Robust Alzheimer's Progression Modeling using Cross-Domain Self-Supervised Deep Learning

TL;DR

This paper introduces a cross-domain self-supervised learning method that enhances Alzheimer's disease progression prediction from brain MRI, outperforming traditional pretraining approaches.

Contribution

It develops a novel self-supervised learning framework for medical imaging regression tasks, specifically improving Alzheimer's progression modeling using multiple data domains.

Findings

Self-supervised pretraining improves Alzheimer's progression prediction.

Pretraining on extended brain MRI data outperforms natural image pretraining.

Combining natural images and brain MRI data yields the best results.

Abstract

Developing successful artificial intelligence systems in practice depends on both robust deep learning models and large, high-quality data. However, acquiring and labeling data can be prohibitively expensive and time-consuming in many real-world applications, such as clinical disease models. Self-supervised learning has demonstrated great potential in increasing model accuracy and robustness in small data regimes. In addition, many clinical imaging and disease modeling applications rely heavily on regression of continuous quantities. However, the applicability of self-supervised learning for these medical-imaging regression tasks has not been extensively studied. In this study, we develop a cross-domain self-supervised learning approach for disease prognostic modeling as a regression problem using medical images as input. We demonstrate that self-supervised pretraining can improve the prediction of Alzheimer's Disease progression from brain MRI. We also show that pretraining on extended (but not labeled) brain MRI data outperforms pretraining on natural images. We further observe that the highest performance is achieved when both natural images and extended brain-MRI data are used for pretraining.