Medical image labeling method and system

Abstract

The invention discloses a medical image labeling method and system, and belongs to the technical field of medical image labeling. The method comprises: acquiring medical image data; carrying out character labeling according to a medical image knowledge graph; carrying out semantic segmentation on the image data by using a Mask R-CNN network model, and segmenting and hiding ribs and clavicle from the image; identifying the focus position and the non-focus position by using a Markov random field model, performing image annotation, annotating the focus position, the attribute information of the focus, the non-focus position and the attribute information of the non-focus in the image, and establishing association between the corresponding image annotation and the character annotation; and finally visualizing the character annotation and the image annotation, and confirming the character annotation and the image annotation through human-computer interaction. According to the invention, themedical image data can be subjected to character annotation and image annotation, the annotation speed is high, the accuracy is high, the film reading efficiency of doctors is effectively improved, and therefore disease diagnosis can be rapidly conducted.

Description

technical field [0001] The invention belongs to the technical field of medical image labeling, and in particular relates to a medical image labeling method and system. Background technique [0002] With the widespread use of various imaging technologies and equipment in hospitals, a large amount of medical imaging data is generated every day, forming medical imaging big data. These image big data contain the basic information of the patient and the relevant inspection and diagnosis information of the lesion, which is the necessary basis for the diagnosis of the disease. How to extract useful information from images and assist clinicians to improve diagnostic accuracy and work efficiency is an urgent problem to be solved. In order to solve this problem, some medical image labeling methods have been designed in the prior art, and corresponding medical image labeling systems have been developed to assist doctors in medical image labeling. [0003] Medical imaging data include...

AI Technical Summary

Problems solved by technology

[0005] Technical problem: Aiming at the problems of inaccuracy and low efficiency in medical image labeling in the prior art, the present invention provides a medical image labeling method and system, which can perform text labeling and image labeling on medical images, with high labeling accuracy, and at the same time Has a high labeling efficiency

Images