CN113592029A - Automatic medical image labeling method and system under small sample condition - Google Patents
Automatic medical image labeling method and system under small sample condition Download PDFInfo
- Publication number
- CN113592029A CN113592029A CN202110941761.7A CN202110941761A CN113592029A CN 113592029 A CN113592029 A CN 113592029A CN 202110941761 A CN202110941761 A CN 202110941761A CN 113592029 A CN113592029 A CN 113592029A
- Authority
- CN
- China
- Prior art keywords
- labeling
- result
- image
- label classification
- model
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for automatically labeling a medical image under a small sample condition, wherein the method comprises the following steps: the system comprises an image acquisition module, a label processing module, a label classification module and a label generation module which are sequentially connected, wherein an initial image data set is obtained by acquiring an image to be labeled and extracting the characteristics of the image to be labeled, and the initial image data set is proportionally divided into a training set and a test set; constructing a pre-labeling model, and taking a training set as the input of the pre-labeling model to obtain a pre-labeling result; constructing a target label classification model, and taking a pre-labeling result as the input of the label classification model to obtain a label classification result; and determining the labeling information of the image to be labeled based on the pre-labeling result and the label classification result. The method and the device realize automatic intelligent labeling of the medical image, do not need manual contour delineation, region information input, edge adjustment of a pre-labeling result and the like, and greatly improve the generation efficiency and accuracy of the labeling data set.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a method and a system for automatically labeling a medical image under a small sample condition.
Background
The labeling of the medical image is a medical corpus labeling for medical experts to perform classification, lesion detection or lesion segmentation on the medical image, such as a Computed Tomography (CT) image, a Magnetic Resonance (MR) image, an electrocardiogram, a pathological section image, and the like, so as to form the medical image. The medical image is the most important auxiliary means for medical diagnosis, drug response monitoring, disease management and the like, and has the advantages of high speed, non-invasion, small side effect, low cost, good effect and the like.
In the medical image labeling process, image labeling often needs experienced radiologists to perform labeling, the number of radiologists is short, and the labor labeling cost is high. When a large number of complicated medical image labels are encountered, a series of problems are caused under the condition of shortage of manpower for labeling. Therefore, Artificial Intelligence (AI) medical data tagging is particularly important. The AI technology requires that sophisticated medical experts incorporate medical business knowledge accumulated over many years into artificial intelligence applications, and medical data and expert knowledge must be deeply combined. However, the AI training process requires a large amount of standard medical image labeling data.
In the prior art, the medical image labeling methods are mainly classified into the following two categories: the traditional manual labeling method and the manual revision method under the pre-labeling. The traditional manual labeling method is that a medical image expert manually delineates the outline of the abnormal data sign of an image to be labeled by using labeling tools such as polygons, lassos, automatic filling and the like, or selects or inputs the name of a label to complete the detection of a focus area; the manual revision method under the pre-labeling is that the medical image expert performs edge adjustment on the pre-labeling result output by the model, and even if the output effect of the model is poor, the expert deletes the result of the output model and performs manual labeling again.
The shapes of focuses in images are often irregular, a large amount of time is consumed for manual marking, the automatic marking method through artificial intelligence learning often has problems in accuracy, correct marking of each image cannot be guaranteed, and the time for forming a certain number of standard data sets cannot be shortened by using the method alone. Therefore, the prior art has the technical defects of time and labor waste and the like, and can not quickly generate a standard labeled data set; moreover, the manual labeling method is prone to form wrong labels due to subjective factors, the labeling effect of the manual revision method under the pre-labeling is poor, each image cannot be ensured to be correctly labeled, and the correctness of the standard labeled data set cannot be further ensured.
Disclosure of Invention
In order to achieve the purpose, the invention provides the following scheme: a method and a system for automatically labeling medical images under the condition of small samples are provided, wherein the method comprises the following steps:
acquiring an image to be marked, extracting the characteristics of the image to be marked to obtain an initial image data set, and dividing the initial image data set into a training set and a test set according to the proportion;
constructing a pre-labeling model, and taking the training set as the input of the pre-labeling model to obtain a pre-labeling result;
constructing a target label classification model, and taking the pre-labeling result as the input of the target label classification model to obtain a label classification result;
and determining the labeling information of the image to be labeled based on the pre-labeling result and the label classification result.
