arXiv · cs.AI · Muhammad Muhtasim Shahriar, M. F. Mridha, Md. Rakibul Islam2026-11-03 13:00 · 11 小时前模型评分31

LENS-GRF：面向痤疮严重度分级与多标注者临床分析的门控残差融合病灶证据网络

LENS-GRF: Permutation-Invariant Lesion Evidence Network with Gated Residual Fusion for Acne Severity Grading and Multi-Rater Clinical Oracle Analysis

导读

LENS-GRF 将全局 Vision Transformer 与 YOLO11s 提取的病灶区域嵌入向量结合，在 ACNE04 留出集上实现 80.82% 的四分类准确率，但未经外部适配在 PLSBRACNE01 队列上仅 35.00%，低于独立训练的全局基线 42.50%。

分类置信度

中 · 待人工复核

来源级别：媒体与个人

应用领域：医疗与生命科学

事件类型：研究发布

证据摘录

“We evaluated LENS-GRF, a lesion evidence network with permutation-invariant aggregation and gated residual fusion that combines a global Vision Transformer with lesion-region embeddings derived from YOLO11s proposals.”
“Fully automated four-class grading was evaluated on 292 held-out ACNE04 images and, without external adaptation, on 200 PLSBRACNE01 participants represented by 600 facial views.”
“Annotation-assisted inference used registered lesion boxes from three dermatologists in a matched subset of 148 participants.”

来源：arXiv · cs.AI · arxiv.org