CN113012134A - Multifunctional medical image data labeling system - Google Patents
Multifunctional medical image data labeling system Download PDFInfo
- Publication number
- CN113012134A CN113012134A CN202110304639.9A CN202110304639A CN113012134A CN 113012134 A CN113012134 A CN 113012134A CN 202110304639 A CN202110304639 A CN 202110304639A CN 113012134 A CN113012134 A CN 113012134A
- Authority
- CN
- China
- Prior art keywords
- image
- labeling
- module
- region
- medical image
- 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
- 238000002372 labelling Methods 0.000 title claims abstract description 70
- 230000011218 segmentation Effects 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000009897 systematic effect Effects 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides a multifunctional medical image data annotation system, which comprises an image reading module, a data annotation module and an annotation data export module; the image reading module is used for reading various medical images; the data labeling module is used for labeling classified information of the medical image and labeling an interested region and a semantic information region; the label data export module is used for exporting the label file formed after the label information is added. The system can carry out multifunctional information labeling on the read medical image, including image classification labeling, image region-of-interest labeling and the like, thereby effectively improving the sorting capacity of the system on the medical image data.
Description
Technical Field
The invention relates to the technical field of data annotation, in particular to a multifunctional medical image data annotation system.
Background
Although the existing labeling platform can classify pictures and perform target recognition, text recognition and the like, the existing labeling platform cannot read medical images in various formats, has a very limited labeling function on the medical images, and cannot effectively arrange medical image data.
Disclosure of Invention
The invention aims to provide a multifunctional medical image data labeling system to solve the technical problems, so that medical image data can be effectively sorted.
In order to solve the above technical problem, an embodiment of the present invention provides a multifunctional medical image data annotation system, which includes an image reading module, a data annotation module, and an annotation data export module; the data labeling module comprises an image classification label module and an image interesting region labeling module;
the image reading module is used for reading the medical image; wherein the medical image comprises one or more of an MRI image, a CT image, an ultrasonic image and an RGB image;
the image classification label module is used for adding attribute category information to which the image belongs to the medical image;
the image region-of-interest labeling module is used for delineating a region of interest in the medical image and adding attribute type information of the region to the delineated region;
and the label data export module is used for exporting the label file formed after the label information is added.
Furthermore, the data labeling module further comprises an image semantic information segmentation labeling module, which is used for delineating a polygonal region of a semantic information region in the medical image and adding attribute category information of the delineated region.
Further, the image classification label module is specifically configured to identify an attribute category of the medical image, and add attribute category information to the medical image according to the identified attribute category.
Further, the image region-of-interest labeling module is specifically configured to circle a region of interest in the medical image in response to a circle instruction of a user, and add attribute type information to the region of interest according to a first labeling instruction of the user.
Further, the image semantic information segmentation and labeling module is specifically configured to perform polygon region delineation on the semantic information region in response to a selected instruction of a user, and add attribute category information to the semantic information region according to a second labeling instruction of the user.
Further, the figure of the region of interest is rectangular or circular.
The system further comprises an encoding module for encoding all the annotation information and the annotated position information to generate an annotation file.
Further, the format of the markup file is xml format or json format.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a multifunctional medical image data annotation system, which comprises an image reading module, a data annotation module and an annotation data export module; the data labeling module comprises an image classification label module, an image region-of-interest labeling module and an image semantic information segmentation labeling module; the image reading module is used for reading the medical image; the data labeling module is used for labeling classified information of the medical image and labeling an interested region and a semantic information region; the label data export module is used for exporting the label file formed after the label information is added. The system can carry out multifunctional information labeling on the read medical image, including image classification labeling, image region-of-interest labeling and the like, thereby effectively improving the sorting capacity of the system on the medical image data.
Drawings
Fig. 1 is a schematic structural diagram of a multifunctional medical image data labeling system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying 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.
Referring to fig. 1, an embodiment of the present invention provides a multifunctional medical image data annotation system, which includes an image reading module, a data annotation module, and an annotation data export module; the data labeling module comprises an image classification label module and an image interesting region labeling module;
the image reading module is used for reading the medical image; wherein the medical image comprises one or more of an MRI image, a CT image, an ultrasonic image and an RGB image; the method specifically realizes that the method can decode and read general image formats (jpg, png and bmp) and medical image formats (tif, tiff and dcm) simultaneously;
the image classification label module is used for adding attribute category information to which the image belongs to the medical image;
the image region-of-interest labeling module is used for delineating a region of interest in the medical image and adding attribute type information of the region to the delineated region; further, the frame selection graph of the region of interest is rectangular or circular;
and the label data export module is used for exporting the label file formed after the label information is added.
The video classification tag module is configured to assign tag information (attribute type information to which a video belongs) to a content attribute of a target video. The image interesting region labeling module is used for giving labeling information (attribute type information of a region) to a certain region (such as a rectangular region) occupied by a target in an image.
