传感技术学报2026，Vol.39Issue(1)：73-79,7.DOI:10.3969/j.issn.1004-1699.2026.01.010
一种心脏MRI图像半监督学习语义分割算法
A Semi-Supervised Learning Semantic Segmentation Algorithm for Cardiac MRI Images
摘要
Abstract
Due to the scarcity of medical image data and the difficulty to obtain labeled data,a semantic segmentation method for semi-supervised learning based on contrastive learning and hard sample recall loss is proposed,as well as a non-intrusive target regions cutout(NTRC)data enhancement algorithm.By designing the hard sample recall loss function,correcting the global error of binary cross entro-py loss function(BCE)and imbalance contrastive loss function(ICLF),the model is guided to find the optimal solution better.Mean-while,the NTRC data enhancement algorithm is used to enhance the data so that the area to be segmented is not invaded and damaged.This algorithm is used for semi-supervised learning semantic segmentation of cardiac MRI images.The results show that the algorithm solves the problem of the imbalance of positive and negative samples and the low accuracy of hard sample segmentation,and generally improves the performance of the semi-supervised semantic segmentation algorithm of cardiac MRI images.关键词
医学图像分割/半监督学习/对比学习/难样本学习/召回损失/数据增强Key words
medical image segmentation/semi-supervised learning/contrastive learning/hard sample learning/recall loss/data enhancement分类
信息技术与安全科学引用本文复制引用
邹贵春,朱恩嵘,吴佳芸,胡晓飞..一种心脏MRI图像半监督学习语义分割算法[J].传感技术学报,2026,39(1):73-79,7.基金项目
国家自然科学基金项目(61771251) （61771251）
江苏省自然科学基金项目(BK20171443) （BK20171443）
