Medical image analysis method, device, electronic equipment and readable storage medium

Abstract

The present invention relates to artificial intelligence, and discloses a method for analyzing medical images, including: using a pre-built disease history picture set to train a pre-built deep learning network model to obtain a disease identification model; constructing a disease identification model based on the disease identification model and the pre-built initial diagnosis model Distillation loss function; perform distillation training on the initial diagnostic model according to the distillation loss function to obtain the first diagnostic model; perform training and output adjustment on the first diagnostic model according to the preset diagnostic target to obtain the target diagnostic model; when receiving the medical In the case of image images, the target diagnostic model is used to analyze the medical image images to be analyzed, and the analysis results are obtained. The present invention also relates to a block chain technology, and the data of the training model can be stored in the block chain. The invention also proposes a medical image analysis device, electronic equipment and a computer-readable storage medium. The invention can reduce the model calculation resource consumption of medical image analysis.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a medical image analysis method, device, electronic equipment and readable storage medium. Background technique [0002] With the development of artificial intelligence, it has become more and more common to use the medical image analysis model based on deep learning model training to analyze medical image pictures to assist in disease diagnosis. However, training deep learning models usually requires a high hardware threshold and cannot Migrate to mobile terminals or places where computing resources are scarce. If you directly train a lightweight model, not only the feature extraction ability is weak, but also the accuracy is low. Therefore, a medical image that maintains high accuracy and does not require too many computing resources is required. Image analysis methods. Contents of the invention [0003] The present invention provides a medical image analysis method, d...

AI Technical Summary

Problems solved by technology

[0002] With the development of artificial intelligence, it has become more and more common to use the medical image analysis model based on deep learning model training to analyze medical image pictures to assist in disease diagnosis. However, training deep learning models usually requires a high hardware threshold and cannot Migrate to mobile terminals or places where computing resources are scarce. If you directly train a lightweight model, not only the feature extraction ability is weak, but also the accuracy is low. Therefore, a medical image that maintains high accuracy and does not require too many computing resources is required. Image Analysis Method

Images