CN111292289B - CT lung tumor segmentation method, device, equipment and medium based on segmentation network - Google Patents
CT lung tumor segmentation method, device, equipment and medium based on segmentation network Download PDFInfo
- Publication number
- CN111292289B CN111292289B CN201811493978.0A CN201811493978A CN111292289B CN 111292289 B CN111292289 B CN 111292289B CN 201811493978 A CN201811493978 A CN 201811493978A CN 111292289 B CN111292289 B CN 111292289B
- Authority
- CN
- China
- Prior art keywords
- image
- lung
- segmentation
- sampling
- region
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
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
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/30061—Lung
-
- 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
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Processing (AREA)
Abstract
The invention is applicable to the technical field of medical image processing, and provides a CT lung tumor segmentation method, device, equipment and medium based on a segmentation network, wherein the method comprises the following steps: the lung pretreatment image obtained through pretreatment is subjected to image segmentation by adopting a first segmentation network to obtain a lung tumor initial segmentation image, the lung pretreatment image and the lung tumor initial segmentation image are subjected to resampling according to pixel spacing to obtain a corresponding lung sampling image and an initial segmentation sampling image, the initial segmentation sampling image is cut into initial segmentation image blocks with the size of a preset number of image blocks by taking the mass center of the initial segmentation sampling image as the center, and the lung tumor segmentation image corresponding to a lung CT image is obtained by adopting a second segmentation network according to the lung sampling image and the initial segmentation image blocks, so that the accuracy and the integrity of lung tumor segmentation on the lung CT image are improved, the lung tumor segmentation image with high accuracy is obtained, and the safety degree of an operation is improved.
Description
Technical Field
The invention belongs to the technical field of medical image processing, and particularly relates to a CT lung tumor segmentation method, device, equipment and medium based on a segmentation network.
Background
Lung cancer is the most common malignancy worldwide, not only with high incidence, top in the list of malignancies, but also with first mortality. In recent years, due to the economic development, the living environment and the living mode of people are greatly changed, smoking people are enlarged, the long-term psychological stress of people is overlarge, the exercise is lacking, the atmospheric environmental pollution is aggravated, and the incidence rate of lung cancer is continuously increased. The rapid development of computed tomography (Computed Tomography, CT) technology has continuously affected the diagnosis of human diseases, and CT images have become one of the important conventional means in clinical diagnosis and treatment.
At present, lung tumor treatment means mainly comprise tumor excision, intervention, radiation treatment and the like, and the tumor excision is the most effective treatment mode. CT tumor segmentation is generally used for operation planning before tumor resection, three-dimensional visualization in operation, operation resection scheme design, operation risk assessment, etc., and is used for extracting organ or tissue characteristics in computer-aided diagnosis, and then qualitative and quantitative analysis is performed to observe the change condition of tumor in radiotherapy process, however, the position, size and shape of lung tumor are changeable, gray scale is similar to adjacent lung blood vessel, and small tumor is difficult to identify. Traditional manual segmentation requires anatomic knowledge and experience, subjective variability, and takes a lot of time and effort until the breakthrough progress of the deep convolutional neural network makes automatic segmentation of lung tumors possible. The existing automatic lung tumor segmentation method depends on lung tumor segmentation based on a threshold segmentation method, and the method is easy to lose abundant texture information of the lung, so that larger lung tumors are easy to remove, and the segmented lung tumors are incomplete.
Disclosure of Invention
The invention aims to provide a CT lung tumor segmentation method, device, equipment and storage medium based on a segmentation network, and aims to solve the problems that the segmentation accuracy is low and the segmented lung tumor is incomplete because the prior art cannot provide an effective method for segmenting the lung tumor in a lung CT image.
In one aspect, the invention provides a CT lung tumor segmentation method based on a segmentation network, which comprises the following steps:
when a lung tumor segmentation request is received for a lung CT image, preprocessing the lung CT image to obtain a corresponding lung preprocessing image;
image segmentation is carried out on the lung pretreatment image through a pre-trained first segmentation network, so that a corresponding lung tumor initial segmentation image is obtained;
resampling the lung pretreatment image and the lung tumor initial segmentation image according to a preset pixel interval to obtain a corresponding lung sampling image and an initial segmentation sampling image;
cutting the initial segmentation sampling image according to the size of a preset image block by taking the mass center of the initial segmentation sampling image as the center to obtain a preset number of initial segmentation image blocks;
and obtaining a lung tumor segmentation image corresponding to the lung CT image by adopting a pre-trained second segmentation network according to the lung sampling image and the initial segmentation image block.
