CN117115134A - Method and device for determining proportion of solid components in lung nodule - Google Patents
Method and device for determining proportion of solid components in lung nodule Download PDFInfo
- Publication number
- CN117115134A CN117115134A CN202311188133.1A CN202311188133A CN117115134A CN 117115134 A CN117115134 A CN 117115134A CN 202311188133 A CN202311188133 A CN 202311188133A CN 117115134 A CN117115134 A CN 117115134A
- Authority
- CN
- China
- Prior art keywords
- lung
- image
- lung nodule
- nodule
- volume
- 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.)
- Pending
Links
- 206010056342 Pulmonary mass Diseases 0.000 title claims abstract description 231
- 239000007787 solid Substances 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 46
- 210000004072 lung Anatomy 0.000 claims abstract description 140
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 47
- 230000011218 segmentation Effects 0.000 claims description 30
- 230000000877 morphologic effect Effects 0.000 claims description 15
- 238000002372 labelling Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 9
- 238000002591 computed tomography Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 4
- 230000010339 dilation Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 10
- 239000004480 active ingredient Substances 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 210000004204 blood vessel Anatomy 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 210000000621 bronchi Anatomy 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000007596 consolidation process Methods 0.000 description 2
- 239000000470 constituent Substances 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000000149 penetrating effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 201000005202 lung cancer Diseases 0.000 description 1
- 208000020816 lung neoplasm Diseases 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000013517 stratification Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/005—Specific pre-processing for tomographic reconstruction, e.g. calibration, source positioning, rebinning, scatter correction, retrospective gating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- 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
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/30061—Lung
- G06T2207/30064—Lung nodule
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (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)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The present disclosure provides a method and apparatus for determining the proportion of an active ingredient in a lung nodule, the method comprising: acquiring an original CT image; preprocessing an original CT image to obtain a lung region image; segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image; constructing a lung three-dimensional image corresponding to the lung region image based on the tissue region image and the lung nodule region image; obtaining a three-dimensional image of a lung nodule and a three-dimensional image of a solid component in the lung nodule based on the three-dimensional image of the lung; determining a first volume of the lung nodule from the three-dimensional image of the lung nodule and a second volume of the solid component from the three-dimensional image of the solid component; from the first volume and the second volume, the real-world component occupancy rate in the lung nodule is determined. By the method, on the basis of obtaining the three-dimensional image of the lung, the volume of the lung nodule and the volume of the solid component in the lung nodule are determined, and CTR is determined on the basis of the volumes, so that CTR measurement and calculation are more accurate.
Description
Technical Field
The present disclosure relates to the biomedical field, and more particularly, to a method and apparatus for determining the ratio of solid components in lung nodules.
Background
With the improvement of computer tomography (computed tomography, CT) technology and the popularization of screening of high risk groups of lung cancer, more and more lung nodules are found, the size, the proportion and the growth of the solid components in the lung nodules are important for risk stratification and the formulation of subsequent treatment schemes, and the higher the solid component proportion (consolidation tumor ratio, CTR) in the lung nodules is, the higher the focus invasion degree is, and the worse the prognosis is.
CTR is the ratio of the maximum diameter of the solid component in the lung nodule to the maximum diameter of the lung nodule, and currently, CTR is determined by adopting a manual method, namely, by visual observation and measurement of two-dimensional images, but the consistency of discrimination criteria of different readers and the same reader at different times is larger, so that unavoidable errors exist in the determined CTR. In addition, the two-dimensional image can only measure the two-dimensional cross section of the real component in the lung nodule, and some lung nodules mainly show irregular characteristics such as branches, burrs and the like, so that the maximum diameter in the two-dimensional cross section is often not the actual maximum diameter of the lung nodule, and the calculated real component proportion is inconsistent with the actual real component proportion, namely, the manual CTR measurement is low in usability and high in heterogeneity.
Disclosure of Invention
The present disclosure provides a method, apparatus, electronic device, and storage medium for determining the fraction of solid constituents in lung nodules to address at least the above technical problems in the prior art.
According to a first aspect of the present disclosure there is provided a method of determining the proportion of a real component in a lung nodule, the method comprising: acquiring an original computed tomography CT image; preprocessing the original CT image to obtain a lung region image; segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image; constructing a lung three-dimensional image corresponding to the lung region image based on the region image of the tissue and the lung nodule region image; based on the lung three-dimensional image, obtaining a lung nodule three-dimensional image and a three-dimensional image of a solid component in the lung nodule; determining a first volume of the lung nodule from the three-dimensional image of the lung nodule, and determining a second volume of the solid component from the three-dimensional image of the solid component; a real component duty cycle in the lung nodule is determined from the first volume and the second volume.
