Fundus image segmentation model training method and device

Abstract

The invention provides a fundus image segmentation model training method and device. The method comprises the steps of obtaining a first segmentation model and a second segmentation model which are pre-trained; segmenting the fundus image in the training data by using the first segmentation model and the second segmentation model respectively, wherein the first segmentation model outputs first confidence information about the first target of interest, and the second segmentation model outputs second confidence information about the first target of interest and the second target of interest; obtaining integrated confidence information according to the first confidence information and the second confidence information; and optimizing parameters of the second segmentation model according to the integrated confidence information, a second confidence, the annotation data and a loss function constructed by a segmentation result determined by the second confidence.

Description

technical field [0001] The invention relates to the field of medical image detection, in particular to a method and equipment for training a fundus image segmentation model. 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. In terms of fundus image detection, most semantic segmentation tasks use end-to-end deep learning methods to achieve better results. Accurate boundary and position detection is very important for tracking the development of fundus image lesions, and pixel-by-pixel segmentation of lesions is an important task. A task with great medical application value. [0003] Existing technologies have been able to train machine learning models through a large number of fundus image data sets, so that they can accurately segment objects of interest in fundus images. ...

AI Technical Summary

Problems solved by technology

To this end, the producer needs to train a high-level model. According to the existing technology, the producer needs to use a large amount of new data to retrain the model. In the new training data, not only the original target of interest needs to be marked, but also the newly added target of interest needs to be marked. Target, this repetitive labeling work wastes manpower, and more types of interesting targets also increase the difficulty of labeling, if the amount of training data is small, it will affect the segmentation performance of the model

Images