CLEAR-HPV: Interpretable Concept Discovery for HPV-Associated Morphology in Whole-Slide Histologyhttps://arxiv.org/submit/7596892/preview

TL;DR

CLEAR-HPV introduces an interpretable framework for HPV-related histopathology that automatically discovers morphologic concepts and generates spatial maps without needing concept labels during training.

Contribution

It restructures MIL latent space using attention to enable concept discovery and interpretability in whole-slide histopathology without additional concept annotations.

Findings

Automatically discovers keratinizing, basaloid, and stromal concepts

Reduces high-dimensional features to 10 interpretable concepts

Generalizes across multiple cancer datasets

Abstract

Human papillomavirus (HPV) status is a critical determinant of prognosis and treatment response in head and neck and cervical cancers. Although attention-based multiple instance learning (MIL) achieves strong slide-level prediction for HPV-related whole-slide histopathology, it provides limited morphologic interpretability. To address this limitation, we introduce Concept-Level Explainable Attention-guided Representation for HPV (CLEAR-HPV), a framework that restructures the MIL latent space using attention to enable concept discovery without requiring concept labels during training. Operating in an attention-weighted latent space, CLEAR-HPV automatically discovers keratinizing, basaloid, and stromal morphologic concepts, generates spatial concept maps, and represents each slide using a compact concept-fraction vector. CLEAR-HPV's concept-fraction vectors preserve the predictive information of the original MIL embeddings while reducing the high-dimensional feature space (e.g., 1536 dimensions) to only 10 interpretable concepts. CLEAR-HPV generalizes consistently across TCGA-HNSCC, TCGA-CESC, and CPTAC-HNSCC, providing compact, concept-level interpretability through a general, backbone-agnostic framework for attention-based MIL models of whole-slide histopathology.