Enhanced MRI Representation via Cross-series Masking

TL;DR

This paper introduces a self-supervised Cross-Series Masking strategy to improve MRI representations by effectively integrating multi-series data, leading to enhanced performance in various medical imaging tasks.

Contribution

The novel CSM strategy enables self-supervised learning of MRI representations by masking and reconstructing across series, improving downstream task accuracy.

Findings

Achieves state-of-the-art results on multiple datasets.

Effectively models intra- and inter-series correlations.

Enhances downstream segmentation and classification tasks.

Abstract

Magnetic resonance imaging (MRI) is indispensable for diagnosing and planning treatment in various medical conditions due to its ability to produce multi-series images that reveal different tissue characteristics. However, integrating these diverse series to form a coherent analysis presents significant challenges, such as differing spatial resolutions and contrast patterns meanwhile requiring extensive annotated data, which is scarce in clinical practice. Due to these issues, we introduce a novel Cross-Series Masking (CSM) Strategy for effectively learning MRI representation in a self-supervised manner. Specifically, CSM commences by randomly sampling a subset of regions and series, which are then strategically masked. In the training process, the cross-series representation is learned by utilizing the unmasked data to reconstruct the masked portions. This process not only integrates information across different series but also facilitates the ability to model both intra-series and inter-series correlations and complementarities. With the learned representation, the downstream tasks like segmentation and classification are also enhanced. Taking brain tissue segmentation, breast tumor benign/malignant classification, and prostate cancer diagnosis as examples, our method achieves state-of-the-art performance on both public and in-house datasets.