INTERACT-CMIL: Multi-Task Shared Learning and Inter-Task Consistency for Conjunctival Melanocytic Intraepithelial Lesion Grading
This work addresses the challenge of accurate CMIL grading for ocular pathology diagnosis, offering a reproducible computational benchmark, though it appears to be an incremental improvement over existing deep learning approaches.
The researchers tackled the difficult problem of grading Conjunctival Melanocytic Intraepithelial Lesions (CMIL) by developing INTERACT-CMIL, a multi-head deep learning framework that jointly predicts five histopathological axes, achieving relative macro F1 gains up to 55.1% for WHO4 and 25.0% for vertical spread over baseline methods.
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.