In another aspect, the present invention provides a CT lung tumor segmentation apparatus based on a segmentation network, the apparatus comprising:
the CT image preprocessing unit is used for preprocessing the lung CT image when a lung tumor segmentation request is received, so as to obtain a corresponding lung preprocessing image;
the first image segmentation unit is used for carrying out image segmentation on the lung pretreatment image through a pre-trained first segmentation network to obtain a corresponding lung tumor initial segmentation image;
the image resampling unit is used for resampling the lung pretreatment image and the lung tumor initial segmentation image according to a preset pixel interval to obtain a corresponding lung sampling image and an initial segmentation sampling image;
the image block obtaining unit is used for cutting the initial segmentation sampling image according to the size of the preset image block by taking the mass center of the initial segmentation sampling image as the center to obtain a preset number of initial segmentation image blocks; and
and the second image segmentation unit is used for obtaining a lung tumor segmentation image corresponding to the lung CT image by adopting a pre-trained second segmentation network according to the lung sampling image and the initial segmentation image block.
In another aspect, the present invention also provides a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps described in the CT lung tumor segmentation method based on the segmentation network as described above when the computer program is executed.
In another aspect, the present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps as described above for a CT lung tumor segmentation method based on a segmentation network.
The lung pretreatment image obtained through pretreatment is subjected to image segmentation by adopting a first segmentation network to obtain a lung tumor initial segmentation image, the lung pretreatment image and the lung tumor initial segmentation image are subjected to resampling according to pixel spacing to obtain a corresponding lung sampling image and an initial segmentation sampling image, the centroid of the initial segmentation sampling image is calculated, the initial segmentation sampling image is cut into initial segmentation image blocks with a preset number of image blocks and the size by taking the centroid as the center, and the lung tumor segmentation image corresponding to a lung CT image is obtained by adopting a second segmentation network according to the lung sampling image and the initial segmentation image blocks, so that the lung tumor area in the lung CT image is positioned by adopting the first segmentation network, and then the lung tumor is segmented by adopting the second segmentation network, thereby improving the accuracy and the integrity of lung tumor segmentation on the lung CT image, further obtaining a high-precision lung tumor segmentation image and improving the safety degree of an operation.
Drawings
Fig. 1 is a flowchart of an implementation of a CT lung tumor segmentation method based on a segmentation network according to an embodiment of the present invention;
FIG. 2 is a flowchart of a second embodiment of the present invention for preprocessing a CT image of a lung;
fig. 3 is a flowchart of an implementation of training a preset split network according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a CT lung tumor segmentation apparatus based on a segmentation network according to a fourth embodiment of the present invention;
fig. 5 is a schematic diagram of a preferred structure of a CT lung tumor segmentation apparatus based on a segmentation network according to a fourth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a CT lung tumor segmentation apparatus based on a segmentation network according to a fifth embodiment of the present invention; and
fig. 7 is a schematic structural diagram of a computing device according to a sixth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The following describes in detail the implementation of the present invention in connection with specific embodiments:
embodiment one:
fig. 1 shows a flow of implementation of a CT lung tumor segmentation method based on a segmentation network according to an embodiment of the present invention, and for convenience of explanation, only the portions relevant to the embodiment of the present invention are shown, which is described in detail below:
in step S101, when a lung tumor segmentation request is received for a lung CT image, the lung CT image is preprocessed to obtain a corresponding lung preprocessed image.
The embodiment of the invention is applicable to medical image processing platforms, systems or devices, such as personal computers, servers and the like. In the embodiment of the invention, since the CT image is formed by arranging a certain number of pixels with different gray scales from black to white according to a matrix, the different gray scales of the CT image reflect the absorption degree of corresponding organs and tissues on X rays, the black area represents a low-absorption area, namely a low-density area, such as a lung containing a large amount of gas, and the white area represents a high-absorption area, namely a high-density area, such as bones, so that the anatomical structure of certain organs of a human body and the characteristics of pathological tissues with changed density in the organs can be clearly obtained according to the CT image, the lung CT image of a patient can be generated by performing the tomographic scanning on the lung of the patient, and the pathological tissues of the lung of the patient can be found through the lung CT image, thereby performing treatment. When a user needs to divide a lung CT image of a patient into lung tumors, a lung tumor division request is sent, wherein the user can obtain the lung CT image of the patient from a published medical image database or a surgical image provided by a hospital, when the lung tumor division request is received, the lung CT image input by the user is obtained, and the obtained lung CT image is preprocessed to obtain a corresponding lung preprocessing image.
In step S102, an image of the lung pretreatment image is segmented by a pre-trained first segmentation network, so as to obtain a corresponding lung tumor initial segmentation image.
In an embodiment of the present invention, image segmentation is a technique and process that divides an image into a number of specific regions with unique properties and proposes an object of interest. Inputting the lung pretreatment image into a first segmentation network trained in advance for image segmentation, and extracting a lung tumor area in the lung pretreatment image to obtain a corresponding lung tumor initial segmentation image with coarse granularity.
In step S103, resampling the lung pretreatment image and the lung tumor initial segmentation image according to the preset pixel pitch to obtain a corresponding lung sampling image and initial segmentation sampling image.
