CN112070790B - Mixed lung segmentation system based on deep learning and image processing - Google Patents

Mixed lung segmentation system based on deep learning and image processing Download PDF

Info

Publication number
CN112070790B
CN112070790B CN202010951317.9A CN202010951317A CN112070790B CN 112070790 B CN112070790 B CN 112070790B CN 202010951317 A CN202010951317 A CN 202010951317A CN 112070790 B CN112070790 B CN 112070790B
Authority
CN
China
Prior art keywords
segmentation
lung
image
module
deep learning
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010951317.9A
Other languages
Chinese (zh)
Other versions
CN112070790A (en
Inventor
张忞
周欣欢
刘艺博
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Weiyin Technology Co ltd
Original Assignee
Hangzhou Weiyin Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Weiyin Technology Co ltd filed Critical Hangzhou Weiyin Technology Co ltd
Priority to CN202010951317.9A priority Critical patent/CN112070790B/en
Publication of CN112070790A publication Critical patent/CN112070790A/en
Application granted granted Critical
Publication of CN112070790B publication Critical patent/CN112070790B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • 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
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30061—Lung
    • G06T2207/30064—Lung nodule
    • 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
    • G06T2207/30101—Blood vessel; Artery; Vein; Vascular

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to a mixed lung segmentation system based on deep learning and image processing, which comprises: the acquisition module is used for acquiring a DICOM file of the lung CT image; the preprocessing module is used for preprocessing the DICOM file; the first segmentation module is used for performing bronchial segmentation, blood vessel segmentation and pulmonary nodule detection on the preprocessed DICOM file; the second segmentation module is used for taking the DICOM file, the segmentation result of the bronchus and the segmentation result of the blood vessel as the input of the deep learning model, and performing segmentation and extraction of the lung lobe and segmentation of the artery and vein; and the third segmentation module is used for taking the segmentation result of the bronchus, the segmentation result of the lung lobe and the segmentation result of the arteriovenous as the input of the segmentation model to segment the lung. The invention realizes the segmentation of the whole lung and can provide anatomical structure reference for preoperative planning for wedge-shaped operation or puncture ablation operation of the lung.

