用少量标注数据实现精准皮肤病变分割，提升边界识别能力。
Confidence-Weighted Semi-Supervised Learning for Skin Lesion Segmentation Using Hybrid CNN-Transformer Networks
- 通过教师-学生框架生成带置信度的伪标签，提高伪标签质量。
- 仅用50%标注数据即达Dice 0.9153、IoU 0.8552，优于传统方法。
- 适合标注数据稀缺的医学图像分割任务，尤其皮肤病变分析。
基于皮肤镜分析的自动皮肤病变分割对早期皮肤癌检测至关重要，但受限于标注数据少而难实现。本文提出MIRA-U半监督框架，结合不确定性感知的教师-学生伪标签机制与混合CNN-Transformer架构。教师网络通过掩码图像建模预训练，生成置信度加权的软伪标签，指导带有交叉注意力跳跃连接的U型CNN-Transformer学生网络。该设计显著提升伪标签质量与边界分割精度，在低标注场景下超越基于重建和纯CNN的基线方法。在ISIC-2016和PH2数据集上的大量实验表明，仅使用50%标注数据即可达到Dice相似性系数（DSC）0.9153、交并比（IoU）0.8552。代码已开源。
原文摘要 · Abstract (English)
Automated skin lesion segmentation through dermoscopic analysis is essential for early skin cancer detection, yet remains challenging due to limited annotated training data. We present MIRA-U, a semi-supervised framework that combines uncertainty-aware teacher-student pseudo-labeling with a hybrid CNN-Transformer architecture. Our approach employs a teacher network pre-trained via masked image modeling to generate confidence-weighted soft pseudo-labels, which guide a U-shaped CNN-Transformer student network featuring cross-attention skip connections. This design enhances pseudo-label quality and boundary delineation, surpassing reconstruction-based and CNN-only baselines, particularly in low-annotation regimes. Extensive evaluation on ISIC-2016 and PH2 datasets demonstrates superior performance, achieving a Dice Similarity Coefficient (DSC) of 0.9153 and Intersection over Union (IoU) of 0.8552 using only 50% labeled data. Code is publicly available on GitHub.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。