In an embodiment, the preprocessing the original CT image to obtain a lung region image includes: normalizing the original CT image according to preset window width and window level parameters; identifying the CT image after normalization processing through an image identification model to obtain a lung parenchyma region image; and carrying out morphological image processing on the lung parenchyma region image to obtain a lung region image.
In one embodiment, the segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image includes: dividing the lung region image through a tissue division model to obtain an initial region image of a target, wherein the target is the tissues or the lung nodules; determining a maximum connected domain of the target according to the initial region image of the target; and obtaining the region image of the target through morphological image processing based on the maximum connected domain.
In an embodiment, the segmenting the lung region image by the tissue segmentation model to obtain the initial region image of the lung nodule includes: acquiring an interested area image of a lung nodule according to the lung area image; and segmenting the region-of-interest image through a tissue segmentation model to obtain an initial region image of the lung nodule.
In one embodiment, the obtaining a three-dimensional image of the solid component in the lung nodule based on the three-dimensional image of the lung includes: performing dilation morphological processing on the regional image of the lung nodule; performing histogram calculation on the regional image of the inflated lung nodule to obtain a CT threshold corresponding to the real component; and setting the CT value of the lung three-dimensional image as the CT threshold value to obtain the three-dimensional image of the real component.
In an embodiment, the determining the first volume of the lung nodule from the three-dimensional image of the lung nodule and the second volume of the solid component from the three-dimensional image of the solid component comprises: determining the number of pixels corresponding to the lung nodule according to the lung nodule three-dimensional image, and determining a first volume of the lung nodule according to the number of pixels and the size of a single pixel; and determining the number of pixels corresponding to the real component according to the three-dimensional image of the real component, and determining the second volume of the real component according to the number of pixels and the size of a single pixel.
In an embodiment, the method further comprises: the three-dimensional image of the lung contains labeling information of each tissue and the lung nodule; determining a third volume which is misidentified as a real component in the lung nodule according to the labeling information; correcting the real component duty cycle in the lung nodule according to the third volume.
According to a second aspect of the present disclosure there is provided an apparatus for determining the proportion of an active ingredient in a lung nodule, the apparatus comprising: the acquisition module is used for acquiring an original CT image; the processing module is used for preprocessing the original CT image to obtain a lung region image; the segmentation module is also used for segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image; a construction module for constructing a three-dimensional image of the lung corresponding to the lung region image based on the region image of the tissue and the lung nodule region image; the obtaining module is used for obtaining a three-dimensional image of a lung nodule and a three-dimensional image of a solid component in the lung nodule based on the three-dimensional image of the lung; a determination module for determining a first volume of the lung nodule from the three-dimensional image of the lung nodule and a second volume of the solid component from the three-dimensional image of the solid component; the determination module is further configured to determine a real-world component duty cycle in the lung nodule based on the first volume and the second volume.
In one embodiment, the processing module includes: the first processing sub-module is used for carrying out normalization processing on the original CT image according to preset window width and window level parameters; the identification sub-module is used for identifying the CT image after normalization processing through an image identification model to obtain a lung parenchyma region image; and the second processing submodule is used for carrying out morphological image processing on the lung parenchyma region image to obtain a lung region image.
In an embodiment, the segmentation module includes: the segmentation submodule is used for segmenting the lung region image through a tissue segmentation model to obtain an initial region image of a target, wherein the target is the tissues or the lung nodules; the determining submodule is used for determining the maximum connected domain of the target according to the initial area image of the target; and the third processing submodule is used for obtaining the regional image of the target through morphological image processing based on the maximum connected domain.
In an embodiment, the segmentation submodule is specifically configured to obtain an image of a region of interest in which a lung nodule is located according to the image of the lung region; and segmenting the region-of-interest image through a tissue segmentation model to obtain an initial region image of the lung nodule.
In an embodiment, the obtaining module includes: a fourth processing sub-module for performing an dilated morphological process on the regional image of the lung nodule; the obtaining submodule is used for carrying out histogram calculation on the regional image of the inflated lung nodule to obtain a CT threshold value corresponding to the real component; the obtaining submodule is further used for setting the CT value of the three-dimensional lung image as the CT threshold value to obtain the three-dimensional image of the real component.
