Brand new:

License: CC BY 4.0

arXiv:2507.15958v1 [eess.IV] 21 Jul 2025

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

Haitian Wang12, Xinyu Wang2, Yiren Wang2, Karen Lee2, Zichen Geng2,
Xian Zhang2, Kehkashan Kiran1, Yu Zhang1†, Bo Miao3†Corresponding author: Yu Zhang. Contact: [email protected]Mailing address (China): 1 Dongxiang Road, Chang’an District, Xi’an, Shaanxi 710129, P.R. China. Phone: (+86) 138919975111Northwestern Polytechnical University, Xi’an, Shaanxi 710129, China2The University of Western Australia, Perth, WA 6009, Australia3Australian Institute for Machine Learning, University of Adelaide, SA 5005, Australia

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% Top-1 accuracy and 81.7% macro F1 on the clinical dataset, consistently outperforming leading 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, and exceeding the performance of advanced CNN-to-SNN conversion methods. These results demonstrate the effectiveness of QANA for accurate, real-time, and privacy-sensitive medical analysis in edge environments

V Conclusion

In this paper, we proposed QANA, a quantization-aware neuromorphic framework for skin lesion classification on edge devices. Extensive experiments on the large-scale HAM10000 benchmark and a real-world clinical dataset show that QANA achieves state-of-the-art accuracy (91.6% Top-1, 82.4% macro F1 on HAM10000; 90.8%/81.7% on the clinical set) while enabling real-time and energy-efficient inference on the BrainChip Akida platform (1.5 ms latency, 1.7 mJ per image). These results demonstrate that QANA is highly effective for portable medical analysis and AI deployment in dermatology under limited computing resources.

VI Acknowledgement

This research was supported by the National Natural Science Foundation of China (Nos. 62172336 and 62032018). The authors gratefully acknowledge BrainChip Holdings Ltd. for providing technical support and the Akida AKD1000 hardware platform, whose powerful neuromorphic computing capabilities enabled strong performance of the SNN model. The authors also extend their appreciation to Dr. Atif Mansoor, Dr. Bo Miao and their teams for their preliminary contributions to this research

The use cases for Brainchip’s AKIDA Technologies is only limited by the imaginations of engineers, data scientists and entrepreneurs.

My opinion only DYOR

Fact Finder