MMRINet: Efficient Mamba-Based Segmentation with Dual-Path Refinement for Low-Resource MRI Analysis

2025-11-15

AI Summary

To address the challenge of balancing segmentation accuracy and computational efficiency for multi-parametric MRI brain tumor segmentation in resource-constrained settings, this paper proposes MMRINet—a lightweight 3D network. Its key contributions are: (1) the first integration of the linear-complexity Mamba state-space model into 3D medical image segmentation, replacing computationally expensive self-attention for efficient long-range contextual modeling; (2) a dual-path feature refinement (DPFR) module that enhances feature diversity and deep semantic consistency without requiring auxiliary data; and (3) a progressive multi-scale fusion architecture (PFA) to optimize cross-scale information flow. With only 2.5 million parameters, MMRINet achieves a Dice score of 0.752 and HD95 of 12.23 on BraTS-Lighthouse SSA 2025—outperforming existing lightweight models and demonstrating strong potential for clinical deployment under low-resource conditions.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Hardware-aware ML
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Automated brain tumor segmentation in multi-parametric MRI remains challenging in resource-constrained settings where deep 3D networks are computationally prohibitive. We propose MMRINet, a lightweight architecture that replaces quadratic-complexity attention with linear-complexity Mamba state-space models for efficient volumetric context modeling. Novel Dual-Path Feature Refinement (DPFR) modules maximize feature diversity without additional data requirements, while Progressive Feature Aggregation (PFA) enables effective multi-scale fusion. In the BraTS-Lighthouse SSA 2025, our model achieves strong performance with an average Dice score of (0.752) and an average HD95 of (12.23) with only ~2.5M parameters, demonstrating efficient and accurate segmentation suitable for low-resource clinical environments. Our GitHub repository can be accessed here: github.com/BioMedIA-MBZUAI/MMRINet.

Problem

• Efficient brain tumor segmentation in low-resource MRI environments
• Replacing quadratic attention with linear Mamba models for efficiency
• Achieving accurate segmentation with minimal parameters for clinical use

Innovation

• Uses linear-complexity Mamba state-space models
• Introduces Dual-Path Feature Refinement modules
• Implements Progressive Feature Aggregation for fusion