In an embodiment, the determining module is further configured to determine a number of pixels corresponding to the lung nodule according to the three-dimensional image of the lung nodule, and determine a first volume of the lung nodule according to the number of pixels and a size of a single pixel; and determining the number of pixels corresponding to the real component according to the three-dimensional image of the real component, and determining the second volume of the real component according to the number of pixels and the size of a single pixel.
In an embodiment, the three-dimensional image of the lung includes labeling information of the respective tissue and the lung nodule, and the apparatus further includes: the correction module is used for determining a third volume which is misidentified as the real component in the lung nodule according to the labeling information; correcting the real component duty cycle in the lung nodule according to the third volume.
According to a third aspect of the present disclosure, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the methods described in the present disclosure.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of the present disclosure.
The method, the device, the electronic equipment and the storage medium for determining the proportion of the solid component in the lung nodule acquire an original CT image; preprocessing an original CT image to obtain a lung region image; segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image; constructing a lung three-dimensional image corresponding to the lung region image based on the tissue region image and the lung nodule region image; obtaining a three-dimensional image of a lung nodule and a three-dimensional image of a solid component in the lung nodule based on the three-dimensional image of the lung; determining a first volume of the lung nodule from the three-dimensional image of the lung nodule and a second volume of the solid component from the three-dimensional image of the solid component; from the first volume and the second volume, the real-world component occupancy rate in the lung nodule is determined. By using the method, the corresponding lung three-dimensional image is constructed based on the lung region image, the volume of the lung nodule and the volume of the solid component in the lung nodule are determined on the basis of the lung three-dimensional image, and the solid component proportion in the lung nodule is determined according to the volume, so that the problems of low usability and high heterogeneity of manual CTR measurement are solved, and CTR measurement is more accurate.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
FIG. 1 illustrates a schematic flow diagram of an implementation of a method of determining the real-world component occupancy in a lung nodule in accordance with an embodiment of the present disclosure;
FIG. 2 illustrates a schematic diagram of an implementation flow of preprocessing an original CT image in accordance with an embodiment of the present disclosure;
FIG. 3 illustrates a schematic implementation flow diagram of obtaining an area image of various tissues of the lung and an area image of a lung nodule in an embodiment of the present disclosure;
FIG. 4 illustrates a schematic implementation flow diagram of obtaining an initial region image of a lung nodule in accordance with an embodiment of the present disclosure;
FIG. 5 illustrates a schematic diagram of an implementation flow of obtaining a three-dimensional image of a solid component in a lung nodule in an embodiment of the present disclosure;
FIG. 6 illustrates a block diagram of an apparatus for determining the real-world component occupancy in a lung nodule according to an embodiment of the present disclosure;
fig. 7 shows a schematic diagram of a composition structure of an electronic device according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, features and advantages of the present disclosure more comprehensible, the technical solutions in the embodiments of the present disclosure will be clearly described in conjunction with the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, but not all embodiments. Based on the embodiments in this disclosure, all other embodiments that a person skilled in the art would obtain without making any inventive effort are within the scope of protection of this disclosure.
Fig. 1 shows a schematic implementation flow diagram of a method for determining a proportion of an active component in a lung nodule according to an embodiment of the present disclosure, including:
step 101, an original computed tomography CT image is acquired.
First, a computed tomography image (Computed Tomography, CT) is an examination of image diagnostics, and a certain thickness layer of a human body is scanned by an X-ray beam.
Step 102, preprocessing the original CT image to obtain a lung region image.
After the original CT image of the lung is obtained, preprocessing is carried out on the original CT image, so that the original CT image data accords with the processing requirement of a follow-up model, the follow-up processing is more convenient, the original CT image is segmented, and the image irrelevant to the lung in the original CT image is removed, so that the image only comprising the lung region is obtained.
And 103, segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image.
The lung comprises blood vessels, bronchi, lung lobes, lung nodules and the like, each tissue and the lung nodules have respective characteristics, the obtained lung region images are segmented according to the corresponding characteristics, region images corresponding to each tissue are respectively obtained, and for example, region images corresponding to the vestibule can be obtained after the tissue region images are segmented according to the characteristics of the blood vessels.
Step 104, constructing a three-dimensional lung image corresponding to the lung region image based on the tissue region image and the lung nodule region image.
