CN113658159A - Lung integral extraction method and system based on lung key points - Google Patents
Lung integral extraction method and system based on lung key points Download PDFInfo
- Publication number
- CN113658159A CN113658159A CN202110974430.3A CN202110974430A CN113658159A CN 113658159 A CN113658159 A CN 113658159A CN 202110974430 A CN202110974430 A CN 202110974430A CN 113658159 A CN113658159 A CN 113658159A
- Authority
- CN
- China
- Prior art keywords
- image
- lung
- edge
- template
- transformation matrix
- 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
- 210000004072 lung Anatomy 0.000 title claims abstract description 234
- 238000000605 extraction Methods 0.000 title claims abstract description 27
- 239000011159 matrix material Substances 0.000 claims abstract description 71
- 230000009466 transformation Effects 0.000 claims abstract description 62
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 17
- 230000002685 pulmonary effect Effects 0.000 claims description 32
- 230000001131 transforming effect Effects 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 6
- 206010056342 Pulmonary mass Diseases 0.000 abstract description 10
- 239000002609 medium Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000013507 mapping Methods 0.000 description 6
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 4
- 201000005202 lung cancer Diseases 0.000 description 4
- 208000020816 lung neoplasm Diseases 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000012120 mounting media Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012015 optical character recognition Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
Abstract
The invention relates to a lung integral extraction method and a system based on lung key points, wherein the method comprises the following steps: acquiring an image template corresponding to the category of the lung image; determining edge keypoint locations on the lung image; generating a transformation matrix based on the edge keypoint location on the lung image and the edge keypoint location on the image template; determining an image position corresponding to the lung image based on the image position on the image template and the transformation matrix; extracting the region at the image position corresponding to the lung image to obtain a target lung image; the invention improves the identification precision of the lung edge and reduces the misdiagnosis probability of lung nodule detection.
Description
Technical Field
The invention relates to the technical field of medical auxiliary diagnosis, in particular to a method and a system for integrally extracting a lung based on key points of the lung.
Background
The lung cancer becomes a malignant tumor with the highest morbidity and mortality worldwide, seriously threatens the life and health of human beings, early discovery is an effective method for improving the treatment effect of lung cancer patients, and meanwhile, the detection and identification of lung nodules are increasingly important in lung cancer treatment because the lung nodules are early forms of the lung cancer. When lung nodules are detected on a lung image, some lung nodules are attached to the edge of the lung, and when lung extraction is performed, due to the accuracy problem of an extraction algorithm, the lung nodules are often discarded as extrapulmonary tissues, so that missed diagnosis occurs in lung nodule detection.
Disclosure of Invention
The invention aims to provide a lung integral extraction method and system based on lung key points, and aims to solve the problem that misdiagnosis occurs in lung nodule detection due to low extraction precision of central lung images in the prior art.
The technical purpose of the invention is realized by the following technical scheme:
in a first aspect, the present application provides a method for pulmonary global extraction based on pulmonary keypoints, the method including the following steps:
acquiring an image template corresponding to the category of the lung image;
determining edge keypoint locations on the lung image;
generating a transformation matrix based on the edge keypoint location on the lung image and the edge keypoint location on the image template;
determining an image position corresponding to the lung image based on the image position on the image template and the transformation matrix;
and extracting the region at the image position corresponding to the lung image to obtain a target lung image.
In some of these embodiments, the determining edge keypoint locations on the lung image comprises:
acquiring a key point detection model corresponding to the category of the lung image;
and inputting the lung image into the key point detection model to obtain the position of an edge key point on the lung image.
In some of these embodiments, the keypoint detection model is trained by:
acquiring a lung image set with the same category as the lung image and the position of an edge key point on the lung image in the lung image set;
labeling the corresponding lung image based on the position of an edge key point on the lung image in the lung image set to generate a sample lung image set;
and training by using the sample lung image set to obtain the key point detection model.