In the embodiment of the invention, the lung preprocessing image is resampled to a preset pixel spacing (namely pixel space spacing) to obtain a lung sampling image, and the lung tumor initial segmentation image is resampled to the pixel spacing to obtain a corresponding initial segmentation sampling image.
Before resampling the lung pretreatment image and the lung tumor initial segmentation image according to a preset pixel pitch, the pixel pitch is preferably set to be 1mm×1mm×2mm, so that image information of the lung sampling image and the initial segmentation sampling image is increased, and image quality of the lung sampling image and the initial segmentation sampling image is further improved.
In step S104, the initial divided sample image is cut according to the preset image block size with the centroid of the initial divided sample image as the center, to obtain a preset number of initial divided image blocks.
In the embodiment of the invention, the centroid of the initial segmentation sampling image is calculated, and a preset number of initial segmentation image blocks with preset image block sizes are extracted from the initial segmentation sampling image by taking the calculated centroid as the center.
Before cropping the initial divided sample image, the image block size is preferably set to 128×128×64, thereby improving the image quality of the initial divided image block.
When clipping the initial segmentation sample image, it is preferable to set the pixel gray value of the centroid of the initial segmentation sample image to 2, so as to improve the brightness of the pixel at the centroid, and further improve the accuracy of the subsequent lung tumor segmentation.
In step S105, a lung tumor segmented image corresponding to the lung CT image is obtained by using a pre-trained second segmentation network according to the lung sampling image and the initial segmented image block.
In the embodiment of the invention, the lung sampling image and all the initial segmentation image blocks are input into a pre-trained second segmentation network, and the lung tumor segmentation image is output through the second segmentation network, namely the final lung tumor segmentation image with fine granularity obtained by segmenting the lung tumor region in the lung CT image.
In the embodiment of the invention, a first segmentation network is adopted to carry out image segmentation on a lung pretreatment image obtained through pretreatment to obtain a lung tumor initial segmentation image, the lung pretreatment image and the lung tumor initial segmentation image are resampled according to pixel spacing to obtain a corresponding lung sampling image and an initial segmentation sampling image, the initial segmentation sampling image is cut into initial segmentation image blocks with a preset number of image blocks by taking the center of mass of the initial segmentation sampling image as the center, and a lung tumor segmentation image corresponding to a lung CT image is obtained by adopting a second segmentation network according to the lung sampling image and the initial segmentation image blocks, so that a lung tumor area in the lung CT image is positioned through the first segmentation network, and then the lung tumor is segmented through the second segmentation network, thereby improving the accuracy and the integrity of lung tumor segmentation on the lung CT image, further obtaining a high-precision lung tumor segmentation image and improving the safety degree of surgery.
Embodiment two:
fig. 2 shows a flow of preprocessing a lung CT image according to the second embodiment of the present invention, and for convenience of explanation, only the portions related to the second embodiment of the present invention are shown, which is described in detail below:
in step S201, an air communication region in a lung CT image is extracted according to a preset seed point.
In the embodiment of the invention, the air communication area in the lung CT image, namely the background area of the lung CT image, is extracted by using a preset seed point as a starting point and adopting an area growth method.
Before extracting the air-connected region in the lung CT image, the first pixel point in the upper left corner of the lung CT image is preferably set as a seed point, thereby improving the accuracy and integrity of the air-connected region extraction.
In step S202, the extracted air-connected region is removed from the lung CT image, and a corresponding body mask region image is obtained.
In the embodiment of the invention, the air communication area is cut off from the lung CT image to obtain the corresponding body mask area image, thereby removing noise in the lung CT image and improving the image quality of the obtained body mask area image.
In step S203, the body mask region image is subjected to threshold segmentation to obtain a left lung maximum communication region and a right lung maximum communication region.
In the embodiment of the invention, the body mask region is subjected to image segmentation by a threshold segmentation method, so that a left lung maximum communication region and a right lung maximum communication region in the body mask region image are obtained.
In thresholding the body mask region image, the body mask region is preferably thresholded according to a thresholding method of-1024, -400, thereby improving the accuracy and integrity of the left and right lung maximum connected region segmentation while simplifying the image segmentation of the body mask region.
In step S204, the region of interest is extracted from the CT image of the lung according to the maximum communication region of the left lung and the maximum communication region of the right lung, so as to obtain a corresponding image of the region of interest of the lung.
In step S205, gray scale transformation is performed on the lung region of interest image according to a preset gray scale transformation formula, and normalization processing is performed on the lung region of interest image after gray scale transformation, so as to obtain a lung preprocessing image corresponding to the lung CT image.
In the embodiment of the present invention, preferably, the gray level conversion formula is f (x) =0.2×i (x), where I (x) is a gray level value of an xth pixel point in the maximum left lung connected region or the maximum right lung connected region, and f (x) is a gray level value of the xth pixel point after gray level conversion, so that the contrast ratio of the image of the region of interest of the lung is improved, the image of the region of interest of the lung becomes clearer, finer and more precise, and is easy to identify, and further the display effect of the image of the region of interest of the lung is improved.
