LENS-GRF：具有门控残差融合的置换不变病变证据网络用于痤疮严重程度分级与多评分者临床预言分析
LENS-GRF: Permutation-Invariant Lesion Evidence Network with Gated Residual Fusion for Acne Severity Grading and Multi-Rater Clinical Oracle Analysis
浏览论文内容
中文总结 AI 辅助
提出LENS-GRF框架，结合置换不变病变证据网络与门控残差融合，实现痤疮严重程度分级，在ACNE04上达95.89%准确率，并通过多评分者预言分析揭示域偏移与标注差异。
中文摘要 AI 辅助
自动痤疮严重程度分级需要同时考虑整个面部上下文和细粒度的病变证据。我们提出了LENS-GRF（具有Set-Transformer和门控残差融合的病变证据网络），这是一个可解释的多阶段框架，用于四类痤疮严重程度分级。该方法结合了自适应面部皮肤分割和全局Vision Transformer先验，以及一个置换不变的病变Set Transformer，该Transformer编码局部病变补丁和空间几何信息。门控残差融合自适应地控制局部残差贡献，并在门控为零时退化为全局预测。在ACNE04上，使用YOLOv11s的全自动LENS-GRF达到了80.82%的准确率；使用真实病变标注时，达到了95.89%±0.59%的准确率和0.9753的二次加权Kappa系数。一项数据完整性审计发现了15对跨分割重复图像，其中5对具有冲突的严重程度标签。在PLSBRACNE01完整队列（200名受试者，600个视图）的锁定零样本评估中，自动LENS-GRF达到了35.00%的准确率，而全局基线为42.50%。在用于三位皮肤科医生预言分析的148名受试者共同队列中，真实病变输入将最佳预言准确率提高到47.97%，而最高预言QWK为0.5799。成对预言一致性范围为49.32%至66.22%，突显了检测器域偏移、标注变异性和跨标准不匹配问题。
英文摘要
Automated acne severity grading requires both whole-face context and fine-grained lesion evidence. We propose LENS-GRF (Lesion Evidence Network with Set-Transformer and Gated Residual Fusion), an interpretable multi-stage framework for four-class acne severity grading. The method combines Adaptive Facial Skin Segmentation and a global Vision Transformer prior with a permutation-invariant Lesion Set Transformer that encodes localized lesion patches and spatial geometry. Gated Residual Fusion adaptively controls the local residual contribution and reduces to the global prediction when the gate is zero. On ACNE04, fully automated LENS-GRF with YOLOv11s achieved 80.82% accuracy; with ground-truth lesion annotations, it achieved 95.89% +/- 0.59% accuracy and a Quadratic Weighted Kappa of 0.9753. A data-integrity audit identified 15 cross-split duplicate image pairs, including five with conflicting severity labels. In locked zero-shot evaluation on the full PLSBRACNE01 cohort (200 subjects, 600 views), automated LENS-GRF achieved 35.00% accuracy versus 42.50% for the global baseline. On the 148-subject common cohort used for three-dermatologist oracle analysis, ground-truth lesion inputs increased the best oracle accuracy to 47.97%, while the highest oracle QWK was 0.5799. Pairwise oracle agreement ranged from 49.32% to 66.22%, highlighting detector domain shift, annotation variability, and cross-criterion mismatch.
发表机构
- International Islamic University Chittagong (IIUC)（国际伊斯兰大学吉大港分校）
- American International University-Bangladesh (AIUB)（美国国际大学孟加拉分校）
机构由 AI 辅助整理，请以论文原文为准。
