Segmentation model training method, device and computer-readable storage medium

Abstract

The present invention provides a segmentation model training method, device and computer-readable storage medium. The method includes: inputting the collected cardiac CT images into a deep learning network model for training, and obtaining the first segmentation results of each cardiac CT image, based on reinforcement learning The method is to fine-tune the first segmentation result according to the position information of the ventricle and the first segmentation result to obtain the second segmentation result, and iteratively train the deep learning network model according to the second segmentation result and the above-mentioned ventricle position information, and the trained A deep learning network model serves as a segmentation model for segmenting cardiac myocardium. By using cardiac CT images and the ventricle position information of each cardiac CT image as training data to train the deep learning network model, it is possible to obtain a segmentation model that can automatically segment cardiac CT images into ventricles, and further combine reinforcement learning methods. Fine-tuning and iterative training can obtain a segmentation model with higher segmentation accuracy.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a segmentation model training method, device and computer-readable storage medium. Background technique [0002] Cardiovascular disease is a serious threat to human life and health. Early quantitative diagnosis and risk assessment of cardiovascular disease play a key role in prolonging human life and health. With the rapid development of science and technology, the functions and imaging quality of imaging diagnostic equipment have been greatly improved. In particular, the rapid development of computed tomography (Computed Tomography, CT) technology continues to affect the diagnosis of human diseases, and has gradually become an important diagnostic method for heart examination. The ventricle area is the core area of ​​the heart and has always been the focus of heart disease research. It is very meaningful to study heart tissue, especially the left ventricle, wit...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a segmentation model training method, aiming to solve the technical problem of lack of tools capable of automatically performing ventricular myocardium segmentation in the prior art

Images