When the lung region of interest image after gray level transformation is normalized, preferably, the lung region of interest image after gray level transformation is normalized to [0,1], so that the contrast of the lung region of interest image is further improved, and details of the lung region of interest image are clearer.
In the embodiment of the invention, the robustness and the execution efficiency of the algorithm are improved by carrying out preprocessing such as air communication region cutting, region of interest extraction, threshold segmentation, gray level transformation, gray level normalization and the like on the lung CT image.
Embodiment III:
fig. 3 shows a flow of training a preset split network according to the third embodiment of the present invention, and for convenience of explanation, only the relevant parts of the third embodiment of the present invention are shown, which is described in detail below:
in step S301, resampling the training sample obtained by the preprocessing according to the preset sample sampling size to obtain a first sampled training sample.
In the embodiment of the invention, the training sample obtained by preprocessing is resampled to a preset sample sampling size to obtain a first sampled training sample, wherein the training sample is a lung tumor CT image data set with different shapes and sizes.
Before resampling the preprocessed training samples, the sample size is preferably set to 128×128×64, so as to increase the image information of the first sampled training samples, thereby improving the image quality of the first sampled training samples.
Before resampling the preprocessed training samples, it is further preferred that the preprocessing of the training samples is performed, in particular, by:
1) Extracting an air communication area in a training sample according to a preset seed point;
2) Removing the extracted air communication area from the training sample to obtain a corresponding body mask sample image;
3) Threshold segmentation is carried out on the body mask sample image, so that a left lung maximum communication area and a right lung maximum communication area are obtained;
4) According to the maximum communication area of the left lung and the maximum communication area of the right lung, extracting an interested area of a training sample to obtain a corresponding sample image of the interested area of the lung;
5) And carrying out gray level transformation on the lung region of interest sample image according to a preset gray level transformation formula, and carrying out normalization processing on the lung region of interest sample image after gray level transformation to obtain a preprocessed training sample.
Therefore, the pretreatment of the training samples is realized through the steps 1) to 5), the image characteristic contrast of the training samples is improved, the training samples become clearer, finer and more easily identified, and the training effect of the follow-up segmentation network is further improved.
In step S302, training the preset segmentation network through the first sampling training sample according to the preset training iteration number, so as to obtain a first segmentation network.
In the embodiment of the invention, the iterative training of the preset training iteration times is carried out on the preset segmentation network through the first sampling training sample to obtain the first segmentation network, wherein the preset segmentation network is a semantic segmentation network such as a full convolution network (Fully Convolutional Networks, FCN), segNet, U-Net or V-Net, and the like, the obtained first segmentation network is obtained by inputting the first sampling training sample into the semantic segmentation network to train the semantic segmentation network, so that the first segmentation network can roughly position a lung tumor region in a lung CT image, and the integrity of image segmentation on the lung tumor region in the lung CT image through the first segmentation network is improved.
In step S303, the training samples are resampled according to the pixel pitch, so as to obtain second sampled training samples.
In the embodiment of the present invention, the training sample obtained by the preprocessing is resampled to a preset pixel space (i.e., pixel space), so as to obtain a second sampled training sample, where the training sample is the same as the training sample in step S301.
In step S304, the second sampled training samples are cut according to the size of the image block with the preset positioning point as the center, so as to obtain a preset number of training sample image blocks, where the positioning point is a pixel point of the tumor area in the second sampled training samples.
In the embodiment of the invention, a pixel point is randomly selected from a tumor area in a second sampling training sample as a locating point, and a training sample image block with a preset number of preset image blocks is extracted from the second sampling training sample by taking the locating point as a center.
When the second sampled training sample is cut, the gray value of the pixel of the positioning point is preferably set to 2, so that the brightness of the pixel at the positioning point is improved, and the training effect of the subsequent second segmentation network is further improved.
In step S305, training the preset segmentation network through the training sample image block according to the training iteration number, to obtain a second segmentation network.
In the embodiment of the invention, the second segmentation network is obtained by carrying out iterative training of the preset segmentation network for the preset training iteration times through the training sample image blocks, and the obtained second segmentation network is obtained by inputting all the training sample image blocks into the semantic segmentation network and training the semantic segmentation network, so that the second segmentation network can accurately position lung tumors in lung CT images, and the accuracy of lung tumor image segmentation of the lung CT images through the second segmentation network is improved.
In the embodiment of the invention, the first segmentation network and the second segmentation network are trained in parallel through the lung tumor CT image data sets with different shapes and sizes, so that the training efficiency is improved, and the consumption of memory in the training process is reduced.
