用皮肤镜图像做无创分型，深度学习识别侵袭性基底细胞癌
Deep Learning for Biopsy-Free Subtyping of Basal Cell Carcinoma from Dermatoscopic Images
- 基于预训练视觉变压器，仅凭一张皮肤镜图分类
- 在1271张图像上达AUC 0.784，优于传统模型和医生水平
- 为无需活检的癌症分型提供新可能，适合临床辅助决策
基底细胞癌（BCC）占皮肤癌诊断近80%，其临床管理依赖组织病理亚型，侵袭性亚型需更激进治疗。当前亚型判定依赖皮肤活检，过程昂贵且创伤。本文首次探索仅用单张皮肤镜图像进行BCC亚型分类的深度学习方法。受限于数据量，采用先进的预训练视觉变压器（ViTs），该模型在少量标注数据下表现优异。通过重复分层k折交叉验证，在包含1271张不同BCC亚型的皮肤镜图像数据集上，ViTs实现AUC 0.784，显著优于标准卷积神经网络基线及既往人类医生表现，可有效区分侵袭性与非侵袭性亚型。初步结果表明，结合深度学习与皮肤镜可实现无活检的亚型分型，有助于优化治疗方案并改善患者预后。
原文摘要 · Abstract (English)
Basal Cell Carcinoma (BCC) is the most common type of skin cancer, accounting for nearly 80% of skin cancer di- agnoses. Its optimal clinical management is guided by the distinct histopathologic subtype, with aggressive variants requiring more drastic measures. In current clinical practice, subtyping relies on skin biopsies, a procedure both costly and invasive. In this paper, we conduct a preliminary investigation into using deep learning for BCC subtyping, solely from a single dermatoscopic image of the lesion. Given the limited data at our disposal, we employ pre-trained vision transformers (ViTs), a state-of-the-art family of models highly effective for challenging downstream tasks with limited labeled data. Through repeated stratified k-fold cross-validation, we demonstrate that ViTs can achieve superior performance (AUC 0.784 on a dataset of 1271 dermatoscopic images of various BCC subtypes) over standard CNN-based baselines as well as previously-reported human reader perfor- mance, on the task of differentiating aggressive BCCs from other subtype families. These initial findings highlight the potential of combining deep learning and dermatoscopy to provide a biopsy- free alternative for BCC subtyping, thus aiding in improving treatment planning and patient outcomes.
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。