MultiMix: Sparingly Supervised, Extreme Multitask Learning From Medical Images

TL;DR

MultiMix is a novel semi-supervised multitask learning model that jointly performs disease classification and anatomical segmentation on chest X-ray images, improving generalization with limited labeled data.

Contribution

It introduces a sparingly supervised multitask learning framework with explainability via bridge saliency, enhancing medical image analysis with minimal labeled data.

Findings

Effective in pneumonia classification and lung segmentation

Demonstrates strong generalization in cross-domain settings

Utilizes limited labeled data for high performance

Abstract

Semi-supervised learning via learning from limited quantities of labeled data has been investigated as an alternative to supervised counterparts. Maximizing knowledge gains from copious unlabeled data benefit semi-supervised learning settings. Moreover, learning multiple tasks within the same model further improves model generalizability. We propose a novel multitask learning model, namely MultiMix, which jointly learns disease classification and anatomical segmentation in a sparingly supervised manner, while preserving explainability through bridge saliency between the two tasks. Our extensive experimentation with varied quantities of labeled data in the training sets justify the effectiveness of our multitasking model for the classification of pneumonia and segmentation of lungs from chest X-ray images. Moreover, both in-domain and cross-domain evaluations across the tasks further showcase the potential of our model to adapt to challenging generalization scenarios.