Description

Mixed lung segmentation system based on deep learning and image processing
Technical Field
The invention relates to the technical field of image processing, in particular to a hybrid lung segmentation system based on deep learning and image processing.
Background
The deep learning method obtains huge achievements in the field of image processing, and provides possibility for the medical image data to identify special parts by applying a deep learning technology. Currently, CAD systems based on deep learning have wide application in identifying and segmenting organs, feature regions, etc. in CT images.
Image segmentation is used as a branch of image processing and is an important research direction in medical field application. Two-dimensional reconstruction and quantitative analysis of human tissues both require segmentation of relevant parts in advance. However, since the individual difference of the internal tissues of the human body is large, the requirements of different algorithms on the shape and quality of the input image are different, and the requirement on the accuracy of the lung image segmentation in clinical application is high, the lung image segmentation becomes a difficult problem in the clinical application of medical images.
The existing device and method for segmenting lung CT images are all directed at segmenting partial organs of the lung, and an overall segmentation scheme required by a thoracic surgery pulmonary nodule is not presented.
Disclosure of Invention
The invention provides a mixed lung segmentation system based on deep learning and image processing, which solves the problem of integral lung segmentation.
The technical scheme adopted by the invention for solving the technical problem is as follows: a hybrid lung segmentation system based on deep learning and image processing is provided, comprising: the acquisition module is used for acquiring a DICOM file of the lung CT image; the preprocessing module is used for preprocessing the DICOM file; the first segmentation module is used for performing bronchial segmentation, blood vessel segmentation and pulmonary nodule detection on the preprocessed DICOM file; the second segmentation module is used for taking the DICOM file, the segmentation result of the bronchus and the segmentation result of the blood vessel as the input of the deep learning model, and performing segmentation and extraction of the lung lobe and segmentation of the artery and vein; and the third segmentation module is used for taking the segmentation result of the bronchus, the segmentation result of the lung lobe and the segmentation result of the arteriovenous as the input of the segmentation model to segment the lung.
The preprocessing module is used for performing one or more of the following combinations on the DICOM file of the CT image through resampling and cutting: resizing, cropping, rotating, normalizing, and normalizing.
The first segmentation module comprises: the lung extraction submodule is used for extracting a lung image from the preprocessed image through threshold value binarization processing and opening and closing processing of the image; the bronchus extraction submodule is used for acquiring a bronchus image from the lung image through a region growing algorithm and/or a deep learning Unet segmentation algorithm; the blood vessel segmentation submodule is used for calculating vesselness values of all pixels in the lung image and extracting blood vessels by adopting a binarization processing mode; and the lung nodule detection submodule is used for carrying out lung nodule detection on the lung image through the deep learning model and extracting the detected lung nodule through the detection frame.
The second segmentation module comprises: and the lung lobe segmentation submodule is used for taking the bronchial segmentation result and the preprocessed image as the input of the deep learning model and dividing the lung into: left upper lung, left lower lung, right upper lung, right lower lung, and right middle lung; and the arteriovenous segmentation sub-module is used for taking the result of the bronchial segmentation and the result of the blood vessel segmentation as the input of a two-classification model, performing two-classification on each pixel of the blood vessel image, and dividing the blood vessel into an arterial blood vessel and a venous blood vessel.
The third segmentation module is used for segmenting each lung lobe by veins according to the fact that each lung segment comprises a third-level bronchus and the segment is segmented by veins, calculating the distance between each pixel and the nearest bronchus and veins of each lung lobe, clustering and segmenting, and dividing each lung lobe into 2-5 lung segments.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: according to the invention, the extraction of bronchus, the segmentation of blood vessels and the detection of pulmonary nodules are carried out on the lung medical image, the segmentation and the extraction of lung lobes and the segmentation of arteriovenous are realized on the basis of the extraction of bronchus and the segmentation of blood vessels, and the segmentation of lung segments is realized on the basis of the lung lobe segmentation result, so that the segmentation of the whole lung is realized. The method is used for fusing a large amount of prior professional experience knowledge, so that the method can effectively avoid the problem that a deep learning algorithm or a traditional machine learning algorithm excessively depends on training data, can greatly improve the accuracy and robustness of segmentation, and provides anatomical structure reference for preoperative planning for a lung wedge operation or puncture ablation operation.
Drawings
Fig. 1 is a schematic structural view of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
The embodiment of the invention relates to a hybrid lung segmentation system based on deep learning and image processing, which comprises the following components in part by weight as shown in figure 1: the device comprises an acquisition module, a preprocessing module, a first segmentation module, a second segmentation module and a third segmentation module.
The system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a DICOM file of a lung CT image;
the preprocessing module is used for preprocessing the DICOM file, and the preprocessing is to perform one or more of the following combinations on the DICOM file of the CT image through resampling and clipping: resizing, cropping, rotating, normalizing, and normalizing.
And the first segmentation module is used for performing bronchial segmentation, blood vessel segmentation and pulmonary nodule detection on the preprocessed DICOM file. The first segmentation module comprises: and the lung extraction submodule is used for extracting a lung image from the preprocessed image through threshold value binarization processing and opening and closing processing of the image. The bronchus extraction submodule is used for acquiring a bronchus image from a lung image through a region growing algorithm and/or a deep learning Unet segmentation algorithm, and probability fusion is required when the region growing algorithm and the deep learning Unet segmentation algorithm are combined, wherein the probability fusion mode is as follows: eta = alpha regiongrow + (1-alpha) Unet, wherein regiongrow is the probability of determining as the bronchus by adopting a region growing algorithm, unet is the probability of determining as the bronchus by adopting a deep learning Unet segmentation algorithm, and alpha is a weight factor and has a value range of 0-1. The blood vessel segmentation submodule is used for calculating vesselness values of all pixels in the lung image and extracting blood vessels by adopting a binarization processing mode; and the lung nodule detection submodule is used for carrying out lung nodule detection on the lung image through the deep learning model and extracting the lung nodule in the detection frame through an ostu threshold segmentation algorithm.
And the second segmentation module is used for taking the DICOM file, the segmentation result of the bronchus and the segmentation result of the blood vessel as the input of the deep learning model, and performing segmentation and extraction of the lung lobe and segmentation of the artery and vein. The second segmentation module comprises: a lung lobe segmentation sub-module, configured to take the result of the bronchial segmentation and the preprocessed image as input of a deep learning model (e.g., unet in deep learning), and segment the lung into: left upper lung, left lower lung, right upper lung, right lower lung, and right middle lung; and an arteriovenous segmentation sub-module which is used for taking the result of the bronchial segmentation and the result of the blood vessel segmentation as the input of a classification model (such as resnet, SVM or xgboost), and performing binary classification on each pixel of the blood vessel image to divide the blood vessel into an arterial blood vessel and a venous blood vessel.
And the third segmentation module is used for taking the segmentation result of the bronchus, the segmentation result of the lung lobe and the segmentation result of the arteriovenous as the input of the segmentation model to segment the lung. The third segmentation module is used for segmenting each lung lobe by veins according to the fact that each lung segment comprises a third-level bronchus and the segment is segmented by veins, calculating the distance between each pixel and the nearest bronchus and veins of each lung lobe, clustering and segmenting, and dividing each lung lobe into 2-5 lung segments.
The invention can be found out easily that the lung segmentation method can be used for segmenting the lung segment based on the lung lobe segmentation result by extracting the bronchus, segmenting the blood vessel and detecting the lung nodule from the lung medical image, realizing the segmentation and extraction of the lung lobe and the segmentation of the artery and vein based on the extraction of the bronchus and the segmentation of the blood vessel, thereby realizing the segmentation of the whole lung and providing anatomical structure reference planned before the operation for the thoracic surgery lung wedge operation or the lung puncture ablation operation. Compared with other methods, the segmentation sequence of the invention can accurately divide the lung segments. Because the method adopts a large amount of prior professional knowledge, the robustness of the method is greatly enhanced, and the problem that a deep learning algorithm or a traditional machine learning algorithm excessively depends on training data is effectively avoided.

