Joint Prediction of Meningioma Grade and Brain Invasion via Task-Aware Contrastive Learning

TL;DR

This paper introduces a novel task-aware contrastive learning method that jointly predicts meningioma grade and brain invasion from multi-modal MRIs, improving accuracy over existing multi-task approaches.

Contribution

It proposes a contrastive learning framework that disentangles task-specific and common features for better joint prediction of meningioma characteristics.

Findings

Achieved AUCs of 0.8870 for tumor grade prediction.

Achieved AUCs of 0.9787 for brain invasion prediction.

Outperformed existing multi-task learning methods.

Abstract

Preoperative and noninvasive prediction of the meningioma grade is important in clinical practice, as it directly influences the clinical decision making. What's more, brain invasion in meningioma (i.e., the presence of tumor tissue within the adjacent brain tissue) is an independent criterion for the grading of meningioma and influences the treatment strategy. Although efforts have been reported to address these two tasks, most of them rely on hand-crafted features and there is no attempt to exploit the two prediction tasks simultaneously. In this paper, we propose a novel task-aware contrastive learning algorithm to jointly predict meningioma grade and brain invasion from multi-modal MRIs. Based on the basic multi-task learning framework, our key idea is to adopt contrastive learning strategy to disentangle the image features into task-specific features and task-common features, and explicitly leverage their inherent connections to improve feature representation for the two prediction tasks. In this retrospective study, an MRI dataset was collected, for which 800 patients (containing 148 high-grade, 62 invasion) were diagnosed with meningioma by pathological analysis. Experimental results show that the proposed algorithm outperforms alternative multi-task learning methods, achieving AUCs of 0:8870 and 0:9787 for the prediction of meningioma grade and brain invasion, respectively. The code is available at https://github.com/IsDling/predictTCL.