In the embodiment of the present invention, the data labeling module further includes an image semantic information segmentation labeling module, which is configured to perform polygon region delineation on a semantic information region in the medical image, and add attribute category information to the delineated region.
In an embodiment of the present invention, the image classification tag module is specifically configured to identify an attribute of the medical image, and add tag information to the medical image according to the identified attribute. Specifically, the image classification label module is used for performing classification labels on the content and the attributes of the same type of images and providing a data set for medical image data disease diagnosis classification, treatment classification and prognosis classification tasks based on supervised learning. Through the image classification label module, a user can add classification information labels of the images to the read medical images.
In the embodiment of the present invention, the image region-of-interest labeling module is specifically configured to circle a region of interest in the medical image in response to a circle instruction of a user, and add attribute type information to the region of interest according to a first labeling instruction of the user. Specifically, the image region-of-interest labeling module is used for enclosing a focus by using a rectangular frame in the same type of image, giving a content and an attribute label of the enclosed focus or region, and providing a data set for a medical image recognition task based on supervised learning. Through the image interesting region marking module, a user can circle the interesting region in a rectangular or circular shape and add a corresponding region label to the interesting region.
In the embodiment of the present invention, further, the image semantic information segmentation and labeling module is specifically configured to perform polygon region delineation on the semantic information region in response to a selected instruction of a user, and add attribute category information to the semantic information region according to a second labeling instruction of the user. Specifically, the image semantic information segmentation and labeling module is used for selecting pixel levels of regions such as focuses in the same type of images by using polygons and endowing the regions with content and attribute labels, so as to provide a data set for a medical image semantic segmentation task based on supervised learning. Through the image semantic information segmentation and labeling module, a user can define polygons for semantic information areas and add corresponding area labels to the areas.
It should be noted that the user can perform data labeling on the same medical image for multiple times at the same time, and can use multiple label categories.
In the embodiment of the present invention, further, the system further includes an encoding module, configured to encode all the annotation information and the annotated location information to generate an annotation file. Further, the format of the markup file is xml format or json format.
It should be noted that the system of the present invention can perform informatization processing and maintenance on the labeled information of different levels for the image, including the whole label of the medical image, the labeling of the region of interest in the medical image, and the labeling of semantic information in the medical image, and these three labels can be simultaneously applied to the same image if necessary. Through different labels of the medical image, the system integrates and codes all labels through a coding module, and stores all label information in the same xml or json format file, so that the label information can be provided for the supervised learning task of the medical image.
The system can be used by clinicians, is applied to a data set labeling link in a deep learning task, can label different information of a target image according to different requirements of the task in the deep learning, is beneficial to development of a medical image algorithm based on the deep learning, and can perform systematic maintenance and management on the data and the labeled information, so that the sustainability and maintainability of the deep learning execution task are realized.
Based on the above scheme, the following illustrates an application flow of the system of the present invention:
1. reading various medical images;
2. selecting labels of various medical image data;
3. labeling the image according to each labeling function;
4. and carrying out centralized coding to obtain the image labeling file.
Compared with the prior art, the invention has the following beneficial effects:
1. the multifunctional medical image reading device has the function of reading various medical image information, such as MRI images, CT images, ultrasonic images and RGB images. The application universality of the system is reflected.
2. The multifunctional labeling functional module comprises an image classification label module, an image region-of-interest labeling module and an image semantic information segmentation labeling module. The versatility of the system is embodied.
3. And the three label sets are coded in a file. The data sustainability and maintainability are embodied.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (8)
1. A multifunctional medical image data annotation system is characterized by comprising an image reading module, a data annotation module and an annotation data export module; the data labeling module comprises an image classification label module and an image interesting region labeling module;
the image reading module is used for reading the medical image; wherein the medical image comprises one or more of an MRI image, a CT image, an ultrasonic image and an RGB image;
the image classification label module is used for adding attribute category information to which the image belongs to the medical image;
the image region-of-interest labeling module is used for delineating a region of interest in the medical image and adding attribute type information of the region to the delineated region;
and the label data export module is used for exporting the label file formed after the label information is added.
2. The system according to claim 1, wherein the data labeling module further comprises an image semantic information segmentation labeling module for delineating a polygonal region from a semantic information region in the medical image and adding attribute class information of the delineated region.
3. The system according to claim 1, wherein the image classification label module is specifically configured to identify an attribute category of the medical image, and add attribute category information to the medical image according to the identified attribute category.
4. The system for labeling medical image data according to claim 1, wherein the image region-of-interest labeling module is specifically configured to circle a region of interest in the medical image in response to a user's delineation instruction, and add attribute type information to the region of interest according to a first labeling instruction of a user.
5. The system according to claim 2, wherein the image semantic information segmentation labeling module is configured to perform polygon region delineation on the semantic information region in response to a selected instruction of a user, and add attribute type information of the semantic information region according to a second labeling instruction of the user.
6. The system according to claim 4, wherein the figure of the region of interest is a rectangle or a circle.
7. The system for labeling medical image data according to any one of claims 1 to 6, further comprising a coding module for coding all labeling information and labeled position information to generate a labeling file.