In some embodiments, the generating a transformation matrix based on the edge keypoint locations on the lung image and the edge keypoint locations on the image template comprises:
generating a first transformation matrix from edge keypoint locations on the lung image to edge keypoint locations on the image template; and
the determining the image position corresponding to the lung image based on the image position on the image template and the transformation matrix comprises:
transforming the lung image based on the first transformation matrix to obtain a transformed lung image;
and taking the image position on the image template as the image position on the transformed lung image.
In some embodiments, the generating a transformation matrix based on the edge keypoint locations on the lung image and the edge keypoint locations on the image template comprises:
generating a second transformation matrix of edge keypoint locations on the image template to edge keypoint locations on the lung image; and
the determining the image position corresponding to the lung image based on the image position on the image template and the transformation matrix comprises:
and transforming the image position on the image template based on the second transformation matrix to obtain the image position on the lung image.
In some of these embodiments, the image template is generated by:
acquiring a standard lung image with the same category as the lung image, and an edge key point position and an image position on the standard lung image;
and labeling the standard lung image based on the position of the edge key point on the standard lung image and the position of the image to generate the image template.
In a second aspect, the present application provides a pulmonary keypoint-based pulmonary global extraction device, including:
the image acquisition module is used for acquiring an image template corresponding to the category of the lung image;
a keypoint determination module for determining the location of edge keypoints on the lung image;
a matrix generation module for generating a transformation matrix based on the edge key point position on the lung image and the edge key point position on the image template;
a position determining module, configured to determine an image position corresponding to the lung image based on the image position on the image template and the transformation matrix;
and the target image acquisition module is used for extracting the region at the image position corresponding to the lung image to obtain a target lung image.
In a third aspect, embodiments of the present application provide a computer device, including a memory and one or more processors;
the memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a pulmonary keypoint-based pulmonary ensemble draw method as described in the first aspect.
In a fourth aspect, embodiments of the present application provide a storage medium containing computer-executable instructions for performing the pulmonary keypoint-based pulmonary ensemble extraction method according to the first aspect when executed by a computer processor.
The invention has the beneficial effects that: the method comprises the steps of obtaining an image template corresponding to the category of a lung image; determining edge keypoint locations on the lung image; generating a transformation matrix based on the edge keypoint location on the lung image and the edge keypoint location on the image template; determining an image position corresponding to the lung image based on the image position on the image template and the transformation matrix; extracting the region at the image position corresponding to the lung image to obtain a target lung image; the recognition accuracy of the lung edges is improved, and the misdiagnosis probability of lung nodule detection is reduced.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic diagram of the steps of a method for extracting the whole lung based on key points of the lung;
FIG. 2 is a schematic diagram of a pulmonary integrated aspiration device based on pulmonary keypoints;
fig. 3 is a schematic diagram of a computer device for a lung integral extraction method based on lung key points.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
Referring to fig. 1, a lung integral extraction method based on lung key points according to the present invention is shown, the method includes the following steps:
100. acquiring an image template corresponding to the category of the lung image;
in this embodiment, a corresponding image template is obtained based on the category of the lung image. Wherein, the lung image is the lung image which needs to be extracted in a whole way.
Optionally, the lung images of the same category correspond to the same image template. The lung images of the same category may have the same layout, while different lung images of the same category may have different region content. Furthermore, different lung images of the same category may also have different orientations, tilts, etc. The image template corresponding to the lung image of a category may be provided with the positions of key points on the standard lung image of the category and the positions of the regions of various categories thereon. The same category of lung images corresponds to one standard lung image. The standard lung images are images of the lungs in fixed size, fixed orientation, fixed inclination (usually no inclination), etc.
200. Determining edge keypoint locations on the lung image;
specifically, a key point detection model corresponding to the category of the lung image is obtained; and inputting the lung image into the key point detection model to obtain the position of an edge key point on the lung image.