Claims (4)

1. A hybrid lung segmentation system based on deep learning and image processing, comprising: the acquisition module is used for acquiring a DICOM file of the lung CT image; the preprocessing module is used for preprocessing the DICOM file; the first segmentation module is used for performing bronchial segmentation, blood vessel segmentation and pulmonary nodule detection on the preprocessed DICOM file; the second segmentation module is used for taking the DICOM file, the segmentation result of the bronchus and the segmentation result of the blood vessel as the input of the deep learning model, and performing segmentation and extraction of the lung lobe and segmentation of the artery and vein; the third segmentation module is used for taking the segmentation result of the bronchus, the segmentation result of the lung lobe and the segmentation result of the arteriovenous as the input of a segmentation model to segment the lung; the third segmentation module is used for segmenting each lung lobe by veins according to the fact that each lung segment contains a third-level bronchus and segments, calculating the distance between each pixel and the nearest bronchus and veins for each lung lobe, performing clustering segmentation, and segmenting each lung lobe into 2-5 lung segments.
2. The deep learning and image processing based hybrid lung segmentation system of claim 1 wherein the pre-processing module is configured to combine, by resampling and cropping, the DICOM file of the CT image with one or more of: resizing, cropping, rotating, normalizing, and normalizing.
3. The hybrid deep learning and image processing lung segmentation system according to claim 1, wherein the first segmentation module comprises: the lung extraction submodule is used for extracting a lung image from the preprocessed image through threshold binarization processing and opening and closing processing of the image; the bronchus extraction submodule is used for acquiring a bronchus image from the lung image through a region growing algorithm and/or a deep learning Unet segmentation algorithm; the blood vessel segmentation submodule is used for calculating vesselness values of all pixels in the lung image and extracting blood vessels by adopting a binarization processing mode; and the lung nodule detection submodule is used for carrying out lung nodule detection on the lung image through the deep learning model and extracting the detected lung nodule through the detection frame.
4. The hybrid deep learning and image processing lung segmentation system according to claim 1, wherein the second segmentation module comprises: and the lung lobe segmentation submodule is used for taking the bronchial segmentation result and the preprocessed image as the input of the deep learning model and dividing the lung into: the left upper lung, the left lower lung, the right upper lung, the right lower lung, and the right middle lung; and the arteriovenous segmentation sub-module is used for taking the bronchial segmentation result and the blood vessel segmentation result as the input of a two-classification model, and performing two-classification on each pixel of the blood vessel image to divide the blood vessel into an arterial blood vessel and a venous blood vessel.
CN202010951317.9A 2020-09-11 2020-09-11 Mixed lung segmentation system based on deep learning and image processing Active CN112070790B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010951317.9A CN112070790B (en) 2020-09-11 2020-09-11 Mixed lung segmentation system based on deep learning and image processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010951317.9A CN112070790B (en) 2020-09-11 2020-09-11 Mixed lung segmentation system based on deep learning and image processing

Publications (2)

Publication Number Publication Date
CN112070790A CN112070790A (en) 2020-12-11
CN112070790B true CN112070790B (en) 2023-04-07

Family

ID=73696264

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010951317.9A Active CN112070790B (en) 2020-09-11 2020-09-11 Mixed lung segmentation system based on deep learning and image processing

Country Status (1)

Country Link
CN (1) CN112070790B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112861961B (en) * 2021-02-03 2021-11-12 推想医疗科技股份有限公司 Pulmonary blood vessel classification method and device, storage medium and electronic equipment
CN113361584B (en) * 2021-06-01 2022-05-27 推想医疗科技股份有限公司 Model training method and device, and pulmonary arterial hypertension measurement method and device
CN113793357A (en) * 2021-07-07 2021-12-14 点内（上海）生物科技有限公司 Bronchopulmonary segment image segmentation method and system based on deep learning
CN114708203A (en) * 2022-03-22 2022-07-05 上海联影智能医疗科技有限公司 Training method of image segmentation model, image processing method, device and equipment

