Quantization-Aware Neuromorphic Architecture for Efficient Skin Disease Classification on Resource-Constrained Devices

2025-07-21

AI Summary

To address the challenges of resource constraints, high energy consumption, and privacy sensitivity in skin lesion classification on edge devices, this paper proposes QANA—a quantization-aware spiking neural network. QANA integrates Ghost modules for parameter efficiency, Squeeze-and-Excitation channel-wise attention for discriminative feature enhancement, and a spike-compatible quantization-aware training mechanism enabling end-to-end optimization and efficient deployment on neuromorphic hardware (e.g., BrainChip Akida). Evaluated on HAM10000 and a clinical dataset, QANA achieves 91.6% Top-1 accuracy and 82.4% macro-F1 score, respectively. On-device deployment yields 1.5 ms inference latency and 1.7 mJ per inference—reducing energy consumption by over 98.6% compared to GPU-based inference. To our knowledge, QANA is the first framework to jointly optimize accuracy, energy efficiency, and hardware deployability for edge dermatology diagnosis, establishing a new paradigm for lightweight, privacy-preserving skin lesion analysis.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Learning & Optimization for CV

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate and efficient skin lesion classification on edge devices is critical for accessible dermatological care but remains challenging due to computational, energy, and privacy constraints. We introduce QANA, a novel quantization-aware neuromorphic architecture for incremental skin lesion classification on resource-limited hardware. QANA effectively integrates ghost modules, efficient channel attention, and squeeze-and-excitation blocks for robust feature representation with low-latency and energy-efficient inference. Its quantization-aware head and spike-compatible transformations enable seamless conversion to spiking neural networks (SNNs) and deployment on neuromorphic platforms. Evaluation on the large-scale HAM10000 benchmark and a real-world clinical dataset shows that QANA achieves 91.6% Top-1 accuracy and 82.4% macro F1 on HAM10000, and 90.8% / 81.7% on the clinical dataset, significantly outperforming state-of-the-art CNN-to-SNN models under fair comparison. Deployed on BrainChip Akida hardware, QANA achieves 1.5,ms inference latency and 1.7,mJ energy per image, reducing inference latency and energy use by over 94.6%/98.6% compared to GPU-based CNNs surpassing state-of-the-art CNN-to-SNN conversion baselines. These results demonstrate the effectiveness of QANA for accurate, real-time, and privacy-sensitive medical analysis in edge environments.

Problem

• Efficient skin disease classification on edge devices
• Low-latency, energy-efficient inference for resource-limited hardware
• Seamless conversion to spiking neural networks for deployment

Innovation

• Quantization-aware neuromorphic architecture for edge devices
• Integrates ghost modules and efficient attention blocks
• Enables seamless conversion to spiking neural networks