Optionally, the key point detection model is trained through the following steps: acquiring a lung image set with the same category as the lung image and the position of an edge key point on the lung image in the lung image set; labeling the corresponding lung image based on the position of an edge key point on the lung image in the lung image set to generate a sample lung image set; and training by using the sample lung image set to obtain the key point detection model.
In particular, the keypoints on the lung image may be points on a border that encompasses all regions on the lung image. In general, the key points on the lung image must include four vertices on the frame, and further, the key points on the lung image may include other points on the frame. Thus, the lung image includes at least four keypoints. For example, for a framed category of lung images, the keypoints may include the four vertices of the frame. For the lung image of the needle printing category, the key points may include four marker points in the needle printing.
Wherein, the traditional key point detection technology can be used for detecting the key point of the lung image with the frame category. Specifically, the executing body may first detect contour points of a frame in the lung image, and then determine key points from the contour points based on a certain strategy. For example, a circumscribed circle is added to the contour point, and the contour point on the circumscribed circle is the key point. The key point detection technology based on deep learning can be applied to lung images of any category for key point detection. For example, a multi-layer convolutional neural network is used to detect keypoints on a lung image. The fully-connected layer may or may not be included in the multi-layer convolutional neural network. Where fully connected layers are included, their output may be the coordinates of the keypoints. In the case where a fully connected layer is not included, its output may be a thermodynamic diagram. The thermodynamic value of each point on the thermodynamic diagram can represent the probability that each point is a key point, and the higher the thermodynamic value is, the higher the probability that the corresponding point is a key point is.
300. Generating a transformation matrix based on the edge keypoint locations on the lung image and the edge keypoint locations on the image template.
Specifically, the transformation matrix may be a matrix capable of mapping between the lung image and the image template, and the mapping relationship between the points on the lung image and the points on the image template is stored. Wherein the transformation matrix may be a first transformation matrix or a second transformation matrix. The first transformation matrix may be a matrix that maps from the lung image to the image template, storing a mapping of points on the lung image to points on the image template. And based on the positions of the key points on the lung image and the positions of the key points on the image template, a mapping relation from the lung image to the image template can be determined, so that a first transformation matrix is generated. The second transformation matrix may be a matrix that maps from the image template to the lung image, storing a mapping of points on the image template to points on the lung image. And based on the positions of the key points on the image template and the positions of the key points on the lung image, a mapping relation from the image template to the lung image can be determined, so that a second transformation matrix is generated.
400. And determining the image position corresponding to the lung image based on the image position on the image template and the transformation matrix.
Optionally, generating a transformation matrix based on the edge keypoint location on the lung image and the edge keypoint location on the image template, including: a first transformation matrix of edge keypoint locations on the lung image to edge keypoint locations on the image template is generated. Correspondingly, the determining the image position corresponding to the lung image based on the image position on the image template and the transformation matrix comprises: transforming the lung image based on the first transformation matrix to obtain a transformed lung image; and taking the image position on the image template as the image position on the transformed lung image.
In some embodiments, if the transformation matrix is a first transformation matrix, the lung image is first transformed based on the first transformation matrix to obtain a transformed lung image; the image position on the image template is then taken as the image position on the transformed lung image. Since the first transformation matrix is a matrix that is mapped from the lung image to the image template, transforming the lung image based on the first transformation matrix enables normalization of the lung image to a transformed lung image. Since the size, orientation, tilt, etc. of the transformed lung image are normalized to coincide with the image template, the image position on the transformed lung image coincides with the image position on the image template.
Optionally, the generating a transformation matrix based on the edge key point position on the lung image and the edge key point position on the image template includes: generating a second transformation matrix of edge keypoint locations on the image template to edge keypoint locations on the lung image. Correspondingly, the determining the image position corresponding to the lung image based on the image position on the image template and the transformation matrix comprises: and transforming the image position on the image template based on the second transformation matrix to obtain the image position on the lung image.