Embodiment four:
fig. 4 shows a structure of a CT lung tumor segmentation apparatus based on a segmentation network according to a fourth embodiment of the present invention, and for convenience of explanation, only the portions related to the embodiment of the present invention are shown, including:
a CT image preprocessing unit 41, configured to, when receiving a lung tumor segmentation request for a lung CT image, perform preprocessing on the lung CT image, and obtain a corresponding lung preprocessed image;
a first image segmentation unit 42, configured to perform image segmentation on the lung pretreatment image through a pre-trained first segmentation network, so as to obtain a corresponding lung tumor initial segmentation image;
an image resampling unit 43, configured to resample the lung pretreatment image and the lung tumor initial segmentation image according to a preset pixel pitch, to obtain a corresponding lung sampling image and an initial segmentation sampling image;
an image block obtaining unit 44, configured to crop the initial divided sampling image according to a preset image block size with the centroid of the initial divided sampling image as a center, to obtain a preset number of initial divided image blocks; and
the second image segmentation unit 45 is configured to obtain a lung tumor segmentation image corresponding to the lung CT image by using a pre-trained second segmentation network according to the lung sampling image and the initial segmentation image block.
As shown in fig. 5, preferably, the CT image preprocessing unit 41 includes:
a first region extraction unit 411, configured to extract an air communication region in the lung CT image according to a preset seed point;
a second region extraction unit 412, configured to remove the extracted air-connected region from the lung CT image, so as to obtain a corresponding body mask region image;
an image threshold segmentation unit 413, configured to perform threshold segmentation on the body mask region image, so as to obtain a left lung maximum communication region and a right lung maximum communication region;
a third region extraction unit 414, configured to extract a region of interest from the CT image of the lung according to the maximum communication region of the left lung and the maximum communication region of the right lung, so as to obtain a corresponding image of the region of interest of the lung; and
the normalization processing unit 415 is configured to perform gray level transformation on the lung region of interest image according to a preset gray level transformation formula, and perform normalization processing on the lung region of interest image after gray level transformation, so as to obtain a lung preprocessing image corresponding to the lung CT image.
In the embodiment of the present invention, each unit of the CT lung tumor segmentation apparatus based on the segmentation network may be implemented by a corresponding hardware or software unit, and each unit may be an independent software or hardware unit, or may be integrated into one software or hardware unit, which is not used to limit the present invention. Specifically, the embodiments of each unit may refer to the descriptions of the foregoing method embodiments, which are not repeated herein.
Fifth embodiment:
fig. 6 shows the structure of a CT lung tumor segmentation apparatus based on a segmentation network according to the fifth embodiment of the present invention, and for convenience of explanation, only the portions related to the embodiments of the present invention are shown, including:
a first sample sampling unit 60, configured to resample the training sample obtained by the preprocessing according to a preset sample sampling size, to obtain a first sampled training sample;
a first network training unit 61, configured to train the preset segmentation network through a first sampling training sample according to a preset training iteration number, so as to obtain a first segmentation network;
a second sample sampling unit 62, configured to resample the training sample according to the pixel pitch to obtain a second sampled training sample;
a second sample clipping unit 63, configured to clip the second sampled training samples according to the size of the image block with a preset positioning point as a center, so as to obtain a preset number of image blocks of the training samples, where the positioning point is a pixel point of a tumor area in the second sampled training samples;
a second network training unit 64, configured to train the preset segmentation network through the training sample image block according to the training iteration number, so as to obtain a second segmentation network;
a CT image preprocessing unit 65, configured to, when receiving a lung tumor segmentation request for a lung CT image, perform preprocessing on the lung CT image to obtain a corresponding lung preprocessed image;
a first image segmentation unit 66, configured to perform image segmentation on the lung pretreatment image through a pre-trained first segmentation network, so as to obtain a corresponding lung tumor initial segmentation image;
the image resampling unit 67 is configured to resample the lung pretreatment image and the lung tumor initial segmentation image according to a preset pixel pitch, so as to obtain a corresponding lung sampling image and an initial segmentation sampling image;
an image block obtaining unit 68, configured to crop the initial divided sampling image according to a preset image block size with the centroid of the initial divided sampling image as a center, to obtain a preset number of initial divided image blocks; and
the second image segmentation unit 69 is configured to obtain a lung tumor segmentation image corresponding to the lung CT image by using a pre-trained second segmentation network according to the lung sampling image and the initial segmentation image block.
In the embodiment of the present invention, each unit of the CT lung tumor segmentation apparatus based on the segmentation network may be implemented by a corresponding hardware or software unit, and each unit may be an independent software or hardware unit, or may be integrated into one software or hardware unit, which is not used to limit the present invention. Specifically, the embodiments of each unit may refer to the descriptions of the foregoing method embodiments, which are not repeated herein.
Example six:
fig. 7 shows the structure of a computing device provided in the sixth embodiment of the present invention, and only the portions relevant to the embodiment of the present invention are shown for convenience of explanation.
