Any-to-Any Learning in Computational Pathology via Triplet Multimodal Pretraining

TL;DR

ALTER is a flexible, modality-adaptive pretraining framework for computational pathology that integrates multiple data types, enabling robust cross-modal representations and improved performance across diverse clinical tasks.

Contribution

It introduces a novel tripodal pretraining method that handles any subset of modalities, addressing heterogeneity, missing data, and task diversity in computational pathology.

Findings

Achieves superior performance in survival prediction and cancer subtyping.

Effectively handles missing modalities during inference.

Demonstrates robust cross-modal representation learning.

Abstract

Recent advances in computational pathology and artificial intelligence have significantly enhanced the utilization of gigapixel whole-slide images and and additional modalities (e.g., genomics) for pathological diagnosis. Although deep learning has demonstrated strong potential in pathology, several key challenges persist: (1) fusing heterogeneous data types requires sophisticated strategies beyond simple concatenation due to high computational costs; (2) common scenarios of missing modalities necessitate flexible strategies that allow the model to learn robustly in the absence of certain modalities; (3) the downstream tasks in CPath are diverse, ranging from unimodal to multimodal, cnecessitating a unified model capable of handling all modalities. To address these challenges, we propose ALTER, an any-to-any tri-modal pretraining framework that integrates WSIs, genomics, and pathology reports. The term "any" emphasizes ALTER's modality-adaptive design, enabling flexible pretraining with any subset of modalities, and its capacity to learn robust, cross-modal representations beyond WSI-centric approaches. We evaluate ALTER across extensive clinical tasks including survival prediction, cancer subtyping, gene mutation prediction, and report generation, achieving superior or comparable performance to state-of-the-art baselines.