In some embodiments, if the transformation matrix is a second transformation matrix, the image location on the image template may be transformed based on the second transformation matrix to obtain the image location on the lung image. Since the second transformation matrix is a matrix that is mapped from the image template to the lung image, transforming the image position on the image template based on the second transformation matrix enables transforming the image position on the image template to the image position on the lung image.
500. And extracting the region at the image position corresponding to the lung image to obtain a target lung image.
In this embodiment, the region at the image position corresponding to the lung image is extracted to obtain the target lung image. For example, optical character recognition is performed on the image position corresponding to the lung image, and the recognition result is the region in the lung image.
Optionally, the image template is generated by the following steps: and acquiring a standard lung image with the same category as the lung image, and the position of an edge key point and the position of an image on the standard lung image. And labeling the standard lung image based on the position of the edge key point on the standard lung image and the position of the image to generate the image template.
Referring to fig. 2, a lung integral extraction device based on lung key points according to the present invention is shown, which includes: an image acquisition module 101, a keypoint determination module 102, a matrix generation module 103, a position determination module 104, and a target image acquisition module 105.
The image acquisition module is used for acquiring an image template corresponding to the category of the lung image; the key point determining module is used for determining the position of an edge key point on the lung image; the matrix generation module is used for generating a transformation matrix based on the position of the edge key point on the lung image and the position of the edge key point on the image template; the position determining module is used for determining the image position corresponding to the lung image based on the image position on the image template and the transformation matrix; and the target image acquisition module is used for extracting the region at the image position corresponding to the lung image to obtain a target lung image.
As described above, in the embodiment of the present application, an image template corresponding to the category of the lung image is obtained; determining edge keypoint locations on the lung image; generating a transformation matrix based on the edge keypoint location on the lung image and the edge keypoint location on the image template; determining an image position corresponding to the lung image based on the image position on the image template and the transformation matrix; extracting the region at the image position corresponding to the lung image to obtain a target lung image; the recognition accuracy of the lung edges is improved, and the misdiagnosis probability of lung nodule detection is reduced.
The embodiment of the application also provides a computer device which can integrate the pulmonary key point-based pulmonary integral extraction device provided by the embodiment of the application. Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application. Referring to fig. 3, the computer apparatus includes: an input device 43, an output device 44, a memory 42, and one or more processors 41; the memory 42 for storing one or more programs; when executed by the one or more processors 41, cause the one or more processors 41 to implement the pulmonary keypoint-based pulmonary ensemble extraction method provided in the embodiments described above. Wherein the input device 43, the output device 44, the memory 42 and the processor 41 may be connected by a bus or other means, for example, in fig. 3.
The processor 41 executes various functional applications of the device and data processing by executing software programs, instructions and modules stored in the memory 42, namely, the lung keypoint-based lung ensemble extraction method described above.
The computer device provided above can be used to execute the method for extracting the whole lung based on the key points of the lung provided above, and has corresponding functions and advantages.
Embodiments of the present application further provide a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a pulmonary keypoint-based pulmonary ensemble extraction method, the pulmonary keypoint-based pulmonary ensemble extraction method comprising: acquiring an image template corresponding to the category of the lung image; determining edge keypoint locations on the lung image; generating a transformation matrix based on the edge keypoint location on the lung image and the edge keypoint location on the image template; and determining the image position corresponding to the lung image based on the image position on the image template and the transformation matrix.
Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer device memory or random access memory such as DRAM, DDRRAM, SRAM, EDORAM, Lanbus (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer apparatus in which the program is executed, or may be located in a different second computer apparatus connected to the first computer apparatus through a network (such as the internet). The second computer device may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations, such as in different computer devices that are connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.
Of course, the storage medium provided by the embodiments of the present application contains computer executable instructions, and the computer executable instructions are not limited to the pulmonary keypoint-based pulmonary ensemble extraction method described above, and may also perform related operations in the pulmonary keypoint-based pulmonary ensemble extraction method provided by any of the embodiments of the present application.
