Medical image focus segmentation labeling method and system

Abstract

The embodiment of the invention provides a medical image focus segmentation labeling method and system, and relates to the technical field of medical image labeling. The method comprises the followingsteps: allocating a medical image to an annotator according to an annotation application sent by the annotator, so that the annotator performs lesion edge segmentation annotation and lesion categoryannotation on the allocated medical image; wherein one medical image is at least distributed to two annotators; when labeling results of the medical images uploaded by all labeling persons allocated to one medical image are received, whether all the received labeling results of the medical images meet a preset consistency requirement or not is judged; when all the labeling results of the medical image meet the preset consistency requirement, all the labeling results of the medical image are stored, and otherwise, all the labeling results of the medical image are returned to each labeling person. According to the method, the accuracy and consistency of the medical image focus segmentation labeling result are ensured through cross validation of the multi-person segmentation labeling result.

Description

technical field [0001] The invention relates to the technical field of medical image labeling, in particular to a method and system for segmentation and labeling of medical image lesions. Background technique [0002] In recent years, machine learning technology has been widely used in the medical field, especially machine learning technology represented by deep learning has attracted widespread attention in the field of medical imaging. The fully trained deep learning algorithm model has reached or even surpassed the level of ordinary human outpatient doctors in the classification and recognition performance of certain single diseases. However, this has not yet fully realized the full potential of deep learning technology. Current deep learning techniques include classification, detection, segmentation and other subdivisions. The segmentation algorithm can achieve pixel-level classification, not only can give coarse-grained classification results, but also can give accura...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method and system for segmentation and labeling of medical image lesions, which solves the problems in the prior art that the segmentation of medical image lesions through the labeling of a single doctor has a lot of noise and low accuracy

Images