The computing device 7 of an embodiment of the invention comprises a processor 70, a memory 71 and a computer program 72 stored in the memory 71 and executable on the processor 70. The processor 70, when executing the computer program 72, implements the steps of the embodiment of the CT lung tumor segmentation method based on the segmentation network described above, such as steps S101 to S105 shown in fig. 1. Alternatively, the processor 70, when executing the computer program 72, performs the functions of the units in the above-described device embodiments, for example the functions of the units 41 to 45 shown in fig. 4.
In the embodiment of the invention, a first segmentation network is adopted to carry out image segmentation on a lung pretreatment image obtained through pretreatment to obtain a lung tumor initial segmentation image, the lung pretreatment image and the lung tumor initial segmentation image are resampled according to pixel spacing to obtain a corresponding lung sampling image and an initial segmentation sampling image, the initial segmentation sampling image is cut into initial segmentation image blocks with a preset number of image blocks by taking the center of mass of the initial segmentation sampling image as the center, and a lung tumor segmentation image corresponding to a lung CT image is obtained by adopting a second segmentation network according to the lung sampling image and the initial segmentation image blocks, so that a lung tumor area in the lung CT image is positioned through the first segmentation network, and then the lung tumor is segmented through the second segmentation network, thereby improving the accuracy and the integrity of lung tumor segmentation on the lung CT image, further obtaining a high-precision lung tumor segmentation image and improving the safety degree of surgery.
The computing device of the embodiment of the invention can be a personal computer or a server. The steps implemented when the processor 70 executes the computer program 72 in the computing device 7 to implement the CT lung tumor segmentation method based on the segmentation network may refer to the description of the foregoing method embodiments, which are not repeated herein.
Embodiment seven:
in an embodiment of the present invention, a computer readable storage medium is provided, which stores a computer program which, when executed by a processor, implements the steps in the embodiment of the CT lung tumor segmentation method based on a segmentation network described above, for example, steps S101 to S105 shown in fig. 1. Alternatively, the computer program, when executed by a processor, implements the functions of the units in the above-described respective apparatus embodiments, for example, the functions of the units 41 to 45 shown in fig. 4.
In the embodiment of the invention, a first segmentation network is adopted to carry out image segmentation on a lung pretreatment image obtained through pretreatment to obtain a lung tumor initial segmentation image, the lung pretreatment image and the lung tumor initial segmentation image are resampled according to pixel spacing to obtain a corresponding lung sampling image and an initial segmentation sampling image, the initial segmentation sampling image is cut into initial segmentation image blocks with a preset number of image blocks by taking the center of mass of the initial segmentation sampling image as the center, and a lung tumor segmentation image corresponding to a lung CT image is obtained by adopting a second segmentation network according to the lung sampling image and the initial segmentation image blocks, so that a lung tumor area in the lung CT image is positioned through the first segmentation network, and then the lung tumor is segmented through the second segmentation network, thereby improving the accuracy and the integrity of lung tumor segmentation on the lung CT image, further obtaining a high-precision lung tumor segmentation image and improving the safety degree of surgery.
The computer readable storage medium of embodiments of the present invention may include any entity or device capable of carrying computer program code, recording medium, such as ROM/RAM, magnetic disk, optical disk, flash memory, and so on.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (7)
1. A CT lung tumor segmentation method based on a segmentation network, the method comprising the steps of:
when a lung tumor segmentation request is received for a lung CT image, preprocessing the lung CT image to obtain a corresponding lung preprocessing image;
image segmentation is carried out on the lung pretreatment image through a pre-trained first segmentation network, so that a corresponding lung tumor initial segmentation image is obtained;
resampling the lung pretreatment image and the lung tumor initial segmentation image according to a preset pixel interval to obtain a corresponding lung sampling image and an initial segmentation sampling image;
cutting the initial segmentation sampling image according to the size of a preset image block by taking the mass center of the initial segmentation sampling image as the center to obtain a preset number of initial segmentation image blocks;
obtaining a lung tumor segmentation image corresponding to the lung CT image by adopting a pre-trained second segmentation network according to the lung sampling image and the initial segmentation image block;
the step of preprocessing the acquired lung CT image comprises the following steps:
extracting an air communication region in the lung CT image according to a preset seed point;
removing the extracted air communication area from the lung CT image to obtain a corresponding body mask area image;
threshold segmentation is carried out on the body mask region image to obtain a left lung maximum communication region and a right lung maximum communication region;
extracting the region of interest from the lung CT image according to the maximum left lung communication region and the maximum right lung communication region to obtain a corresponding lung region of interest image;
and carrying out gray level transformation on the lung region-of-interest image according to a preset gray level transformation formula, and carrying out normalization processing on the lung region-of-interest image after gray level transformation to obtain the lung preprocessing image corresponding to the lung CT image.
2. The method of claim 1, wherein thresholding the body mask region image comprises
The body mask region image is thresholded according to a threshold range of-1024, -400.
