Medical image annotation multi-version management method
A medical image, multi-version technology, applied in the field of medical image labeling, can solve the problems of low labeling efficiency, the version management system cannot check the revision progress of a specific version, and the labeling records are easy to lose, so as to avoid loss, improve image labeling efficiency, The effect of precise positioning
Pending Publication Date: 2022-02-01
ZHONGSHAN OPHTHALMIC CENT SUN YAT SEN UNIV +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The present invention provides a method for multi-version management of medical image annotation to solve the technical problems that the existing medical image annotation version management method is easy to lose the annotation records, the annotation efficiency is low, and the version management system cannot check the revision progress of a specific version
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0052] Please refer to figure 1 , a method for multi-version management of medical image annotation provided by an embodiment of the present invention, including:
[0053] S101: Receive a first medical image dataset uploaded by a first user; wherein, the first medical image dataset includes several medical images to be labeled.
[0054] S102: Perform full-process annotation processing on the first medical image data set, convert the data generated after each process node is completed into a tree object file, and store each tree object file in combination with the preset SHA-1 algorithm Calculate the address and file content, generate one or more hash values corresponding to each process node, and configure a corresponding version number for each hash value; among them, please refer to figure 2 , the whole process of labeling process includes the following process nodes: initial data storage node, labeling task division node, labeling result uploading node, labeling accepta...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a medical image annotation multi-version management method. The method comprises the following steps: receiving a first medical image data set uploaded by a first user; performing full-process labeling processing on the first medical image data set, converting data generated after each process node is completed into a tree object file, calculating a storage address and file content of each tree object file in combination with a preset SHA-1 algorithm, generating one or more hash values corresponding to each process node, and configuring a corresponding version number for each hash value; and performing version management on the first medical image data set according to an input operation instruction in combination with the hash value and the version number corresponding to each process node. According to the method, the medical image labeling process is stored, and any version in the labeling process can be traced back through the hash value serving as the unique identifier, so that the problem is accurately positioned, and loss of image labeling records is avoided.
Description
technical field [0001] The invention relates to the field of medical image labeling, in particular to a method for multi-version management of medical image labeling. Background technique [0002] In medicine, clinical diagnosis is not an intuitive judgment of the disease, but through the use of labeled medical images to obtain effective labeling data of lesions and related organs, combined with the doctor's initial diagnosis and the patient's inquiry information, to jointly judge the patient's condition. disease and its severity. Effectively labeled medical images provide doctors with important quantitative information in terms of disease diagnosis, condition assessment, development trend prediction, and treatment strategy formulation. [0003] At present, AI-assisted diagnosis retains a large number of data sets that are judged to be correctly labeled information as data evidence, and a large number of data sets that are judged to be wrongly labeled information are retain...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F16/51G06F16/55
CPCG06F16/51G06F16/55
Inventor 林浩添云东源刘力学吴晓航晏丕松
Owner ZHONGSHAN OPHTHALMIC CENT SUN YAT SEN UNIV