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

2026-01-23

AI Summary

This work proposes a three-dimensional segmentation framework based on spiking neural networks (SNNs) to address the limitations of conventional brain tumor segmentation methods in reliability, energy consumption, and computational efficiency—particularly within resource-constrained settings such as medical Internet-of-Things and point-of-care diagnostics. The approach uniquely integrates multi-view SNNs across sagittal, coronal, and axial planes to enable voxel-wise uncertainty estimation and introduces a forward-propagation-through-time (FPTT) strategy that substantially reduces training computational overhead. Evaluated on the BraTS 2017 and 2023 datasets, the model achieves competitive segmentation accuracy with well-calibrated uncertainty estimates while reducing FLOPs by 87%, demonstrating a strong balance between efficiency and robustness.

Technology Category

• Computer Vision: Segmentation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• brain tumor segmentation
• spiking neural networks
• computational efficiency
• medical IoT
• uncertainty estimation

Innovation

• Spiking Neural Networks
• Brain Tumor Segmentation
• Forward Propagation Through Time
• Uncertainty Estimation
• Energy-Efficient AI