# Clinical Inspired MRI Lesion Segmentation

arXiv: https://arxiv.org/abs/2502.16032 · HTML: https://mlsanity.com/paper/2502.16032/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 22 Feb 2025.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [Ambiguous Medical Image Segmentation using Diffusion Models](https://mlsanity.com/paper/2304.04745/) (2023)
- [An Explainable Deep Framework: Towards Task-Specific Fusion for Multi-to-One MRI Synthesis](https://mlsanity.com/paper/2307.00885/) (2023)
- [Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification](https://mlsanity.com/paper/2009.14406/) (2020)

## Built on by (most cited first, 3 of 3)

- [Here Comes the Explanation: A Shapley Perspective on Multi-contrast Medical Image Segmentation](https://mlsanity.com/paper/2504.04645/) (2025)
- [Acquisition Time-Informed Breast Tumor Segmentation from Dynamic Contrast-Enhanced MRI](https://mlsanity.com/paper/2511.16498/) (2025)
- [Clinical Interpretability of Deep Learning Segmentation Through Shapley-Derived Agreement and Uncertainty Metrics](https://mlsanity.com/paper/2512.07224/) (2025)

## Abstract (arXiv)

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.