多任务学习框架提升眼结膜黑素病变分级准确性
INTERACT-CMIL: Multi-Task Shared Learning and Inter-Task Consistency for Conjunctival Melanocytic Intraepithelial Lesion Grading
- 共享特征学习+跨任务一致性损失，联合预测五项病理指标
- 相对基线模型最高提升55.1%的宏F1分数（WHO4）
- 适合眼科病理数字化诊断与临床辅助决策系统研究者
准确评估结膜黑素细胞内皮病变（CMIL）对治疗和黑色素瘤预测至关重要，但因形态学特征细微且诊断标准相互关联而困难。本文提出INTERACT-CMIL，一种多头深度学习框架，通过组合部分监督的共享特征学习和跨任务一致性损失，联合预测五个组织病理学维度：WHO4、WHO5、水平扩散、垂直扩散和细胞学异型性。在来自三家大学医院的486个专家标注的结膜活检图像块构成的新多中心数据集上训练与评估，该框架显著优于传统CNN和基础模型（FM）基线，在WHO4任务上相对宏F1提升达55.1%，垂直扩散任务提升25.0%。模型输出与专家分级高度一致，具备可解释性，为CMIL诊断提供可复现的计算基准，推动眼部病理学数字化标准化进程。
原文摘要 · Abstract (English)
Accurate grading of Conjunctival Melanocytic Intraepithelial Lesions (CMIL) is essential for treatment and melanoma prediction but remains difficult due to subtle morphological cues and interrelated diagnostic criteria. We introduce INTERACT-CMIL, a multi-head deep learning framework that jointly predicts five histopathological axes; WHO4, WHO5, horizontal spread, vertical spread, and cytologic atypia, through Shared Feature Learning with Combinatorial Partial Supervision and an Inter-Dependence Loss enforcing cross-task consistency. Trained and evaluated on a newly curated, multi-center dataset of 486 expert-annotated conjunctival biopsy patches from three university hospitals, INTERACT-CMIL achieves consistent improvements over CNN and foundation-model (FM) baselines, with relative macro F1 gains up to 55.1% (WHO4) and 25.0% (vertical spread). The framework provides coherent, interpretable multi-criteria predictions aligned with expert grading, offering a reproducible computational benchmark for CMIL diagnosis and a step toward standardized digital ocular pathology.
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。