Preferably, the feature types of the feature extraction include: color histogram, block-by-block color moment, edge direction histogram, color correlation graph, facial features, wavelet texture, SIFT-based descriptor bag.
Preferably, in the process of dividing the training set, a target shape mark point is obtained by constructing a dense linear regression model and a sparse linear regression model of the initial shape mark point, and a shape variable model is obtained based on the target shape mark point;
an affine transformation model of the initial shape marking region is built, the texture of the target shape marking region is obtained, and a variable texture model is obtained based on the texture of the target shape marking region;
and performing initial positioning through a Hough voting learning method based on the image to be labeled, and automatically labeling image contents according to the convergence of the translation parameter, the rotation parameter and the scaling parameter of the shape variable model and the texture variable model to obtain the training set.
Preferably, the obtaining the pre-labeling result further comprises determining a cross-mixing ratio of the pre-labeling result, and obtaining a standard label classification result corresponding to the pre-labeling result based on the cross-mixing ratio;
determining label classification sample data based on the pre-labeling result and a standard label classification result corresponding to the pre-labeling result;
training an initial label classification model based on the label classification sample data to obtain the target label classification model.
Preferably, the pre-labeling result is obtained by specifically using sample pre-labeling information of a sample labeling image input by a user, and the pre-labeling result is determined based on the sample pre-labeling information; or, determining the pre-labeling result based on the pre-labeling result of the image to be labeled output by the pre-labeling model.
Preferably, after obtaining the tag classification result, the method further includes: obtaining a verification result corresponding to the label classification result based on the test set and the target label classification model;
and determining the labeling information corresponding to the image to be labeled based on the pre-labeling result, the label classification result and the verification result corresponding to the label classification result.
Preferably, the method further comprises the following steps: determining classification model optimization sample data based on the verification result, the label classification result and the pre-labeling result; and performing optimization iterative training on the target label classification model based on the classification model optimization sample data.
An automatic medical image annotation system under small sample condition, comprising:
the image acquisition module is used for acquiring an image to be annotated and acquiring an initial image data set by performing feature extraction on the image to be annotated;
the annotation processing module is connected with the image acquisition module and used for obtaining a pre-annotation result;
the label classification module is connected with the label processing module and used for obtaining a label classification result;
and the label generation module is connected with the label classification module and used for generating the label information of the image to be labeled according to the pre-labeling result and the label classification result.
Preferably, the feature types of the feature extraction include: color histogram, block-by-block color moment, edge direction histogram, color correlation graph, facial features, wavelet texture, SIFT-based descriptor bag.
Preferably, the system further comprises a storage module, and the storage module is respectively connected to the image acquisition module, the annotation processing module, the label classification module, and the annotation generation module, and is configured to store the initial image data set, the pre-annotation result, the label classification result, and the annotation information of the image to be annotated.
The invention discloses the following technical effects:
according to the automatic medical image labeling method and system under the condition of the small sample, the dense linear regression model and the sparse linear regression model are constructed, the shape mark points of the new sample medical image tissue and organ at other positions can be generated, the texture of the new sample medical image tissue and organ at other positions can be generated through piecewise affine transformation, the medical image labeling sample demand is greatly reduced, and the problem that due to the professional characteristics of the medical image, the number of medical image labels is less than that of the traditional network image is effectively solved. Meanwhile, the problem of insufficient training samples of certain categories can be supplemented, the method has the advantage of sample balance among the categories, and has better clinical reality significance. The task of medical image labeling is converted into the modeling and matching problem of a tissue organ model, a shape and texture variable model of the tissue organ of the medical image is generated in the aligned sample image by a principal component method, and the shape and texture model of the tissue organ has the advantages of rotational invariance, translational invariance and scaling invariance, insensitivity to noise, strong robustness, good robustness and the like.
According to the method, the pre-labeling result of the image to be labeled is generated through the pre-labeling model, and manual contour drawing, region information input and the like of the image are not needed, so that the pre-labeling results of a large number of images are rapidly generated, and the generation efficiency of the labeling data set is improved; and the label classification result of the pre-labeling result is generated through the label classification model, the dimension reduction of the labeling revision problem of the pre-labeling result into the labeling classification problem is realized, the edge adjustment and the like of the pre-labeling result do not need to be manually carried out, and the generation efficiency of the labeling data set is further improved. And the formed labeling data set also comprises a label classification result of the pre-labeling result, so that the accuracy of the labeling data set is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of an image annotation method according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, the present invention provides a method and a system for automatically labeling a medical image under a small sample condition, wherein the method specifically comprises the following steps:
in the present embodiment, taking medical images as an example, the image to be labeled may be, for example, a CT image, an MR image, an ultrasound image, an X-ray image, an electrocardiogram or a pathological section image. It should be noted that the number of the images to be annotated may be one or more.