The pulmonary keypoint-based pulmonary global extraction device, the storage medium and the computer device provided in the above embodiments may perform the pulmonary keypoint-based pulmonary global extraction method provided in any embodiment of the present application, and the technical details not described in detail in the above embodiments may be referred to the pulmonary keypoint-based pulmonary global extraction method provided in any embodiment of the present application.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (9)
1. A lung integral extraction method based on lung key points is characterized in that: the method comprises the following steps:
acquiring an image template corresponding to the category of the lung image;
determining edge keypoint locations on the lung image;
generating a transformation matrix based on the edge keypoint location on the lung image and the edge keypoint location on the image template;
determining an image position corresponding to the lung image based on the image position on the image template and the transformation matrix;
and extracting the region at the image position corresponding to the lung image to obtain a target lung image.
2. The method for extracting the whole lung based on the key points of the lung as claimed in claim 1, wherein: the determining edge keypoint locations on the lung image comprises:
acquiring a key point detection model corresponding to the category of the lung image;
and inputting the lung image into the key point detection model to obtain the position of an edge key point on the lung image.
3. The method for extracting the whole lung based on the key points of the lung as claimed in claim 2, wherein: the key point detection model is trained through the following steps:
acquiring a lung image set with the same category as the lung image and the position of an edge key point on the lung image in the lung image set;
labeling the corresponding lung image based on the position of an edge key point on the lung image in the lung image set to generate a sample lung image set;
and training by using the sample lung image set to obtain the key point detection model.
4. The method for extracting the whole lung based on the key points of the lung as claimed in claim 1, wherein: generating a transformation matrix based on the edge keypoint locations on the lung image and the edge keypoint locations on the image template, comprising:
generating a first transformation matrix from edge keypoint locations on the lung image to edge keypoint locations on the image template; and
the determining the image position corresponding to the lung image based on the image position on the image template and the transformation matrix comprises:
transforming the lung image based on the first transformation matrix to obtain a transformed lung image;
and taking the image position on the image template as the image position on the transformed lung image.
5. The method for extracting the whole lung based on the key points of the lung as claimed in claim 1, wherein: generating a transformation matrix based on the edge keypoint locations on the lung image and the edge keypoint locations on the image template, comprising:
generating a second transformation matrix of edge keypoint locations on the image template to edge keypoint locations on the lung image; and
the determining the image position corresponding to the lung image based on the image position on the image template and the transformation matrix comprises:
and transforming the image position on the image template based on the second transformation matrix to obtain the image position on the lung image.
6. The method for extracting the whole lung based on the key points of the lung as claimed in claim 1, wherein: the image template is generated by the following steps:
acquiring a standard lung image with the same category as the lung image, and an edge key point position and an image position on the standard lung image;
and labeling the standard lung image based on the position of the edge key point on the standard lung image and the position of the image to generate the image template.
7. The utility model provides an integral extraction device of lung based on key point of lung which characterized in that: the method comprises the following steps:
the image acquisition module is used for acquiring an image template corresponding to the category of the lung image;
a keypoint determination module for determining the location of edge keypoints on the lung image;
a matrix generation module for generating a transformation matrix based on the edge key point position on the lung image and the edge key point position on the image template;
a position determining module, configured to determine an image position corresponding to the lung image based on the image position on the image template and the transformation matrix;
and the target image acquisition module is used for extracting the region at the image position corresponding to the lung image to obtain a target lung image.
8. A computer device, comprising: a memory and one or more processors;
the memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a pulmonary keypoint-based pulmonary ensemble extraction method as recited in any of claims 1-6.
