International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 4, pp. 24-29, April 2026.
This work is licensed under a Creative Commons Attribution 4.0 International License.
AI-Enhanced Skin Cancer Screening System Using CNN on Edge Devices for Real-Time and Explainable Diagnosis
G G Vivek Kumar Reddy
M Mohan
A Sriram
B Vinuthna
K Likitha
M Chiranjeevi
Department of ECE, Siddartha Institute of Science and Technology, Puttur, AP, India.
Abstract: Skin cancer is one of the most common and rapidly increasing cancers worldwide, with early detection playing a crucial role in improving survival rates. However, access to dermatological expertise remains limited, particularly in rural and resource-constrained regions, where traditional diagnostic methods are costly, time-consuming, and often inaccurate. This paper presents an AI-enhanced skin cancer screening system that leverages Convolutional Neural Networks (CNN) deployed on edge devices for real-time, offline diagnosis. The proposed system utilizes a Raspberry Pi-based platform integrated with a camera module to capture dermoscopic images, which are then processed using a lightweight TensorFlow Lite CNN model. The system classifies skin lesions into benign and suspicious categories with an accuracy of approximately 92–94%, while achieving inference times of 0.5–1.2 seconds. To enhance interpretability, Grad-CAM-based visualization is incorporated to highlight regions influencing the model’s decision, thereby improving clinical trust and usability. Unlike conventional cloud-based AI systems, the proposed approach ensures complete offline operation, reduced latency, enhanced data privacy, and significantly lower cost (approximately 20 times cheaper than traditional dermoscopy systems). The system is portable, user-friendly, and suitable for deployment in rural healthcare centres, mobile medical camps, and community health programs. Overall, this work demonstrates the effectiveness of combining edge computing, deep learning, and explainable AI for accessible and reliable skin cancer screening.
Keywords: Skin Cancer Detection, Edge AI, Raspberry Pi, Convolutional Neural Networks, TensorFlow Lite.
References:
- G Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, Jan. 2017, doi: 10.1038/nature21056.
- P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Scientific Data, vol. 5, no. 1, p. 180161, Aug. 2018, doi: 10.1038/sdata.2018.161.
- S. A. H. Shah et al., “Explainable AI-Based skin cancer detection using CNN, particle swarm optimization and machine learning,” Journal of Imaging, vol. 10, no. 12, p. 332, Dec. 2024, doi: 10.3390/jimaging10120332.
- Z. M. Gohil and M. B. Desai, “Revolutionizing Dermatology: A Comprehensive survey of AI-Enhanced Early Skin Cancer diagnosis,” Archives of Computational Methods in Engineering, vol. 31, no. 8, pp. 4521–4531, Apr. 2024, doi: 10.1007/s11831-024-10121-7.
- K. Behara, E. Bhero, and J. T. Agee, “AI in dermatology: a comprehensive review into skin cancer detection,” PeerJ Computer Science, vol. 10, p. e2530, Dec. 2024, doi: 10.7717/peerj-cs.2530.
- S. Mukherjee, S. R. Rao, and A. Poddar, “Artificial intelligence powered mobile health apps for skin cancer detection: current challenges and a systems thinking approach for improved public health outcomes in low- and middle-income countries,” Melanoma Research, vol. 36, no. 1, pp. 16–30, Nov. 2025, doi: 10.1097/cmr.0000000000001074.
- S. Pardeshi, H. Motipwar, M. Mirza and S. A. Dhole, “Skin Disease Detection using Deep Learning,” 2025 6th International Conference for Emerging Technology (INCET), BELGAUM, India, 2025, pp. 1-8, doi: 10.1109/INCET64471.2025.11139958.
- S. Aishwarya, C. Selvamurugan, K. G. Parthiban, J. M. Prabhakar, K. K. Lakshmikandhan, and J. T. Raja, “Convolutional neural networks (CNNs) for medical imaging,” in Advances in medical diagnosis, treatment, and care (AMDTC) book series, 2025, pp. 263–312. doi: 10.4018/979-8-3693-9816-6.ch011.
- Y. A. Fahim, I. W. Hasani, S. Kabba, and W. M. Ragab, “Artificial intelligence in healthcare and medicine: clinical applications, therapeutic advances, and future perspectives,” European Journal of Medical Research, vol. 30, no. 1, p. 848, Sep. 2025, doi: 10.1186/s40001-025-03196-w.
- R. Deepa, S. Arunkumar, V. Jayaraj, and A. Sivasamy, “Healthcare’s new Frontier: AI-driven early cancer detection for improved well-being,” AIP Advances, vol. 13, no. 11, Nov. 2023, doi: 10.1063/5.0177640.
- D. Aswani, P. Aurchana, and S. Shanthi, “Revolutionizing Dermatological Diagnoses: A comprehensive survey on the transformative role of AI in skin cancer detection,” in Lecture notes in networks and systems, 2024, pp. 433–444. doi: 10.1007/978-981-97-8666-4_35.
- M. Bhargavi, S. Shareefunnisa, S. Sajida Sultana, R. Renugadevi, T. N. Varshan and K. Ramanjaneyulu, “Deep Learning for Skin Cancer Classification: Leveraging Feature Extraction and Transfer Learning Strategies,” 2024 8th International Conference on Inventive Systems and Control (ICISC), Coimbatore, India, 2024, pp. 181-188, doi: 10.1109/ICISC62624.2024.00038.