016-10-14 2017-03-15 北京网医智捷科技有限公司 一种基于3d卷积神经网络的肺部结节自动检测方法
CN107016665A (zh) * 2017-02-16 2017-08-04 浙江大学 一种基于深度卷积神经网络的ct肺结节检测方法
CN107480677A (zh) * 2017-08-07 2017-12-15 北京深睿博联科技有限责任公司 一种识别三维ct图像中感兴趣区域的方法及装置
CN108648178A (zh) * 2018-04-17 2018-10-12 杭州依图医疗技术有限公司 一种影像结节检测的方法及装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6125194A (en) * 1996-02-06 2000-09-26 Caelum Research Corporation Method and system for re-screening nodules in radiological images using multi-resolution processing, neural network, and image processing
CN100562291C (zh) * 2006-11-08 2009-11-25 沈阳东软医疗***有限公司 一种针对ct图像的处理装置、方法及***
EP2208183B1 (en) * 2007-11-14 2018-05-02 Koninklijke Philips N.V. Computer-aided detection (cad) of a disease
CN105513036B (zh) * 2014-09-26 2019-05-31 上海联影医疗科技有限公司 三维ct图像的分割方法及装置
CN105912831B (zh) * 2015-02-19 2021-08-20 松下知识产权经营株式会社 信息终端的控制方法
CN104751178B (zh) * 2015-03-31 2018-04-03 上海理工大学 基于形状模板匹配结合分类器的肺结节检测装置及方法
CN106940816B (zh) * 2017-03-22 2020-06-09 杭州健培科技有限公司 基于3d全卷积神经网络的ct图像肺结节检测***
CN107154043B (zh) * 2017-06-05 2020-03-24 杭州健培科技有限公司 一种基于3dcnn的肺结节假阳性样本抑制方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8224057B2 (en) * 2007-10-18 2012-07-17 Siemens Aktiengesellschaft Method and system for nodule feature extraction using background contextual information in chest x-ray images
CN106504232A (zh) * 2016-10-14 2017-03-15 北京网医智捷科技有限公司 一种基于3d卷积神经网络的肺部结节自动检测方法
CN107016665A (zh) * 2017-02-16 2017-08-04 浙江大学 一种基于深度卷积神经网络的ct肺结节检测方法
CN107480677A (zh) * 2017-08-07 2017-12-15 北京深睿博联科技有限责任公司 一种识别三维ct图像中感兴趣区域的方法及装置
CN108648178A (zh) * 2018-04-17 2018-10-12 杭州依图医疗技术有限公司 一种影像结节检测的方法及装置

Also Published As

Publication number Publication date
CN108648178A (zh) 2018-10-12

Similar Documents

Publication Publication Date Title
WO2019201204A1 (zh) 一种影像结节检测的方法及装置
US10846853B2 (en) Medical image processing apparatus, medical image processing method, and medical image processing program
US10878573B2 (en) System and method for segmentation of lung
US10980493B2 (en) Medical image display device, method, and program
US10452957B2 (en) Image classification apparatus, method, and program
WO2020182036A1 (zh) 图像处理方法、装置、服务器及存储介质
US10748282B2 (en) Image processing system, apparatus, method and storage medium
JP2017174039A (ja) 画像分類装置、方法およびプログラム
US11741598B2 (en) Method for aiding visualization of lesions in medical imagery and apparatus using the same
US20220101034A1 (en) Method and system for segmenting interventional device in image
US20210056337A1 (en) Recognition processing device, recognition processing method, and program
CN114332132A (zh) 图像分割方法、装置和计算机设备
TWI714025B (zh) 影像辨識方法及影像辨識裝置
CN108597589B (zh) 模型生成方法、目标检测方法及医学成像***
CN112446911A (zh) 中心线提取、界面交互与模型训练方法、***及设备
WO2013037702A1 (en) Method and a system for medical imaging
CN114092470B (zh) 一种基于深度学习的肺裂自动检测方法及装置
JP7321671B2 (ja) 情報処理装置、情報処理方法、情報処理システムおよびプログラム
CN112712507A (zh) 一种确定冠状动脉的钙化区域的方法及装置
JP6634186B2 (ja) 画像処理システム及び画像処理方法
CN111353975A (zh) 网络模型训练方法及装置、病灶定位方法及装置
CN111311553A (zh) 基于感兴趣区域的乳腺肿瘤识别方法、装置及存储介质
CN111951293A (zh) 根据置信度显示结节的方法及计算设备
CN111986165B (zh) 一种***图像中的钙化检出方法及装置
KR20230138011A (ko) 2차원 이미지들의 주석

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: 19787871

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19787871

Country of ref document: EP

Kind code of ref document: A1

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 10.03.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19787871

Country of ref document: EP

Kind code of ref document: A1