paper-with-me

홈 › Papers

INTERACT-CMIL: Multi-Task Shared Learning and Inter-Task Consistency for Conjunctival Melanocytic Intraepithelial Lesion Grading

2025-12-27 · Mert Ikinci, Luna Toma, Karin U. Loeffler, Leticia Ussem, Daniela Süsskind, Julia M. Weller, Yousef Yeganeh, Martina C. Herwig-Carl, Shadi Albarqouni arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.22666

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SCMIL: Sparse Context-aware Multiple Instance Learning for Predicting Cancer Survival Probability Distribution in Whole Slide Images

2024-06-30 · Zekang Yang, Hong Liu, Xiangdong Wang

Cancer survival prediction is a challenging task that involves analyzing of the tumor microenvironment within Whole Slide Image (WSI). Previous methods cannot effectively capture the intricate interaction features among …

Multiple Instance LearningPredictionSurvival Predictionwhole slide images

PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysis

2025-07-24 · Beidi Zhao, SangMook Kim, Hao Chen, Chen Zhou 외 arxiv

Multiple Instance Learning (MIL) has advanced WSI analysis but struggles with the complexity and heterogeneity of WSIs. Existing MIL methods face challenges in aggregating diverse patch information into robust WSI repres…

Multiple Instance Learning

LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning

2023-07-30 · Tiezhu Sun, Weiguo Pian, Nadia Daoudi, Kevin Allix 외

Transfomer-based models have significantly advanced natural language processing, in particular the performance in text classification tasks. Nevertheless, these models face challenges in processing large files, primarily…

Android Malware DetectionClassificationDefect DetectionDocument Classification+7

DCMIL: A Progressive Representation Learning of Whole Slide Images for Cancer Prognosis Analysis

2025-10-16 · Chao Tu, Kun Huang, Jie Zhang, Qianjin Feng 외 arxiv

The burgeoning discipline of computational pathology shows promise in harnessing whole slide images (WSIs) to quantify morphological heterogeneity and develop objective prognostic modes for human cancers. However, progre…

Representation Learning

Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification

2023-11-13 · Yunlong Zhang, Honglin Li, Yuxuan Sun, Sunyi Zheng 외

In the application of Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) classification, attention mechanisms often focus on a subset of discriminative instances, which are closely linked to overfitting…

image-classificationImage ClassificationMultiple Instance Learning