光学精密工程2025，Vol.33Issue(4)：591-609,19.DOI:10.37188/OPE.20253304.0591
伪标签置信度调控结直肠癌病理图像半监督语义分割
Pseudo-label confidence regulates semi-supervised semantic segmentation of pathological images of colorectal cancer
摘要
Abstract
In order to improve the under-utilization of low-confidence pseudo-labels,the need to optimize the accuracy of high-confidence pseudo-labels and the imbalance of pseudo-label categories in the semi-su-pervised semantic segmentation task of colorectal cancer pathological images,this paper proposed a pseu-do-label confidence regulation method to achieve high-quality multi-class semi-supervised semantic seg-mentation of colorectal cancer pathological images.First,based on the semi-supervised semantic segmen-tation framework of the teacher-student model,we propose to embed class confidence regulation in the consistency regularization,and to enhance the certainty by removing the confusing classes in the low confi-dence pseudo-labels generated by the untrained teacher model,so as to increase the contribution rate of the low confidence pseudo-labels.Secondly,an operation paradigm of first screening and then refining the pseudo-tags generated by the teacher model after training is proposed.By refining the filtered high-confi-dence pseudo-tags based on conditional random fields,the problems of boundary ambiguity and lack of se-mantic information in high-confidence pseudo-tags are improved.Finally,in order to alleviate the category imbalance in pseudo-label data,an adaptive random cascade strong data enhancement method based on the classification number of pseudo-label is designed.Through the experimental verification of the self-built colorectal cancer pathological image dataset and the published multi-class pathological image dataset,the proposed method achieves 74.09%average segmentation accuracy of four categories of colorectal cancer pathological images,which is 6.43%higher than that of the benchmark network,and provides powerful algorithm support for semi-supervised semantic segmentation of colorectal cancer pathological images.关键词
结直肠癌病理图像/半监督语义分割/教师-学生模型/一致性正则化/条件随机场/数据增强Key words
colorectal cancer pathological images/semi-supervised semantic segmentation/teacher-stu-dent model/consistency regularization/conditional random fields/data augmentation分类
计算机与自动化引用本文复制引用
徐晗晗,张印辉,何自芬,刘珈岑,李振辉,吴琳,史本杰..伪标签置信度调控结直肠癌病理图像半监督语义分割[J].光学精密工程,2025,33(4):591-609,19.基金项目
国家自然科学基金(No.62061022,No.62171206) （No.62061022,No.62171206）
装备智能运用教育部重点实验室开放基金项目(No.AAIE-2023-0203) （No.AAIE-2023-0203）