Based on the regional images of each tissue and the lung nodule regional images, pixel-level mask results of each tissue and the lung nodule can be obtained, and the MarchingCube algorithm is adopted to convert the pixel-level mask results of each tissue and the lung nodule on the two-dimensional CT image into a three-dimensional model, so that the construction of a lung three-dimensional image is completed, and a lung three-dimensional image corresponding to the lung regional image is obtained.
Step 105, obtaining a three-dimensional image of the lung nodule and a three-dimensional image of a solid component in the lung nodule based on the three-dimensional image of the lung.
Based on the three-dimensional image of the lung, a three-dimensional image of the lung nodule can be obtained, and the density of the solid component in the lung nodule is different from that of the lung nodule, so that the three-dimensional image of the solid component in the lung nodule can be determined from the three-dimensional image of the lung according to the absorption rate of the solid component in the lung nodule to X-ray.
Step 106, determining a first volume of the lung nodule from the three-dimensional image of the lung nodule and determining a second volume of the solid component from the three-dimensional image of the solid component.
A first volume of the lung nodule may be determined from pixels of the lung nodule based on the lung nodule three-dimensional image, and a second volume of the solid component in the lung nodule may be determined from pixels of the solid component in the lung nodule.
Step 107, determining the real-world component ratio in the lung nodule based on the first volume and the second volume.
The ratio of the solid component in the lung nodule is determined based on the ratio of the second volume of the solid component to the first volume of the lung nodule. The existing method for determining the proportion of the solid components in the lung nodule according to the ratio of the diameter of the solid components to the diameter of the lung nodule is converted into the method for determining the proportion of the solid components in the lung nodule according to the ratio of the volume of the solid components to the volume of the lung nodule, so that the obtained proportion of the solid components in the lung nodule is more accurate.
According to the method for determining the proportion of the solid component in the lung nodule, the lung region image is obtained based on the original CT image, the region image of each tissue and the lung nodule region image are obtained by dividing the lung region image, the lung three-dimensional image corresponding to the lung region image is constructed according to the region image of each tissue and the lung nodule region image, the volume of the solid component in the lung nodule and the volume of the solid component in the lung nodule are determined based on the lung three-dimensional image, and therefore the proportion of the solid component in the lung nodule is determined. By the method, on the basis of constructing a three-dimensional image of the lung, the proportion of the solid components in the lung nodule is determined according to the volume of the solid components in the lung nodule, and the problems of low usability and high heterogeneity of manual CTR measurement are solved, so that CTR measurement is more accurate.
In one embodiment, as shown in fig. 2, preprocessing the original CT image to obtain a lung region image includes:
step 201, carrying out normalization processing on an original CT image according to preset window width and window level parameters;
step 202, recognizing the normalized CT image through an image recognition model to obtain a lung parenchyma region image;
step 203, morphological image processing is performed on the lung parenchyma region image to obtain a lung region image.
After the original CT image is obtained, normalization processing is carried out on the original CT image according to preset window width and window level parameters, original CT image data are mapped to a normalized value range, and in the implementation scene of the scheme, the value range is usually selected to be 0-255 gray scale visible to human eyes, so that errors caused by shooting CT images by different manufacturers and different shooting parameters can be avoided, and the difficulty of subsequent model identification is reduced. In this scheme, the window width is set to 1200HU, and the window level is set to 300HU.
After normalization processing is carried out on the original CT image, the normalized image is identified through an image identification model, and a lung parenchyma region image is obtained. The image recognition model is specifically used for acquiring a lung parenchyma image area according to the texture characteristics of the lung parenchyma and a preset CT threshold value, wherein the CT value is a measurement unit for measuring the density of a certain local tissue or organ of a human body, the preset CT threshold value is set to be-500, and the lung parenchyma area image is acquired according to the preset CT threshold value.
In addition, the image recognition model adopted in the application needs to be trained through sample data, the sample data is an original CT image marked with a lung region image, but the sample data has the problems of quantity burning and high acquisition cost, so the sample data can be processed after being obtained so as to improve the sample data quantity. In the scheme, the processing mode of the sample data comprises data enhancement and sampling generation, wherein the data enhancement comprises noise disturbance, distortion, image scaling and the like of the sample data, such as Gaussian noise, spiced salt noise and the like are added on the basis of the sample data, or the sample data is subjected to overturn, rotation, affine transformation, image magnification, image reduction and the like. Sampling generation includes random cropping and image generation, and random cropping of sample data or model training sample data generation by adopting a mode of generating a model. Therefore, more training sample data can be obtained, more various sample data can be obtained in the model training stage, the acquisition cost of the model sample data in the training stage is reduced, and the recognition accuracy and generalization capability of the model are improved.