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1447772A1 (en) * 2003-02-11 2004-08-18 MeVis GmbH A method of lung lobe segmentation and computer system
CN107633514A (en) * 2017-09-19 2018-01-26 北京大学第三医院 A kind of Lung neoplasm periphery blood vessel quantitative evaluation system and method
CN109215033A (en) * 2017-06-30 2019-01-15 上海联影医疗科技有限公司 The method and system of image segmentation
CN111311583A (en) * 2020-02-24 2020-06-19 广州柏视医疗科技有限公司 Method and system for naming pulmonary trachea and blood vessel in segmented mode

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8150113B2 (en) * 2008-01-23 2012-04-03 Carestream Health, Inc. Method for lung lesion location identification
CN109146854B (en) * 2018-08-01 2021-10-01 东北大学 Analysis method for association relationship between pulmonary nodule and pulmonary blood vessel
CN109727260A (en) * 2019-01-24 2019-05-07 杭州英库医疗科技有限公司 A kind of three-dimensional lobe of the lung dividing method based on CT images
CN110956635B (en) * 2019-11-15 2023-12-01 上海联影智能医疗科技有限公司 Lung segment segmentation method, device, equipment and storage medium
CN111091573B (en) * 2019-12-20 2021-07-20 广州柏视医疗科技有限公司 CT image pulmonary vessel segmentation method and system based on deep learning

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1447772A1 (en) * 2003-02-11 2004-08-18 MeVis GmbH A method of lung lobe segmentation and computer system
CN109215033A (en) * 2017-06-30 2019-01-15 上海联影医疗科技有限公司 The method and system of image segmentation
CN107633514A (en) * 2017-09-19 2018-01-26 北京大学第三医院 A kind of Lung neoplasm periphery blood vessel quantitative evaluation system and method
CN111311583A (en) * 2020-02-24 2020-06-19 广州柏视医疗科技有限公司 Method and system for naming pulmonary trachea and blood vessel in segmented mode

Also Published As

Publication number Publication date
CN112070790A (en) 2020-12-11

Similar Documents

Publication Publication Date Title
CN112070790B (en) Mixed lung segmentation system based on deep learning and image processing
CN109636808B (en) Lung lobe segmentation method based on full convolution neural network
CN110934606B (en) Cerebral apoplexy early-stage flat-scan CT image evaluation system and method and readable storage medium
CN110310281B (en) Mask-RCNN deep learning-based pulmonary nodule detection and segmentation method in virtual medical treatment
EP3391284B1 (en) Interpretation and quantification of emergency features on head computed tomography
US20190236782A1 (en) Systems and methods for detecting an indication of malignancy in a sequence of anatomical images
CN108133476B (en) Method and system for automatically detecting pulmonary nodules
CN110796670B (en) Dissection method and device for dissecting interbed artery
EP3814984B1 (en) Systems and methods for automated detection of visual objects in medical images
US20120250957A1 (en) Shape based similarity of continuous wave doppler images
US20210142470A1 (en) System and method for identification of pulmonary arteries and veins depicted on chest ct scans
CN114627067A (en) Wound area measurement and auxiliary diagnosis and treatment method based on image processing
CN111462049A (en) Automatic lesion area form labeling method in mammary gland ultrasonic radiography video
CN116503607B (en) CT image segmentation method and system based on deep learning
CN113160120A (en) Liver blood vessel segmentation method and system based on multi-mode fusion and deep learning
CN113889238A (en) Image identification method and device, electronic equipment and storage medium
CN115471512A (en) Medical image segmentation method based on self-supervision contrast learning
CN111275722A (en) Lung segment and liver segment segmentation method and system
Xu et al. CHSNet: Automatic lesion segmentation network guided by CT image features for acute cerebral hemorrhage
CN114764855A (en) Intelligent cystoscope tumor segmentation method, device and equipment based on deep learning
CN116664592A (en) Image-based arteriovenous blood vessel separation method and device, electronic equipment and medium
Dickson et al. A Dual Channel Multiscale Convolution U-Net Methodfor Liver Tumor Segmentation from Abdomen CT Images
CN116228731A (en) Multi-contrast learning coronary artery high-risk plaque detection method, system and terminal
CN116363311A (en) Coronary Leiden score calculation and risk classification method and system
Wen et al. A novel lesion segmentation algorithm based on U-Net network for Tuberculosis CT image

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 311200 Room 3A08, Building D, Integrated Circuit Design Industrial Park, No. 858, Jianshe Second Road, Economic and Technological Development Zone, Xiaoshan District, Hangzhou, Zhejiang

Applicant after: Hangzhou Weiyin Technology Co.,Ltd.

Address before: 311200 room 806-2, building 1, No. 371, Xingxing Road, Xiaoshan District, Hangzhou, Zhejiang Province

Applicant before: Hangzhou Weiyin Technology Co.,Ltd.

GR01 Patent grant
GR01 Patent grant