基于自反馈阈值学习的半监督皮肤癌诊断模型  

Semi-supervised skin cancer diagnosis based onself-feedback threshold learning

作　　者：韩硕[1] 袁伟珵 杜泽宇 HAN Shuo;YUAN Weicheng;DU Zeyu(College of Basic Medicine,Hebei Medical University,Shijiazhuang 050017,China;School of Health Science,University of Manchester,Manchester M139PL,UK)

机构地区：[1]河北医科大学基础医学院,河北石家庄050017 [2]曼彻斯特大学健康科学学院,英格兰曼彻斯特M139PL

出　　处：《河北大学学报（自然科学版）》2024年第4期441-448,共8页Journal of Hebei University(Natural Science Edition)

基　　金：河北省自然科学基金资助项目(H2019206316)。

摘　　要：为解决监督学习皮肤癌诊断模型的训练需要大量数据标注,且医学专家标注工作成本高、耗时长、易疲劳等问题,提出了一种基于自反馈阈值学习(Self-Feedback Threshold Learning,SFTL)的半监督皮肤癌诊断方法.在标注数据预训练的ResNet网络基础上,引入全局和局部类别间伪标签自反馈阈值学习机制动态筛选ResNet预测概率大于自反馈阈值的无标记样本,引入无监督阈值学习损失和分类交叉熵损失进行模型训练,在标记样本稀缺的情况下深入挖掘无标记数据的鉴别诊断信息,显著降低模型在无标记皮肤病变图像中的误判率.选取公开数据集HAM10000的皮肤病变图像展开实验验证,在仅需50%标记数据下实现了0.8229的准确率和0.7651的F1分数,证明所提出的SFTL模型在半监督场景下可有效解决皮肤癌诊断任务,相比其他同类方法具有更好的分类性能.To address the challenges associated with the need for a large amount of annotated data in supervised skin cancer diagnosis models,such as the high cost,time consumption,and fatigue experienced by medical experts during annotation,this study proposes a semi-supervised skin cancer diagnosis method based on Self-Feedback Threshold Learning(SFTL).Building upon the ResNet network pre-trained with labeled data,a global and local class pseudo-label self-feedback threshold learning mechanism is introduced to dynamically select unlabeled samples with ResNet prediction probabilities exceeding the self-feedback threshold.Unsupervised threshold learning loss and classification cross-entropy loss are incorporated for model training,thereby deeply mining the diagnostic information from unlabeled data when labeled samples are scarce and significantly reducing the misdiagnosis rate in unlabeled skin lesion images.Experimental validation was conducted using the publicly available HAM10000 skin lesion dataset,achieving an accuracy of 0.8229 and an F1 score of 0.7651 with only 50%of the data labeled.The results demonstrate that the proposed SFTL model effectively addresses the skin cancer diagnosis task in semi-supervised scenarios and outperforms other compared methods in terms of classification performance.

关 键 词：半监督皮肤癌诊断 自反馈阈值学习 卷积神经网络 半监督学习 

分 类 号：U492.2[交通运输工程—交通运输规划与管理] TP301.6[交通运输工程—道路与铁道工程]