3. The method of claim 1, wherein the gray scale transformation formula is f (x) =0.2×i (x), where I (x) is a gray scale value of an xth pixel point in the left lung maximum connected area or the right lung maximum connected area, and f (x) is a gray scale value of an xth pixel point after gray scale transformation.
4. The method of claim 1, wherein prior to preprocessing the lung CT image, the method further comprises:
resampling the training sample obtained by pretreatment according to the preset sample sampling size to obtain a first sampling training sample;
training a preset segmentation network through the first sampling training sample according to preset training iteration times to obtain the first segmentation network;
resampling the training sample according to the pixel spacing to obtain a second sampled training sample;
cutting the second sampled training samples according to the size of the image blocks by taking a preset positioning point as a center to obtain a preset number of training sample image blocks, wherein the positioning point is one pixel point of a tumor area in the second sampled training samples;
and training the segmentation network through the training sample image block according to the training iteration times to obtain the second segmentation network.
5. A CT lung tumor segmentation apparatus based on a segmentation network, the apparatus comprising:
the CT image preprocessing unit is used for preprocessing the lung CT image when a lung tumor segmentation request is received, so as to obtain a corresponding lung preprocessing image;
the first image segmentation unit is used for carrying out image segmentation on the lung pretreatment image through a pre-trained first segmentation network to obtain a corresponding lung tumor initial segmentation image;
the image resampling unit is used for resampling the lung pretreatment image and the lung tumor initial segmentation image according to a preset pixel interval to obtain a corresponding lung sampling image and an initial segmentation sampling image;
the image block obtaining unit is used for cutting the initial segmentation sampling image according to the size of the preset image block by taking the mass center of the initial segmentation sampling image as the center to obtain a preset number of initial segmentation image blocks; and
the second image segmentation unit is used for obtaining a lung tumor segmentation image corresponding to the lung CT image by adopting a pre-trained second segmentation network according to the lung sampling image and the initial segmentation image block;
wherein, CT image preprocessing unit includes:
a first region extraction unit, configured to extract an air communication region in the lung CT image according to a preset seed point;
the second region extraction unit is used for removing the extracted air communication region from the lung CT image to obtain a corresponding body mask region image;
the image threshold segmentation unit is used for carrying out threshold segmentation on the body mask region image to obtain a left lung maximum communication region and a right lung maximum communication region;
the third region extraction unit is used for extracting the region of interest from the lung CT image according to the maximum left lung communication region and the maximum right lung communication region to obtain a corresponding lung region of interest image; and
and the normalization processing unit is used for carrying out gray level transformation on the lung region-of-interest image according to a preset gray level transformation formula, and carrying out normalization processing on the lung region-of-interest image after gray level transformation to obtain the lung preprocessing image corresponding to the lung CT image.
6. The apparatus of claim 5, wherein the apparatus further comprises:
the first sample sampling unit is used for resampling the training sample obtained by pretreatment according to the preset sample sampling size to obtain a first sampled training sample;
the first network training unit is used for training a preset segmentation network through the first sampling training sample according to the preset training iteration times to obtain the first segmentation network;
the second sample sampling unit is used for resampling the training sample according to the pixel spacing to obtain a second sampled training sample;
the second sample cutting unit is used for cutting the second sampling training samples according to the size of the image blocks by taking a preset positioning point as a center to obtain a preset number of training sample image blocks, wherein the positioning point is one pixel point of a tumor area in the second sampling training samples; and
and the second network training unit is used for training the segmentation network through the training sample image block according to the training iteration times to obtain the second segmentation network.
