Reliable Brain Tumor Segmentation Based on Spiking Neural Networks with Efficient Training
This work addresses reliable, low-power segmentation for medical IoT and Point-of-Care systems, but it is incremental as it applies existing SNN methods to a specific domain.
The paper tackles 3D brain tumor segmentation by proposing a spiking neural network framework with multi-view ensemble for uncertainty estimation and robustness, achieving competitive accuracy and an 87% reduction in FLOPs on BraTS datasets.
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.