Early-Stage Skin Cancer Detection Using Spiking Neural Networks: A Delta Modulation-Based Approach on the HAM10000 Dataset

Yıl 2026, Cilt: 42 Sayı: 1 , - , 11.03.2026

Aslıhan Sönmez , Volkan Ates

https://doi.org/10.65520/erciyesfen.1826362

https://izlik.org/JA76DA75CH

Öz

Skin cancer is a disease with high morbidity rates where early diagnosis is vital, yet diagnosis is challenging due to visual similarities between lesions.
This study proposes a biologically inspired Spiking Neural Network (SNN) architecture for skin lesion classification as an alternative to the high energy consumption of traditional neural networks.
The model was trained on the HAM10000 dataset and used delta modulation encoding to convert images into spike trains.
Results show strong performance especially in distinguishing Melanoma (MEL) from Basal Cell Carcinoma (BCC).

Anahtar Kelimeler

Spiking neural network , delta modulation , HAM10000 , skin lesion , time-based encoding , classification

Erken Evre Cilt Kanseri Tespiti için İğnecikli Sinir Ağları (SNN) Kullanımı: HAM10000 Veri Kümesi Üzerinde Delta Modülasyon Tabanlı Yaklaşım

https://izlik.org/JA76DA75CH

Öz

Deri kanseri, yüksek morbidite oranlarına sahip ve erken teşhisin hayati önem taşıdığı, ancak lezyonlar arası görsel benzerlikler nedeniyle tanısı zor bir hastalıktır.
Bu çalışma, geleneksel yapay sinir ağlarının yüksek enerji tüketimine bir alternatif olarak, biyolojik esinli İğnecikli Sinir Ağları (SNN) mimarisini kullanarak cilt lezyonlarının sınıflandırılmasını amaçlamaktadır.
HAM10000 veri seti üzerinde eğitilen model, sürekli görüntü verilerini zaman tabanlı iğnecik dizilerine dönüştürmek için enerji verimli bir delta modülasyonu (DM) kodlama tekniği kullanmıştır.
Test sonuçları, modelin özellikle Melanom (MEL) ve Bazal Hücreli Karsinom (BCC) ayrımında yüksek başarı sergilediğini göstermiştir.

Anahtar Kelimeler

İğnecikli sinir ağı , delta modülasyon , HAM10000 , deri lezyonu , zaman tabanlı kodlama , sınıflandırma

Kaynakça

• A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, 2017.
• P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Sci Data, vol. 5, no. 1, pp. 1–9, 2018.
• S. S. Han, M. S. Kim, W. Lim, G. H. Park, I. Park, and S. E. Chang, “Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm,” Journal of Investigative Dermatology, vol. 138, no. 7, pp. 1529–1538, 2018.
• Y. Liu et al., “A deep learning system for differential diagnosis of skin diseases,” Nat Med, vol. 26, no. 6, pp. 900–908, 2020.
• D. A. Okuboyejo and O. O. Olugbara, “A review of prevalent methods for automatic skin lesion diagnosis,” Open Dermatol J, vol. 12, no. 1, 2018.
• Y. Zhang, H. Liu, and Q. Hu, “Transfuse: Fusing transformers and cnns for medical image segmentation,” in International conference on medical image computing and computer-assisted intervention, Springer, 2021, pp. 14–24.
• N. C. F. Codella et al., “Deep learning ensembles for melanoma recognition in dermoscopy images,” IBM J Res Dev, vol. 61, no. 4/5, pp. 1–5, 2017.
• P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Sci Data, vol. 5, no. 1, pp. 1–9, 2018.
• S. M. Thwin and H.-S. Park, “Skin lesion classification using a deep ensemble model,” Applied Sciences, vol. 14, no. 13, p. 5599, 2024.
• V. D. Nguyen, N. D. Bui, and H. K. Do, “Skin lesion classification on imbalanced data using deep learning with soft attention,” Sensors, vol. 22, no. 19, p. 7530, 2022.
• A. Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
• A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, 2017.
• S. S. Han, M. S. Kim, W. Lim, G. H. Park, I. Park, and S. E. Chang, “Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm,” Journal of Investigative Dermatology, vol. 138, no. 7, pp. 1529–1538, 2018.
• E. Erdem and T. Aydin, “Artificial Neural Network-Based Approaches to Improve Classification of Skin Lesions,” in 2023 Medical Technologies Congress (TIPTEKNO), IEEE, 2023, pp. 1–4.
• S. Serte and H. Demirel, “Gabor wavelet-based deep learning for skin lesion classification,” Comput Biol Med, vol. 113, p. 103423, 2019.
• K. Ali, Z. A. Shaikh, A. A. Khan, and A. A. Laghari, “Multiclass skin cancer classification using EfficientNets–a first step towards preventing skin cancer,” Neuroscience Informatics, vol. 2, no. 4, p. 100034, 2022.
• N. Gessert et al., “Skin lesion diagnosis using ensembles, unscaled multi-crop evaluation and loss weighting,” arXiv preprint arXiv:1808.01694, 2018.
• T. Morita and X.-H. Han, “Investigating self-supervised learning for Skin Lesion Classification,” in 2023 18th International Conference on Machine Vision and Applications (MVA), IEEE, 2023, pp. 1–5.
• I. Pacal, B. Ozdemir, J. Zeynalov, H. Gasimov, and N. Pacal, “A novel CNN-ViT-based deep learning model for early skin cancer diagnosis,” Biomed Signal Process Control, vol. 104, p. 107627, 2025.
• W. Maass, “Networks of spiking neurons: the third generation of neural network models,” Neural networks, vol. 10, no. 9, pp. 1659–1671, 1997.
• W. Gerstner and W. M. Kistler, Spiking neuron models: Single neurons, populations, plasticity. Cambridge university press, 2002.
• F. Ponulak and A. Kasinski, “Introduction to spiking neural networks: Information processing, learning and applications,” Acta Neurobiol Exp (Wars), vol. 71, no. 4, pp. 409–433, 2011.
• M. Davies et al., “Loihi: A neuromorphic manycore processor with on-chip learning,” Ieee Micro, vol. 38, no. 1, pp. 82–99, 2018.
• S. Bian, E. Donati, and M. Magno, “Evaluation of encoding schemes on ubiquitous sensor signal for spiking neural network,” IEEE Sens J, 2024.
• M. Pfeiffer and T. Pfeil, “Deep learning with spiking neurons: Opportunities and challenges,” Front Neurosci, vol. 12, p. 409662, 2018.
• E. O. Neftci, H. Mostafa, and F. Zenke, “Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks,” IEEE Signal Process Mag, vol. 36, no. 6, pp. 51–63, 2019.
• A. Tavanaei, M. Ghodrati, S. R. Kheradpisheh, T. Masquelier, and A. Maida, “Deep learning in spiking neural networks,” Neural networks, vol. 111, pp. 47–63, 2019.
• J. K. Eshraghian et al., “Training spiking neural networks using lessons from deep learning,” Proceedings of the IEEE, vol. 111, no. 9, pp. 1016–1054, 2023.