After the lung parenchyma region image is obtained, the lung parenchyma region image is processed by a morphological closing operation image processing method, and a lung region image is obtained.
In one embodiment, as shown in fig. 3, segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image, includes:
step 301, segmenting a lung region image through a tissue segmentation model to obtain an initial region image of a target, wherein the target is each tissue or lung nodule;
step 302, determining the maximum connected domain of the target according to the initial region image of the target;
step 303, obtaining a region image of the target through morphological image processing based on the maximum connected domain.
The lung comprises blood vessels, bronchi, lung nodules, lung lobes and other tissues, and a tissue segmentation model is adopted to segment the lung region image according to the characteristics of each tissue of the lung. The tissue segmentation model is 3D V-Net, and in the scheme, the middle convolution module of the tissue segmentation model is replaced by a Project & exact attention feature extraction module, so that the tissue segmentation model is favorable for learning. The tissue segmentation model adopts a supervised training mode during training, a supervision label is a single-channel binary image, 0 represents a background, and 1 represents a tissue to be identified. And segmenting the lung region image through a tissue segmentation model to obtain an initial region image of each tissue and an initial region image of a lung nodule.
After obtaining the initial area image of each tissue and lung nodule, post-processing the initial area image is needed, specifically, noise removal processing is carried out on the area image of each tissue and the lung nodule area image, the wrong recognition result is removed, and the maximum connected area of the initial area image of each tissue and the initial area image of the lung nodule is reserved.
However, the lung region image is segmented by the tissue segmentation model, and the initial region image of each tissue and the initial region image of the lung nodule are obtained, so that the condition of incomplete morphology is caused due to the occurrence of arteriovenous holes caused by pixel deletion in the pixel level. Therefore, on the basis of determining the maximum connected region of the initial region image of the tissue or the lung nodule, the hole is supplemented by morphological image processing operations such as a closing operation and an opening operation, and the unnecessary burr is eliminated, so that a region image of a pixel-level target, which is the tissue or the lung nodule, is obtained.
In one embodiment, as shown in fig. 4, segmenting the lung region image by the tissue segmentation model, an initial region image of the lung nodule is obtained, comprising:
step 401, acquiring an interested area image of a lung nodule according to the lung area image;
step 402, segmenting the region of interest image through a tissue segmentation model to obtain an initial region image of the lung nodule.
And detecting the lung region image by adopting a target detection network to obtain an interested region image comprising the lung nodule, and then segmenting the interested region image by using a tissue segmentation model to obtain an initial region image of the lung nodule. The object detection network employed in the present application to acquire the Region of interest image including the lung nodule is a Fast Region convolutional neural network (Fast Region-based Convolutional Network, fast RCNN) or a Mask Region convolutional neural network (Mask Region-based Convolutional Network, mask-RCNN). And then segmenting the region of interest image by a tissue segmentation model for segmenting other tissues of the lung to obtain an initial region image of the lung nodule.
In one embodiment, as shown in fig. 5, obtaining a three-dimensional image of solid components in a lung nodule based on a three-dimensional image of a lung, comprises:
step 501, performing expansion morphology processing on a regional image of a lung nodule;
step 502, carrying out histogram calculation on the regional image of the inflated lung nodule to obtain a CT threshold value corresponding to the real component;
in step 503, the CT value of the three-dimensional image of the lung is set as the CT threshold, and a three-dimensional image of the real component is obtained.
The regional image of the lung nodule is processed in an expansive morphology by using a three-dimensional spherical operator until a mask of a blood vessel or bronchial wall of not less than a preset size is visible within the lung nodule, in this case, the preset size may be set to 1 cm. And (3) carrying out histogram measurement on blood vessels, bronchus walls and the like in the region after the lung nodule is expanded, determining the lowest CT threshold value which is indistinguishable by covering the blood vessels, bronchus and the like, only displaying the real components of the lung according to the CT threshold value, and setting the CT value of the three-dimensional image of the lung as the CT threshold value to obtain the three-dimensional image of the real components.
