Clinical Inspired MRI Lesion Segmentation
This work addresses lesion segmentation for medical imaging applications, offering an incremental improvement by adapting clinical insights into a computational method.
The paper tackled the challenge of accurate MRI lesion segmentation by proposing a residual fusion method inspired by clinical practice, which achieved state-of-the-art performance on the BraTS2023 brain tumor dataset and an in-house breast MRI dataset.
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.