无需精细腺体标注，用眼皮轮廓和临床数据实现跨设备睑板腺分割。
TopoPult-SSL: Gland-Mask-Free Cross-Device Meibomian Gland Segmentation via Self-Distilled Weak Clinical Priors
- 利用眼皮轮廓和临床指标做弱监督，无须腺体掩码训练
- 最终模型Dice达0.716，优于现有方法且单次推理完成
- 适合缺乏标注资源的临床部署，尤其适用于新设备迁移
每台新临床成像设备都会带来领域偏移问题：密集的腺体掩码成本高昂，而眼皮轮廓、Pult分级、形态比值等临床信号却可轻易获取。本文提出TopoPult-SSL，一种两阶段跨设备睑板腺分割框架。第一阶段在无目标腺体掩码情况下，仅使用目标眼皮掩码与临床元数据，通过四个弱先验锚点适配源模型。第二阶段在获得目标腺体掩码后，通过自监督蒸馏将多教师模型融合为一个紧凑学生模型。在公开数据集MGD-1k到CAMG（1000 vs. 100张图像，不同设备）上验证，蒸馏模型取得0.716±0.006的Dice分数（最高0.726），优于UA-MT（0.710）和教师集成（0.720）。无腺体掩码的阶段一版本精确率0.694，显著高于SAM/MedSAM的0.30–0.34（p<0.001），支持无需精细标注的部署。代码与可复现脚本已公开。
原文摘要 · Abstract (English)
Every new clinical imaging device creates a domain shift where dense gland masks are expensive yet cheap clinical signals -- eyelid outlines, Pult grades, morphometric ratios -- are routinely recorded. We present TopoPult-SSL, a two-stage framework for cross-device meibomian gland segmentation. Stage 1 adapts a source-trained model without target gland masks in the training loss, using four weak-prior anchors driven by target eyelid masks and clinical metadata only. Stage 2, when target gland masks are available, distils complementary Stage-1 teachers into a single compact student via supervised self-distillation. We develop and validate the technique on the public MGD-1k to CAMG research benchmark (1,000 to 100 images, different device), where the distilled model achieves Dice 0.716+/-0.006 (best 0.726), surpassing UA-MT (0.710) and the ensemble teacher (0.720) -- with a single pass. The gland-mask-free Stage-1 variant reaches Precision 0.694 vs. 0.30-0.34 for SAM/MedSAM (p<0.001), enabling deployment without dense gland contouring. Code and reproducibility scripts are released.
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。