8. The system for labeling medical image data as claimed in claim 7, wherein the format of the labeling file is xml format or json format.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110304639.9A CN113012134A (en) | 2021-03-22 | 2021-03-22 | Multifunctional medical image data labeling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110304639.9A CN113012134A (en) | 2021-03-22 | 2021-03-22 | Multifunctional medical image data labeling system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113012134A true CN113012134A (en) | 2021-06-22 |
Family
ID=76404700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110304639.9A Pending CN113012134A (en) | 2021-03-22 | 2021-03-22 | Multifunctional medical image data labeling system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113012134A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114240880A (en) * | 2021-12-16 | 2022-03-25 | 数坤(北京)网络科技股份有限公司 | Medical scanning data processing method and device, medical equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563123A (en) * | 2017-09-27 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for marking medical image |
| CN110675940A (en) * | 2019-08-01 | 2020-01-10 | 平安科技（深圳）有限公司 | Pathological image labeling method and device, computer equipment and storage medium |
| CN110993064A (en) * | 2019-11-05 | 2020-04-10 | 北京邮电大学 | Deep learning-oriented medical image labeling method and device |
| CN111933251A (en) * | 2020-06-24 | 2020-11-13 | 安徽影联云享医疗科技有限公司 | Medical image labeling method and system |
| CN111968729A (en) * | 2020-08-31 | 2020-11-20 | 深圳度影医疗科技有限公司 | Medical information labeling method, system, intelligent terminal and storage medium |
-
2021
- 2021-03-22 CN CN202110304639.9A patent/CN113012134A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563123A (en) * | 2017-09-27 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for marking medical image |
| CN110675940A (en) * | 2019-08-01 | 2020-01-10 | 平安科技（深圳）有限公司 | Pathological image labeling method and device, computer equipment and storage medium |
| CN110993064A (en) * | 2019-11-05 | 2020-04-10 | 北京邮电大学 | Deep learning-oriented medical image labeling method and device |
| CN111933251A (en) * | 2020-06-24 | 2020-11-13 | 安徽影联云享医疗科技有限公司 | Medical image labeling method and system |
| CN111968729A (en) * | 2020-08-31 | 2020-11-20 | 深圳度影医疗科技有限公司 | Medical information labeling method, system, intelligent terminal and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 曹玉红 等: "基于深度学习的医学影像分割研究综述", 《计算机应用》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114240880A (en) * | 2021-12-16 | 2022-03-25 | 数坤(北京)网络科技股份有限公司 | Medical scanning data processing method and device, medical equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10685462B2 (en) | Automatic data extraction from a digital image | |
| CN110232689A (en) | Semantic classes positions digital environment | |
| CN111932564B (en) | Picture identification method and device, electronic equipment and computer readable storage medium | |
| WO2021189913A1 (en) | Method and apparatus for target object segmentation in image, and electronic device and storage medium | |
| CN112380870A (en) | User intention analysis method and device, electronic equipment and computer storage medium | |
| Moon et al. | Deep learning-based method to recognize line objects and flow arrows from image-format piping and instrumentation diagrams for digitization | |
| CN111414916A (en) | Method and device for extracting and generating text content in image and readable storage medium | |
| CN111522979B (en) | Picture sorting recommendation method and device, electronic equipment and storage medium | |
| Lyu et al. | The early Japanese books reorganization by combining image processing and deep learning | |
| CN113012134A (en) | Multifunctional medical image data labeling system | |
| CN110766460A (en) | User portrait drawing method and device, storage medium and computer equipment | |
| Riaz et al. | Traffic anomaly prediction system using predictive network | |
| CN116311320B (en) | Training method of text image fusion layer, text image recognition method and device | |
| Ichihashi et al. | Estimating visibility of annotations for view management in spatial augmented reality based on machine-learning techniques | |
| CN112613367A (en) | Bill information text box acquisition method, system, equipment and storage medium | |
| CN116863116A (en) | Image recognition method, device, equipment and medium based on artificial intelligence | |
| CN114511569B (en) | Tumor marker-based medical image identification method, device, equipment and medium | |
| CN109190467A (en) | A kind of more object detecting methods, system, terminal and storage medium returned based on key point | |
| CN114943306A (en) | Intention classification method, device, equipment and storage medium | |
| CN113128496B (en) | Method, device and equipment for extracting structured data from image | |
| CN114237829A (en) | Data acquisition and processing method for power equipment | |
| CN113642291A (en) | Method, system, storage medium and terminal for constructing logical structure tree reported by listed companies | |
| CN112801016A (en) | Vote data statistical method, device, equipment and medium | |
| Jang et al. | Exposing digital image forgeries by detecting contextual abnormality using convolutional neural networks | |
| Ajala | Object Detection and Recognition Using YOLO: Detect and Recognize URL (s) in an Image Scene |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210622 |
|
| RJ01 | Rejection of invention patent application after publication |