In one embodiment, determining a first volume of a lung nodule from a three-dimensional image of the lung nodule and determining a second volume of a solid component from a three-dimensional image of the solid component comprises:
determining the number of pixels corresponding to the lung nodule according to the lung nodule three-dimensional image, and determining a first volume of the lung nodule according to the number of pixels and the size of a single pixel;
the number of pixels corresponding to the real component is determined from the three-dimensional image of the real component, and the second volume of the real component is determined from the number of pixels and the size of the individual pixels.
In this scheme, the position of the lung nodule and the number of pixels occupied by the lung nodule are determined according to the three-dimensional image of the lung nodule, and in the three-dimensional image of the lung nodule, each pixel has a fixed space size, for example, the space of a single pixel is 1mm×1mm, so after the number of pixels corresponding to the lung nodule is determined, the first volume of the lung nodule can be determined by accumulating the space occupied by the single pixel according to the number of pixels. Similarly, the position of the solid component in the lung nodule and the number of occupied pixels can be determined according to the three-dimensional image of the solid component in the lung nodule, and the second volume of the solid component in the lung nodule can be determined by accumulating the space occupied by the single pixels according to the number of pixels.
In an embodiment, the method further comprises: the three-dimensional image of the lung contains labeling information of each tissue and lung nodule; determining a third volume that is misrecognized as a solid component in the lung nodule based on the labeling information; the ratio of the solid components in the lung nodules is corrected according to the third volume.
Since there is a physiological form of penetration of blood vessels, when the lung nodule region is directly segmented by CT threshold values corresponding to the real components, interference of the real components penetrating the blood vessels and bronchi in the lung nodule cannot be eliminated, that is, the real components segmented by the CT threshold values may include the real components in the blood vessels and bronchi, and interference occurs in calculation of the ratio of the real components in the lung nodule, so that it is necessary to correct the volume of the real components in the lung nodule.
After the lung three-dimensional image is constructed, labeling each tissue and lung nodule contained in the lung three-dimensional image, and determining the pixel and the space position occupied by each tissue or lung nodule as labeling information of each tissue and lung nodule. After the three-dimensional image of the real component is obtained by segmentation according to the CT threshold corresponding to the real component, the volume of the real component such as a blood vessel, a bronchus and the like penetrating through the lung nodule is determined according to the labeling information, the part is a third volume which is mistakenly identified as the real component in the lung nodule, and the volume of the real component in the lung nodule is corrected according to the third volume, so that the actual volume of the real component in the lung nodule is obtained.
Further, the actual component duty ratio in the lung nodule is corrected by the following formula:
wherein V is mCinsilidation V to volume of solid component in corrected lung nodule Nodule Is the first volume of the lung nodule, V Consolidation For a second volume of solid components in lung nodules segmented according to CT threshold, V modified A third volume that is misrecognized as a solid component in the lung nodule.
Fig. 6 shows a block diagram of an apparatus for determining the real-world component duty cycle in a lung nodule according to an embodiment of the present disclosure.
Referring to fig. 6, in accordance with a second aspect of an embodiment of the present disclosure, there is provided an apparatus for determining the proportion of solid constituents in a lung nodule, the apparatus comprising: an acquisition module 601, configured to acquire an original computed tomography CT image; the processing module 602 is configured to pre-process the original CT image to obtain a lung region image; the segmentation module 603 is further configured to segment the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image; a construction module 604 for constructing a three-dimensional image of the lung corresponding to the lung region image based on the region image of the tissue and the lung nodule region image; an obtaining module 605, configured to obtain a three-dimensional image of a lung nodule and a three-dimensional image of a solid component in the lung nodule based on the three-dimensional image of the lung; a determination module 606 for determining a first volume of the lung nodule from the three-dimensional image of the lung nodule and a second volume of the solid component from the three-dimensional image of the solid component; the determining module 606 is further configured to determine a real-world component duty cycle in the lung nodule based on the first volume and the second volume.
In one embodiment, the processing module 602 includes: the first processing sub-module 6021 is configured to perform normalization processing on the original CT image according to a preset window width and window level parameter; the recognition submodule 6022 is used for recognizing the CT image after normalization processing through an image recognition model to obtain a lung parenchyma region image; the second processing submodule 6023 is configured to perform morphological image processing on the lung parenchyma region image to obtain a lung region image.
