Multi-task Learning of Histology and Molecular Markers for Classifying Diffuse Glioma

TL;DR

This paper introduces a hierarchical multi-task learning framework that jointly predicts histology features and molecular markers for diffuse glioma classification, effectively modeling their interactions to improve diagnostic accuracy.

Contribution

It presents a novel multi-task multi-instance learning approach with a co-occurrence graph and interaction strategy, advancing digital pathology diagnostics.

Findings

Outperforms state-of-the-art methods in diffuse glioma classification

Effectively models co-occurrence of molecular markers

Improves accuracy in histology and molecular marker prediction

Abstract

Most recently, the pathology diagnosis of cancer is shifting to integrating molecular makers with histology features. It is a urgent need for digital pathology methods to effectively integrate molecular markers with histology, which could lead to more accurate diagnosis in the real world scenarios. This paper presents a first attempt to jointly predict molecular markers and histology features and model their interactions for classifying diffuse glioma bases on whole slide images. Specifically, we propose a hierarchical multi-task multi-instance learning framework to jointly predict histology and molecular markers. Moreover, we propose a co-occurrence probability-based label correction graph network to model the co-occurrence of molecular markers. Lastly, we design an inter-omic interaction strategy with the dynamical confidence constraint loss to model the interactions of histology and molecular markers. Our experiments show that our method outperforms other state-of-the-art methods in classifying diffuse glioma,as well as related histology and molecular markers on a multi-institutional dataset.