Clinical Inspired MRI Lesion Segmentation

TL;DR

This paper introduces a clinically inspired residual fusion method that adaptively combines pre- and post-contrast MRI features at multiple resolutions, improving lesion segmentation accuracy across different datasets.

Contribution

The paper presents a novel residual fusion approach that learns subsequence representations for MRI lesion segmentation, inspired by clinical practices, and achieves state-of-the-art results.

Findings

State-of-the-art performance on BraTS2023 brain tumor dataset.

Effective fusion of pre- and post-contrast MRI features.

Potential to improve lesion segmentation in various clinical applications.

Abstract

Magnetic resonance imaging (MRI) is a potent diagnostic tool for detecting pathological tissues in various diseases. Different MRI sequences have different contrast mechanisms and sensitivities for different types of lesions, which pose challenges to accurate and consistent lesion segmentation. In clinical practice, radiologists commonly use the sub-sequence feature, i.e. the difference between post contrast-enhanced T1-weighted (post) and pre-contrast-enhanced (pre) sequences, to locate lesions. Inspired by this, we propose a residual fusion method to learn subsequence representation for MRI lesion segmentation. Specifically, we iteratively and adaptively fuse features from pre- and post-contrast sequences at multiple resolutions, using dynamic weights to achieve optimal fusion and address diverse lesion enhancement patterns. Our method achieves state-of-the-art performances on BraTS2023 dataset for brain tumor segmentation and our in-house breast MRI dataset for breast lesion segmentation. Our method is clinically inspired and has the potential to facilitate lesion segmentation in various applications.