Improving Liver Disease Diagnosis with SNNDeep: A Custom Spiking Neural Network Using Diverse Learning Algorithms

2025-08-24

AI Summary

To address the trade-off between diagnostic accuracy and computational efficiency in binary classification of liver CT images, this paper proposes SNNDeep—the first low-level spiking neural network (SNN) specifically designed for medical image diagnosis. Methodologically, it integrates surrogate gradient learning, Tempotron-based weight updates, and biologically inspired active learning, with hyperparameters optimized via Optuna and implementation enabled on snnTorch and SpikingJelly frameworks. Its key contribution lies in being the first to deploy a highly configurable SNN in high-stakes biomedical imaging tasks, balancing biological plausibility with clinical practicality. Evaluated on the Medical Segmentation Decathlon Task03 Liver dataset, SNNDeep achieves a validation accuracy of 98.35%, outperforming mainstream deep learning frameworks while reducing training overhead and enhancing generalization. These results demonstrate the viability of lightweight SNNs for resource-constrained clinical deployment.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Medical and Biological Imaging
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Purpose: Spiking neural networks (SNNs) have recently gained attention as energy-efficient, biologically plausible alternatives to conventional deep learning models. Their application in high-stakes biomedical imaging remains almost entirely unexplored. Methods: This study introduces SNNDeep, the first tailored SNN specifically optimized for binary classification of liver health status from computed tomography (CT) features. To ensure clinical relevance and broad generalizability, the model was developed and evaluated using the Task03Liver dataset from the Medical Segmentation Decathlon (MSD), a standardized benchmark widely used for assessing performance across diverse medical imaging tasks. We benchmark three fundamentally different learning algorithms, namely Surrogate Gradient Learning, the Tempotron rule, and Bio-Inspired Active Learning across three architectural variants: a fully customized low-level model built from scratch, and two implementations using leading SNN frameworks, i.e., snnTorch and SpikingJelly. Hyperparameter optimization was performed using Optuna. Results: Our results demonstrate that the custom-built SNNDeep consistently outperforms framework-based implementations, achieving a maximum validation accuracy of 98.35%, superior adaptability across learning rules, and significantly reduced training overhead. Conclusion:This study provides the first empirical evidence that low-level, highly tunable SNNs can surpass standard frameworks in medical imaging, especially in data-limited, temporally constrained diagnostic settings, thereby opening a new pathway for neuro-inspired AI in precision medicine.

Problem

• Optimizing SNN for liver disease binary classification from CT scans
• Evaluating diverse learning algorithms for medical imaging applications
• Addressing data-limited diagnostic challenges with biologically plausible AI

Innovation

• Custom Spiking Neural Network for liver diagnosis
• Uses Surrogate Gradient, Tempotron, Bio-Inspired Learning
• Achieves 98.35% accuracy with reduced training overhead