7. A computing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811493978.0A CN111292289B (en) | 2018-12-07 | 2018-12-07 | CT lung tumor segmentation method, device, equipment and medium based on segmentation network |
| PCT/CN2019/122103 WO2020114332A1 (en) | 2018-12-07 | 2019-11-29 | Segmentation-network-based ct lung tumor segmentation method, apparatus and device, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811493978.0A CN111292289B (en) | 2018-12-07 | 2018-12-07 | CT lung tumor segmentation method, device, equipment and medium based on segmentation network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111292289A CN111292289A (en) | 2020-06-16 |
| CN111292289B true CN111292289B (en) | 2023-09-26 |
Family
ID=70975202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811493978.0A Active CN111292289B (en) | 2018-12-07 | 2018-12-07 | CT lung tumor segmentation method, device, equipment and medium based on segmentation network |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111292289B (en) |
| WO (1) | WO2020114332A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112614143A (en) * | 2020-12-30 | 2021-04-06 | 深圳市联影高端医疗装备创新研究院 | Image segmentation method and device, electronic equipment and storage medium |
| CN112767411B (en) * | 2020-12-31 | 2024-08-06 | 罗雄彪 | Synchronous segmentation method for multiple organs of lung |
| CN117934480B (en) * | 2024-03-25 | 2024-05-28 | 天津市第五中心医院 | Lung CT image processing method and system for lung injury prediction |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392910A (en) * | 2017-07-06 | 2017-11-24 | 沈阳东软医疗系统有限公司 | A kind of lobe of the lung dividing method and device based on CT images |
| CN108492297A (en) * | 2017-12-25 | 2018-09-04 | 重庆理工大学 | The MRI brain tumors positioning for cascading convolutional network based on depth and dividing method in tumor |
| CN108615237A (en) * | 2018-05-08 | 2018-10-02 | 上海商汤智能科技有限公司 | A kind of method for processing lung images and image processing equipment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080267499A1 (en) * | 2007-04-30 | 2008-10-30 | General Electric Company | Method and system for automatic detection of objects in an image |
| US8929636B2 (en) * | 2012-02-02 | 2015-01-06 | Peter Yim | Method and system for image segmentation |
| CN103942785A (en) * | 2014-04-09 | 2014-07-23 | 苏州大学 | Lung tumor segmentation method based on PET and CT images of image segmentation |
| GB201705876D0 (en) * | 2017-04-11 | 2017-05-24 | Kheiron Medical Tech Ltd | Recist |
| CN108537784B (en) * | 2018-03-30 | 2021-08-24 | 四川元匠科技有限公司 | CT image pulmonary nodule detection method based on deep learning |
-
2018
- 2018-12-07 CN CN201811493978.0A patent/CN111292289B/en active Active
-
2019
- 2019-11-29 WO PCT/CN2019/122103 patent/WO2020114332A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392910A (en) * | 2017-07-06 | 2017-11-24 | 沈阳东软医疗系统有限公司 | A kind of lobe of the lung dividing method and device based on CT images |
| CN108492297A (en) * | 2017-12-25 | 2018-09-04 | 重庆理工大学 | The MRI brain tumors positioning for cascading convolutional network based on depth and dividing method in tumor |
| CN108615237A (en) * | 2018-05-08 | 2018-10-02 | 上海商汤智能科技有限公司 | A kind of method for processing lung images and image processing equipment |
Non-Patent Citations (3)
| Title |
|---|
| Huang X et al.Lung nodule detection in CT using3D convolutional neural networks.《Proceedings of IEEE14th International Symposium on Biomedical Imaging.Los Alamitos:IEEE Computer Society Press》.2017,第379-383页. * |
| 张鹏 等.基于深度学习的计算机辅助肺癌诊断方法.《计算机辅助设计与图形学学报》.2018,(第01期),第92-101页. * |
| 胡光亮等.基于卷积神经网络的鼻咽肿瘤MR图像分割.《计算机应用》.2018,第213-217页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111292289A (en) | 2020-06-16 |
| WO2020114332A1 (en) | 2020-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3770850B1 (en) | Medical image identifying method, model training method, and computer device | |
| WO2021115312A1 (en) | Method for automatically sketching contour line of normal organ in medical image | |
| WO2021238438A1 (en) | Tumor image processing method and apparatus, electronic device, and storage medium | |
| CN111292289B (en) | CT lung tumor segmentation method, device, equipment and medium based on segmentation network | |
| CN109389584A (en) | Multiple dimensioned rhinopharyngeal neoplasm dividing method based on CNN | |
| CN110097557B (en) | Medical image automatic segmentation method and system based on 3D-UNet | |
| CN108062749B (en) | Identification method and device for levator ani fissure hole and electronic equipment | |
| CN110189324B (en) | Medical image processing method and processing device | |
| CN110706236B (en) | Three-dimensional reconstruction method and device of blood vessel image | |
| CN112950552B (en) | Rib segmentation marking method and system based on convolutional neural network | |
| CN114092450A (en) | Real-time image segmentation method, system and device based on gastroscopy video | |
| CN110766659A (en) | Medical image recognition method, apparatus, device and medium | |
| CN111260669A (en) | Lung lobe segmentation method and device based on CT image | |
| CN112561917A (en) | Image segmentation method and system, electronic device and readable storage medium | |
| CN115115657A (en) | Focus segmentation method and device, electronic device and storage medium | |
| CN113706541B (en) | Image processing method and device | |
| CN116309551B (en) | Method, device, electronic equipment and readable medium for determining focus sampling area | |
| CN117427286A (en) | Tumor radiotherapy target area identification method, system and equipment based on energy spectrum CT | |
| CN110858412B (en) | Heart coronary artery CTA model building method based on image registration | |
| CN115147360B (en) | Plaque segmentation method and device, electronic equipment and readable storage medium | |
| CN113658198B (en) | Interactive emphysema focus segmentation method, device, storage medium and equipment | |
| CN111127636B (en) | Intelligent complex intra-articular fracture desktop-level three-dimensional diagnosis system | |
| CN118230889B (en) | Medical image report automatic generation method and system based on deep learning | |
| CN116344001B (en) | Medical information visual management system and method based on artificial intelligence | |
| CN110197712B (en) | Medical image storage system and storage method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |