Recent Advances in Dual-discriminator Spiking Generative Adversarial Network Based Classification and Segmentation for Predicting Pathogenesis of Foot Ulcers in Patients with Diabetes: A Systematic Review

Abstract

Diabetic foot ulcers represent one of the most severe complications of diabetes, often leading to infection, amputation, and increased mortality if not diagnosed and managed early. Recent advancements in artificial intelligence have introduced innovative approaches for improving the prediction, classification, and segmentation of foot ulcer pathogenesis. Among these, dual-discriminator spiking generative adversarial networks have emerged as a promising paradigm due to their ability to model complex biological patterns while maintaining energy efficiency and temporal dynamics. This systematic review explores recent developments in integrating spiking neural mechanisms with generative adversarial architectures for medical imaging analysis related to diabetic foot ulcers. The study highlights how dual-discriminator frameworks enhance both data realism and classification robustness, while spiking neurons contribute to improved feature representation and computational efficiency. Additionally, the review examines the role of multimodal data integration, including clinical records, imaging modalities, and sensor-based inputs, in enhancing predictive accuracy. The findings indicate that combining advanced deep learning architectures with biologically inspired computation significantly improves segmentation precision and early-stage pathogenesis detection. This paper provides a comprehensive synthesis of current methodologies, identifies research gaps, and outlines future directions for deploying intelligent diagnostic systems in real-world clinical settings to reduce complications associated with diabetic foot ulcers.