Neural network model training method and device and medical image processing system

Abstract

The invention relates to a neural network-based computer vision technology in the field of artificial intelligence. Specifically, the invention provides a neural network model training method and device for image processing, a medical image processing method using the neural network model, and a medical image processing system. The training method comprises: a training image set acquisition step of acquiring a training image set for training a neural network model, the training image set comprising unlabeled first-class training images; a first training step of training a neural network modelby using the first type of training images and a first loss function corresponding to the first type of training images; wherein the first loss function corresponds to the difference of prediction values of the neural network model for one image in the first type of training images and the interference image thereof. According to the training method provided by the invention, the non-standard training data is further utilized on the basis of utilizing the standard training data, so that the training cost is reduced, and the development cycle of a medical image processing system is accelerated.

Description

technical field [0001] The present disclosure relates to the field of artificial intelligence, and more specifically, the present disclosure relates to a training method and device for a neural network model for image processing, a medical image processing method using a neural network model, and a medical image processing system. Background technique [0002] Computer vision is a science that studies how to make machines "see". To put it further, it refers to using cameras and computers instead of human eyes to identify, track and measure targets, and further graphics processing, so that computer processing It becomes an image that is more suitable for human eyes to observe or sent to the instrument for detection. As a scientific discipline, computer vision studies related theories and technologies, trying to build artificial intelligence systems that can obtain information from images or multidimensional data. Computer vision technology usually includes image processing, ...

AI Technical Summary

Problems solved by technology

However, unlike the acquisition and annotation of general natural images, medical images are expensive to acquire and require doctors with professional knowledge to annotate, which makes the construction of training image sets difficult and costly

Images