In one embodiment, the segmentation module 603 includes: the segmentation submodule 6031 is used for segmenting the lung region image through the tissue segmentation model to obtain an initial region image of a target, wherein the target is a tissue or a lung nodule; a determining submodule 6032 for determining a maximum connected domain of the target according to the initial region image of the target; the third processing sub-module 6033 is configured to obtain a region image of the target through morphological image processing based on the maximum connected domain.
In one embodiment, the segmentation submodule 6031 is specifically configured to acquire an image of a region of interest in which a lung nodule is located according to an image of a lung region; and segmenting the region-of-interest image through the tissue segmentation model to obtain an initial region image of the lung nodule.
In one embodiment, the obtaining module 605 includes: a fourth processing submodule 6051 for performing an inflation morphology processing on the region image of the lung nodule; an obtaining submodule 6052, configured to perform histogram measurement on the region image of the inflated lung nodule, and obtain a CT threshold corresponding to the real component; the obtaining submodule 6052 is further used for setting a CT value of the three-dimensional image of the lung to be a CT threshold value, and obtaining a three-dimensional image of the real component.
In an embodiment, the determining module 606 is further configured to determine a number of pixels corresponding to the lung nodule based on the three-dimensional image of the lung nodule, and determine a first volume of the lung nodule based on the number of pixels and a size of the single pixel; the number of pixels corresponding to the real component is determined from the three-dimensional image of the real component, and the second volume of the real component is determined from the number of pixels and the size of the individual pixels.
In one embodiment, the three-dimensional image of the lung includes labeling information of each tissue and lung nodule, and the apparatus further comprises: a correction module 607 for determining a third volume that is misrecognized as an actual component of the lung nodule based on the labeling information; the ratio of the solid components in the lung nodules is corrected according to the third volume.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.
Fig. 7 illustrates a schematic block diagram of an example electronic device 700 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the apparatus 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 may also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Various components in device 700 are connected to I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, etc.; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, an optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as one method of determining the actual component duty cycle in a lung nodule. For example, in some embodiments, a method of determining the actual component duty cycle in a lung nodule may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 700 via ROM 702 and/or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of one method of determining the proportion of real components in lung nodules described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform a method of determining the real-world component duty cycle in a lung nodule by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The foregoing is merely specific embodiments of the disclosure, but the protection scope of the disclosure is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the disclosure, and it is intended to cover the scope of the disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (10)
1. A method of determining the proportion of a solid component in a lung nodule, the method comprising:
acquiring an original computed tomography CT image;
preprocessing the original CT image to obtain a lung region image;
segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image;
constructing a lung three-dimensional image corresponding to the lung region image based on the region image of the tissue and the lung nodule region image;
based on the lung three-dimensional image, obtaining a lung nodule three-dimensional image and a three-dimensional image of a solid component in the lung nodule;
determining a first volume of the lung nodule from the three-dimensional image of the lung nodule, and determining a second volume of the solid component from the three-dimensional image of the solid component;
a real component duty cycle in the lung nodule is determined from the first volume and the second volume.
2. The method of claim 1, wherein the preprocessing of the original CT image to obtain a lung region image comprises:
normalizing the original CT image according to preset window width and window level parameters;
identifying the CT image after normalization processing through an image identification model to obtain a lung parenchyma region image;
and carrying out morphological image processing on the lung parenchyma region image to obtain a lung region image.
3. The method of claim 1, wherein segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image comprises:
dividing the lung region image through a tissue division model to obtain an initial region image of a target, wherein the target is the tissues or the lung nodules;
determining a maximum connected domain of the target according to the initial region image of the target;
and obtaining the region image of the target through morphological image processing based on the maximum connected domain.
4. The method of claim 3, wherein segmenting the lung region image by a tissue segmentation model results in an initial region image of the lung nodule, comprising:
acquiring an interested area image of a lung nodule according to the lung area image;
and segmenting the region-of-interest image through a tissue segmentation model to obtain an initial region image of the lung nodule.
5. The method of claim 1, wherein the obtaining a three-dimensional image of solid components in a lung nodule based on the three-dimensional image of the lung comprises:
performing dilation morphological processing on the regional image of the lung nodule;
performing histogram calculation on the regional image of the inflated lung nodule to obtain a CT threshold corresponding to the real component;
and setting the CT value of the lung three-dimensional image as the CT threshold value to obtain the three-dimensional image of the real component.
