Reliable Brain Tumor Segmentation Based on Spiking Neural Networks with Efficient Training

TL;DR

This paper introduces a reliable, energy-efficient 3D brain tumor segmentation framework using spiking neural networks, employing multi-view ensemble and FPTT to improve robustness and reduce computational costs.

Contribution

It presents a novel multi-view ensemble SNN approach with FPTT training for efficient, accurate brain tumor segmentation and uncertainty estimation.

Findings

Achieved competitive accuracy on BraTS datasets.

Reduced FLOPs by 87% compared to traditional methods.

Provided well-calibrated voxel-wise uncertainty estimates.

Abstract

We propose a reliable and energy-efficient framework for 3D brain tumor segmentation using spiking neural networks (SNNs). A multi-view ensemble of sagittal, coronal, and axial SNN models provides voxel-wise uncertainty estimation and enhances segmentation robustness. To address the high computational cost in training SNN models for semantic image segmentation, we employ Forward Propagation Through Time (FPTT), which maintains temporal learning efficiency with significantly reduced computational cost. Experiments on the Multimodal Brain Tumor Segmentation Challenges (BraTS 2017 and BraTS 2023) demonstrate competitive accuracy, well-calibrated uncertainty, and an 87% reduction in FLOPs, underscoring the potential of SNNs for reliable, low-power medical IoT and Point-of-Care systems.