Graph-Based Multi-Modal Light-weight Network for Adaptive Brain Tumor Segmentation

TL;DR

This paper introduces GMLN-BTS, a lightweight, graph-based neural network for brain tumor segmentation that achieves high accuracy with significantly fewer parameters than existing models, making it suitable for practical deployment.

Contribution

The paper presents a novel multi-modal brain tumor segmentation network combining graph-based interactions and efficient encoding, reducing parameters by 98% while maintaining state-of-the-art performance.

Findings

Achieves state-of-the-art results on BraTS benchmarks

Reduces parameter count by 98% compared to 3D Transformers

Maintains high segmentation accuracy with resource efficiency

Abstract

Multi-modal brain tumor segmentation remains challenging for practical deployment due to the high computational costs of mainstream models. In this work, we propose GMLN-BTS, a Graph-based Multi-modal interaction Lightweight Network for brain tumor segmentation. Our architecture achieves high-precision, resource-efficient segmentation through three key components. First, a Modality-Aware Adaptive Encoder (M2AE) facilitates efficient multi-scale semantic extraction. Second, a Graph-based Multi-Modal Collaborative Interaction Module (G2MCIM) leverages graph structures to model complementary cross-modal relationships. Finally, a Voxel Refinement UpSampling Module (VRUM) integrates linear interpolation with multi-scale transposed convolutions to suppress artifacts and preserve boundary details. Experimental results on BraTS 2017, 2019, and 2021 benchmarks demonstrate that GMLN-BTS achieves state-of-the-art performance among lightweight models. With only 4.58M parameters, our method reduces parameter count by 98% compared to mainstream 3D Transformers while significantly outperforming existing compact approaches.