6. The method of claim 1, wherein the determining the first volume of the lung nodule from the three-dimensional image of the lung nodule and the second volume of the solid component from the three-dimensional image of the solid component comprises:
determining the number of pixels corresponding to the lung nodule according to the lung nodule three-dimensional image, and determining a first volume of the lung nodule according to the number of pixels and the size of a single pixel;
and determining the number of pixels corresponding to the real component according to the three-dimensional image of the real component, and determining the second volume of the real component according to the number of pixels and the size of a single pixel.
7. The method of claim 5, wherein the method further comprises:
the three-dimensional image of the lung contains labeling information of each tissue and the lung nodule;
determining a third volume which is misidentified as a real component in the lung nodule according to the labeling information;
correcting the real component duty cycle in the lung nodule according to the third volume.
8. An apparatus for determining the proportion of a solid component in a lung nodule, the apparatus comprising:
the acquisition module is used for acquiring an original CT image;
the processing module is used for preprocessing the original CT image to obtain a lung region image;
the segmentation module is also used for segmenting the lung region image to obtain a region image of each tissue of the lung and a lung nodule region image;
a construction module for constructing a three-dimensional image of the lung corresponding to the lung region image based on the region image of the tissue and the lung nodule region image;
the obtaining module is used for obtaining a three-dimensional image of a lung nodule and a three-dimensional image of a solid component in the lung nodule based on the three-dimensional image of the lung;
a determination module for determining a first volume of the lung nodule from the three-dimensional image of the lung nodule and a second volume of the solid component from the three-dimensional image of the solid component;
the determination module is further configured to determine a real-world component duty cycle in the lung nodule based on the first volume and the second volume.
9. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
10. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311188133.1A CN117115134A (en) | 2023-09-14 | 2023-09-14 | Method and device for determining proportion of solid components in lung nodule |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311188133.1A CN117115134A (en) | 2023-09-14 | 2023-09-14 | Method and device for determining proportion of solid components in lung nodule |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117115134A true CN117115134A (en) | 2023-11-24 |
Family
ID=88794780
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311188133.1A Pending CN117115134A (en) | 2023-09-14 | 2023-09-14 | Method and device for determining proportion of solid components in lung nodule |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117115134A (en) |
-
2023
- 2023-09-14 CN CN202311188133.1A patent/CN117115134A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Saad et al. | Image segmentation for lung region in chest X-ray images using edge detection and morphology | |
CN114565763B (en) | Image segmentation method, device, apparatus, medium and program product | |
CN110176010B (en) | Image detection method, device, equipment and storage medium | |
CN116245832B (en) | Image processing method, device, equipment and storage medium | |
CN114693604A (en) | Spine medical image processing method, device, equipment and storage medium | |
CN117373070B (en) | Method and device for labeling blood vessel segments, electronic equipment and storage medium | |
CN115439453B (en) | Vertebra body positioning method and device, electronic equipment and storage medium | |
CN114820652B (en) | Method, device and medium for segmenting partial quality abnormal region of mammary gland X-ray image | |
CN114693671B (en) | Lung nodule semi-automatic segmentation method, device, equipment and medium based on deep learning | |
CN114332132A (en) | Image segmentation method and device and computer equipment | |
US8160336B2 (en) | Reducing false positives for automatic computerized detection of objects | |
CN112116623B (en) | Image segmentation method and device | |
CN115294401B (en) | CT image-based classification method, device, equipment and storage medium | |
CN115439423B (en) | CT image-based identification method, device, equipment and storage medium | |
CN115147360B (en) | Plaque segmentation method and device, electronic equipment and readable storage medium | |
CN114037775B (en) | Bone structure growth method and device, electronic equipment and storage medium | |
CN117115134A (en) | Method and device for determining proportion of solid components in lung nodule | |
CN111275719A (en) | Calcification false positive recognition method, device, terminal and medium and model training method and device | |
CN115578564B (en) | Training method and device for instance segmentation model, electronic equipment and storage medium | |
CN115690498B (en) | Vertebral bone density confirmation method, device, electronic equipment and storage medium | |
CN117809092B (en) | Medical image processing method and device, electronic equipment and storage medium | |
CN113822904B (en) | Image labeling device, method and readable storage medium | |
CN116029967B (en) | Pulmonary embolism image processing method, device, equipment and storage medium | |
CN115564788B (en) | Lung trachea segmentation model training and segmentation method and device based on prior information | |
CN117635578A (en) | Image processing method, device, electronic equipment and storage medium |
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 |