Pediatric chest X-ray diagnosis using neuromorphic models

• Published in: Computers in biology and medicine Vol. 192; no. Pt A; p. 110173
• Main Authors: Bokhari, Syed Mohsin, Sohaib, Sarmad, Shafi, Muhammad
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2025
• Subjects: Child; Child, Preschool; Female; Hierarchical Spiking Neural Networks (HSNN); Humans; Infant; Internal Medicine; Machine Learning; Male; Neural Networks, Computer; Neuromorphic computing; Other; Pediatric chest X-rays (pediCXR); Radiographic Image Interpretation, Computer-Assisted - methods; Radiography, Thoracic - methods; Spiking convolutional neural networks (SCNN); Spiking Neural Networks (SNNs); Spiking Neural Networks (SNNs); Pediatric chest X-rays (pediCXR); Hierarchical Spiking Neural Networks (HSNN); Spiking convolutional neural networks (SCNN); Neuromorphic computing
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2025.110173

This research presents an innovative neuromorphic method utilizing Spiking Neural Networks (SNNs) to analyze pediatric chest X-rays (PediCXR) to identify prevalent thoracic illnesses. We incorporate spiking-based machine learning models such as Spiking Convolutional Neural Networks (SCNN), Spiking Residual Networks (S-ResNet), and Hierarchical Spiking Neural Networks (HSNN), for pediatric chest radiographic analysis utilizing the publically available benchmark PediCXR dataset. These models employ spatiotemporal feature extraction, residual connections, and event-driven processing to improve diagnostic precision. The HSNN model surpasses benchmark approaches from the literature, with a classification accuracy of 96% across six thoracic illness categories, with an F1-score of 0.95 and a specificity of 1.0 in pneumonia detection. Our research demonstrates that neuromorphic computing is a feasible and biologically inspired approach to real-time medical imaging diagnostics, significantly improving performance. •This research underscores the effectiveness of SNN models in interpreting PCXR.•HSNN exhibited exceptional performance with a classification accuracy of 96%.•highlights the capacity of spiking neural networks for illness identification.