M-Net: MRI Brain Tumor Sequential Segmentation Network via Mesh-Cast

TL;DR

M-Net is a novel MRI brain tumor segmentation framework that leverages sequential slice correlations using a Mesh-Cast mechanism and a Two-Phase training strategy, improving accuracy and efficiency over existing methods.

Contribution

The paper introduces Mesh-Cast, a flexible mechanism for integrating sequential models into MRI segmentation, and a Two-Phase training strategy to enhance volumetric contextual learning.

Findings

Outperforms existing methods on BraTS datasets

Effectively captures spatial correlations between MRI slices

Reduces computational costs compared to 3D convolutions

Abstract

MRI tumor segmentation remains a critical challenge in medical imaging, where volumetric analysis faces unique computational demands due to the complexity of 3D data. The spatially sequential arrangement of adjacent MRI slices provides valuable information that enhances segmentation continuity and accuracy, yet this characteristic remains underutilized in many existing models. The spatial correlations between adjacent MRI slices can be regarded as "temporal-like" data, similar to frame sequences in video segmentation tasks. To bridge this gap, we propose M-Net, a flexible framework specifically designed for sequential image segmentation. M-Net introduces the novel Mesh-Cast mechanism, which seamlessly integrates arbitrary sequential models into the processing of both channel and temporal information, thereby systematically capturing the inherent "temporal-like" spatial correlations between MRI slices. Additionally, we define an MRI sequential input pattern and design a Two-Phase Sequential (TPS) training strategy, which first focuses on learning common patterns across sequences before refining slice-specific feature extraction. This approach leverages temporal modeling techniques to preserve volumetric contextual information while avoiding the high computational cost of full 3D convolutions, thereby enhancing the generalizability and robustness of M-Net in sequential segmentation tasks. Experiments on the BraTS2019 and BraTS2023 datasets demonstrate that M-Net outperforms existing methods across all key metrics, establishing itself as a robust solution for temporally-aware MRI tumor segmentation.