Performing feature extraction on the image to be annotated to obtain an initial image data set, and dividing the initial image data set into a training set and a test set according to a ratio of 7: 3; the feature types of the feature extraction include: color histogram, block-by-block color moment, edge direction histogram, color correlation graph, facial features, wavelet texture, SIFT-based descriptor bag.
Obtaining target shape mark points by constructing a dense linear regression model and a sparse linear regression model of initial shape mark points, and aligning the shape mark points of all tissues and organs by using a generalized alignment and singular value decomposition algorithm based on the target shape mark points to obtain shape mark points with unchanged rotation, translation and scaling; and performing principal component analysis on the tissue and organ shape mark points after the generalized alignment, and obtaining a shape variable model by using the mean value shape, the orthogonal basis vector of the shape subspace and the projection coefficient of the shape subspace.
An affine transformation model of the initial shape marking region is built, the texture of the target shape marking region is obtained, and a variable texture model is obtained based on the texture of the target shape marking region;
and performing initial positioning through a Hough voting learning method based on the image to be labeled, and automatically labeling image contents according to the convergence of the translation parameter, the rotation parameter and the scaling parameter of the shape variable model and the texture variable model to obtain a training set.
Specifically, initial values of parameters such as translation, rotation and scaling of the model are obtained by initially positioning the shape of the tissue organ and the position of the texture model in the image to be labeled by using a Hough voting learning method.
The shape marking points of the tissue organ execute the following steps of voting: establishing a Hough voting lookup table, searching in the lookup table by using the gradient direction index of the point, and calculating the position of a possible reference point; and adding 1 to the ticket number of the Hough space point corresponding to the possible reference point position. And after the whole voting process is finished, counting the number of votes obtained from all the points, and searching the peak value of the parameter space accumulator, namely the position, the scaling and the rotation with the maximum global number of votes, to initially position the liver in the image to be detected.
And each mark point searches for a pixel point with the minimum Euclidean distance from the texture feature of the current point along the normal vector direction to update, corrects parameters such as the shape of the tissue organ, the translation, the rotation and the zoom ratio of the texture variable model and the like, and realizes automatic marking according to the convergence of the parameters.
Constructing a pre-labeling model, taking the training set as the input of the pre-labeling model, obtaining a pre-labeling result, determining a cross-over ratio of the pre-labeling result, and obtaining a standard label classification result corresponding to the pre-labeling result based on the cross-over ratio;
determining label classification sample data based on the pre-labeling result and a standard label classification result corresponding to the pre-labeling result;
training an initial label classification model based on label classification sample data to obtain the target label classification model.
Obtaining the pre-labeling result, specifically, through sample pre-labeling information of a sample labeling image input by a user, and determining each sample pre-labeling result based on the sample pre-labeling information; or determining the pre-labeling result of each sample based on the pre-labeling result of the image to be labeled output by the pre-labeling model.
Constructing a target label classification model, taking the pre-labeling result as the input of the label classification model to obtain a label classification result, and obtaining a verification result corresponding to the label classification result based on the test set and the target label classification model;
and determining the labeling information corresponding to the image to be labeled based on the pre-labeling result, the label classification result and the verification result corresponding to the label classification result.
The method can also determine classification model optimization sample data based on the verification result, the label classification result and the pre-labeling result; and performing optimization iterative training on the pre-trained label classification model based on the classification model optimization sample data.
An automatic medical image annotation system under small sample condition, comprising:
the image acquisition module is used for acquiring an image to be annotated and acquiring an initial image data set by performing feature extraction on the image to be annotated;
the annotation processing module is connected with the image acquisition module and used for obtaining a pre-annotation result;
the label classification module is connected with the label processing module and used for obtaining a label classification result;
and the label generation module is connected with the label classification module and used for generating the label information of the image to be labeled according to the pre-labeling result and the label classification result.
The feature types of the feature extraction include: color histogram, block-by-block color moment, edge direction histogram, color correlation graph, facial features, wavelet texture, SIFT-based descriptor bag.