9. A storage medium containing computer-executable instructions, which when executed by a computer processor, perform a pulmonary keypoint-based pulmonary ensemble extraction method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110974430.3A CN113658159A (en) | 2021-08-24 | 2021-08-24 | Lung integral extraction method and system based on lung key points |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110974430.3A CN113658159A (en) | 2021-08-24 | 2021-08-24 | Lung integral extraction method and system based on lung key points |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113658159A true CN113658159A (en) | 2021-11-16 |
Family
ID=78492676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110974430.3A Pending CN113658159A (en) | 2021-08-24 | 2021-08-24 | Lung integral extraction method and system based on lung key points |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113658159A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507354A (en) * | 2020-04-17 | 2020-08-07 | 北京百度网讯科技有限公司 | Information extraction method, device, equipment and storage medium |
| CN111507965A (en) * | 2020-04-17 | 2020-08-07 | 中山仰视科技有限公司 | Novel coronavirus pneumonia focus detection method, system, device and storage medium |
| CN112085714A (en) * | 2020-08-31 | 2020-12-15 | 广州视源电子科技股份有限公司 | Pulmonary nodule detection method, model training method, device, equipment and medium |
| CN112635013A (en) * | 2020-11-30 | 2021-04-09 | 泰康保险集团股份有限公司 | Medical image information processing method and device, electronic equipment and storage medium |
-
2021
- 2021-08-24 CN CN202110974430.3A patent/CN113658159A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507354A (en) * | 2020-04-17 | 2020-08-07 | 北京百度网讯科技有限公司 | Information extraction method, device, equipment and storage medium |
| CN111507965A (en) * | 2020-04-17 | 2020-08-07 | 中山仰视科技有限公司 | Novel coronavirus pneumonia focus detection method, system, device and storage medium |
| CN112085714A (en) * | 2020-08-31 | 2020-12-15 | 广州视源电子科技股份有限公司 | Pulmonary nodule detection method, model training method, device, equipment and medium |
| CN112635013A (en) * | 2020-11-30 | 2021-04-09 | 泰康保险集团股份有限公司 | Medical image information processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gojcic et al. | The perfect match: 3d point cloud matching with smoothed densities | |
| Schönberger et al. | A vote-and-verify strategy for fast spatial verification in image retrieval | |
| Cao et al. | Breast tumor detection in ultrasound images using deep learning | |
| JP7046553B2 (en) | Superposition method of magnetic tracking system equipped with an image pickup device | |
| CN112950651A (en) | Automatic delineation method of mediastinal lymph drainage area based on deep learning network | |
| US8165354B1 (en) | Face recognition with discriminative face alignment | |
| US8737725B2 (en) | Method and system for learning based object detection in medical images | |
| Lee et al. | Familiarity based unified visual attention model for fast and robust object recognition | |
| JP2007054636A (en) | Method for positioning a pair of images and program storing apparatus for executing above method by realizing program comprised of command executed by computer | |
| US8554016B2 (en) | Image registration system and method for registering images for deformable surfaces | |
| JP2008080132A (en) | System and method for detecting object in high-dimensional image space | |
| KR20160129000A (en) | Real-time 3d gesture recognition and tracking system for mobile devices | |
| JP2007518461A (en) | Automatic optimal surface determination for heart related acquisition | |
| JP2010000133A (en) | Image display, image display method and program | |
| CN109460044A (en) | A kind of robot method for homing, device and robot based on two dimensional code | |
| CN107392847A (en) | A kind of fingerprint image joining method based on minutiae point and range image | |
| CN110135304A (en) | Human body method for recognizing position and attitude and device | |
| CN114121269B (en) | Traditional Chinese medicine facial diagnosis auxiliary diagnosis method and device based on face feature detection and storage medium | |
| WO2020108436A1 (en) | Tongue surface image segmentation device and method, and computer storage medium | |
| CN113658159A (en) | Lung integral extraction method and system based on lung key points | |
| JP2006260311A (en) | Matching method, matching device, and program | |
| Zhu et al. | Global and local geometric constrained feature matching for high resolution remote sensing images | |
| CN107464243B (en) | Aortic valve positioning method, device and equipment | |
| CN113241156B (en) | Marking method and system of orthopedics focus counting network based on detection guidance | |
| CN113689939A (en) | Image storage method, system and computing device for image feature matching |
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 |