The system also comprises a storage module which is respectively connected with the image acquisition module, the annotation processing module, the label classification module and the annotation generation module and is used for storing the initial image data set, the pre-annotation result, the label classification result and the annotation information of the image to be annotated.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solutions of the present invention can be made by those skilled in the art without departing from the spirit of the present invention, and the technical solutions of the present invention are within the scope of the present invention defined by the claims.
Claims (10)
1. A medical image automatic labeling method under a small sample condition is characterized by comprising the following steps:
acquiring an image to be marked, extracting the characteristics of the image to be marked to obtain an initial image data set, and dividing the initial image data set into a training set and a test set according to the proportion;
constructing a pre-labeling model, and taking the training set as the input of the pre-labeling model to obtain a pre-labeling result;
constructing a target label classification model, and taking the pre-labeling result as the input of the target label classification model to obtain a label classification result;
and determining the labeling information of the image to be labeled based on the pre-labeling result and the label classification result.
2. The method for automatically labeling medical images under small sample condition according to claim 1,
the feature types of the feature extraction include: color histogram, block-by-block color moment, edge direction histogram, color correlation graph, facial features, wavelet texture, SIFT-based descriptor bag.
3. The method for automatically labeling medical images under small sample condition according to claim 1,
in the process of dividing the training set, a target shape mark point is obtained by constructing a dense linear regression model and a sparse linear regression model of the initial shape mark point, and a shape variable model is obtained based on the target shape mark point;
an affine transformation model of the initial shape marking region is built, the texture of the target shape marking region is obtained, and a variable texture model is obtained based on the texture of the target shape marking region;
and performing initial positioning through a Hough voting learning method based on the image to be labeled, and automatically labeling image contents according to the convergence of the translation parameter, the rotation parameter and the scaling parameter of the shape variable model and the texture variable model to obtain the training set.
4. The method for automatically labeling medical images under small sample condition according to claim 1,
the obtaining of the pre-labeling result further comprises the steps of determining a cross-over ratio of the pre-labeling result, and obtaining a standard label classification result corresponding to the pre-labeling result based on the cross-over ratio;
determining label classification sample data based on the pre-labeling result and a standard label classification result corresponding to the pre-labeling result;
training an initial label classification model based on the label classification sample data to obtain the target label classification model.
5. The method for automatically labeling medical images under small sample condition according to claim 1,
obtaining the pre-labeling result, namely, the pre-labeling result is determined according to the sample pre-labeling information of the sample labeling image input by the user; or, determining the pre-labeling result based on the pre-labeling result of the image to be labeled output by the pre-labeling model.
6. The method for automatically labeling medical images under small sample condition according to claim 1,
after obtaining the label classification result, the method further comprises: obtaining a verification result corresponding to the label classification result based on the test set and the target label classification model;
and determining the labeling information corresponding to the image to be labeled based on the pre-labeling result, the label classification result and the verification result corresponding to the label classification result.
7. The method for automatically labeling medical images under small sample condition according to claim 6,
further comprising: determining classification model optimization sample data based on the verification result, the label classification result and the pre-labeling result; and performing optimization iterative training on the target label classification model based on the classification model optimization sample data.
8. An automatic medical image labeling system under small sample condition, comprising:
the image acquisition module is used for acquiring an image to be annotated and acquiring an initial image data set by performing feature extraction on the image to be annotated;
the annotation processing module is connected with the image acquisition module and used for obtaining a pre-annotation result;
the label classification module is connected with the label processing module and used for obtaining a label classification result;
and the label generation module is connected with the label classification module and used for generating the label information of the image to be labeled according to the pre-labeling result and the label classification result.
9. The automatic medical image annotation system under small sample condition of claim 8,
the feature types of the feature extraction include: color histogram, block-by-block color moment, edge direction histogram, color correlation graph, facial features, wavelet texture, SIFT-based descriptor bag.
10. The automatic medical image annotation system under small sample condition of claim 8,
the system also comprises a storage module which is respectively connected with the image acquisition module, the annotation processing module, the label classification module and the annotation generation module and is used for storing the initial image data set, the pre-annotation result, the label classification result and the annotation information of the image to be annotated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110941761.7A CN113592029A (en) | 2021-08-17 | 2021-08-17 | Automatic medical image labeling method and system under small sample condition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110941761.7A CN113592029A (en) | 2021-08-17 | 2021-08-17 | Automatic medical image labeling method and system under small sample condition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113592029A true CN113592029A (en) | 2021-11-02 |
Family
ID=78258269
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110941761.7A Pending CN113592029A (en) | 2021-08-17 | 2021-08-17 | Automatic medical image labeling method and system under small sample condition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113592029A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116246756A (en) * | 2023-01-06 | 2023-06-09 | 北京医准智能科技有限公司 | Model updating method, device, electronic equipment and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103605667A (en) * | 2013-10-28 | 2014-02-26 | 中国计量学院 | Automatic image annotation algorithm |
CN105118068A (en) * | 2015-09-29 | 2015-12-02 | 常熟理工学院 | Medical image automatic annotation method under small sample condition |
CN112784879A (en) * | 2020-12-31 | 2021-05-11 | 前线智能科技(南京)有限公司 | Medical image segmentation or classification method based on small sample domain self-adaption |
CN112884060A (en) * | 2021-03-09 | 2021-06-01 | 联仁健康医疗大数据科技股份有限公司 | Image annotation method and device, electronic equipment and storage medium |
-
2021
- 2021-08-17 CN CN202110941761.7A patent/CN113592029A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103605667A (en) * | 2013-10-28 | 2014-02-26 | 中国计量学院 | Automatic image annotation algorithm |
CN105118068A (en) * | 2015-09-29 | 2015-12-02 | 常熟理工学院 | Medical image automatic annotation method under small sample condition |
CN112784879A (en) * | 2020-12-31 | 2021-05-11 | 前线智能科技(南京)有限公司 | Medical image segmentation or classification method based on small sample domain self-adaption |
CN112884060A (en) * | 2021-03-09 | 2021-06-01 | 联仁健康医疗大数据科技股份有限公司 | Image annotation method and device, electronic equipment and storage medium |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116246756A (en) * | 2023-01-06 | 2023-06-09 | 北京医准智能科技有限公司 | Model updating method, device, electronic equipment and medium |
CN116246756B (en) * | 2023-01-06 | 2023-12-22 | 浙江医准智能科技有限公司 | Model updating method, device, electronic equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Hill et al. | Model-based interpretation of 3d medical images. | |
US8379957B2 (en) | System and method for segmentation of anatomical structures in MRI volumes using graph cuts | |
Heimann et al. | Comparison and evaluation of methods for liver segmentation from CT datasets | |
Criminisi et al. | Decision forests with long-range spatial context for organ localization in CT volumes | |
Loog et al. | Segmentation of the posterior ribs in chest radiographs using iterated contextual pixel classification | |
US8538109B2 (en) | Method and system for dynamic pulmonary trunk modeling and intervention planning | |
US8494238B2 (en) | Redundant spatial ensemble for computer-aided detection and image understanding | |
CN112102237A (en) | Brain tumor recognition model training method and device based on semi-supervised learning | |
US20070058850A1 (en) | Method for automatic construction of 2d statistical shape model for the lung regions | |
CN112037200A (en) | Method for automatically identifying anatomical features and reconstructing model in medical image | |
JP2016533782A (en) | Method and system for characterizing images acquired by medical imaging equipment | |
WO2022042348A1 (en) | Medical image annotation method and apparatus, device, and storage medium | |
CN111080596A (en) | Auxiliary screening method and system for pneumoconiosis fusing local shadows and global features | |
CN111695431A (en) | Face recognition method, face recognition device, terminal equipment and storage medium | |
Ma et al. | Combining population and patient-specific characteristics for prostate segmentation on 3D CT images | |
CN104281856A (en) | Image preprocessing method and system for brain medical image classification | |
CN115035089A (en) | Brain anatomy structure positioning method suitable for two-dimensional brain image data | |
AU2021105831A4 (en) | Method for Automatically Noting Medical Image Under Small Samples and System Thereof | |
CN113592029A (en) | Automatic medical image labeling method and system under small sample condition | |
CN111128349A (en) | GAN-based medical image focus detection marking data enhancement method and device | |
CN112766314A (en) | Anatomical structure recognition method, electronic device, and storage medium | |
Xie et al. | Automatic neuron tracing in volumetric microscopy images with anisotropic path searching | |
CN111325282A (en) | Mammary gland X-ray image identification method and device suitable for multiple models | |
Broadhurst et al. | Histogram statistics of local model-relative image regions | |
CN116228660A (en) | Method and device for detecting abnormal parts of chest film |
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 |