A practical deep learning framework for multi-class skin cancer detection using U-Net segmentation and ResNet50 transfer learning

Mahesh Kumar Singh; Arun Kumar Singh; Pushpa Choudhary; Akhilesh Kumar Singh; Lalit Kumar Tyagi

doi:10.46481/jnsps.2026.3530

Authors

Mahesh Kumar Singh
[email protected]

Department of Computer Science and Engineering, SRM Institute of Science and Technology, Delhi-NCR Campus, Modinagar, Ghaziabad, Uttar Pradesh 201204, India
Arun Kumar Singh
Department of Computer Science and Engineering, Greater Noida Institute of Technology, Greater Noida, Uttar Pradesh, India
Pushpa Choudhary
Department of Computer Science and Engineering, Galgotias College of Engineering and Technology, Greater Noida, Uttar Pradesh, India
Akhilesh Kumar Singh
School of Computer Applications, Galgotias University, Greater Noida, Uttar Pradesh, India
Lalit Kumar Tyagi
Department of Computer Science and Engineering, School of Science and Technology, Swami Rama Himalayan University, Dehradun, Uttarakhand, India

Keywords:

Skin cancer detection, U-Net segmentation, ResNet50 transfer learning, Explainable artificial intelligence, Web-based screening

Abstract

Existing artificial intelligence (AI)-based diagnostic systems often lack interpretability, clinical decision support, and accessibility for practical deployment, despite the importance of early skin cancer detection in improving patient outcomes. This paper proposes an integrated deep learning framework for multi-class skin cancer detection that combines lesion segmentation using U-Net with transfer-learning classification of seven skin-lesion classes using ResNet50. The framework links classification results with segmented lesion regions to improve interpretability and uses Gradient-weighted Class Activation Mapping (Grad-CAM) to provide visual explanations of model predictions, thereby improving transparency and clinician confidence in the recommendations. It is implemented as a lightweight web-based application for remote, resource-efficient skin-lesion screening without costly local hardware. Experimental results on the HAM10000 dataset indicate that the framework outperforms baseline deep learning models in segmentation and classification while providing interpretable predictions and computationally efficient computer-aided dermoscopic screening. The proposed system offers an explainable decision-support approach for preliminary skin cancer assessment and may support earlier diagnosis in resource-limited clinical settings.

Dimensions

REFERENCES

[1] F. Bray, M. Laversanne, H. Sung, J. Ferlay, R. L. Siegel, I. Soerjomataram & A. Jemal, ``Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries'', CA: A Cancer Journal for Clinicians 74 (2024) 229. https://pubmed.ncbi.nlm.nih.gov/38572751/.

[2] O. Ronneberger, P. Fischer & T. Brox, ``U-Net: Convolutional networks for biomedical image segmentation'', 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), Munich, Germany, 2015, pp. 234--241. https://doi.org/10.1007/978-3-319-24574-4_28.

[3] M. Z. U. Rehman, F. Ahmed, S. A. Alsuhibany, S. S. Jamal, M. Z. Ali & J. Ahmad, ``Classification of skin cancer lesions using explainable deep learning'', Sensors 22 (2022) 6915. https://doi.org/10.3390/s22186915.

[4] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh & D. Batra, ``Grad-CAM: Visual explanations from deep networks via gradient-based localization'', International Journal of Computer Vision 128 (2020) 336. https://doi.org/10.1007/s11263-019-01228-7.

[5] Z. Liu, J. Hu, X. Gong & F. Li, ``Skin lesion segmentation with a multiscale input fusion U-Net incorporating Res2-SE and pyramid dilated convolution'', Scientific Reports 15 (2025) 7975. https://doi.org/10.1038/s41598-025-92447-1.

[6] M. Fiaz, M. B. Shoaib Khan, A. H. Khan, A. Bilal, M. Abdullah, A. A. Darem & R. Sarwar, ``An explainable hybrid deep learning framework for precise skin lesion segmentation and multi-class classification'', Frontiers in Medicine 12 (2025) 1681542. https://doi.org/10.3389/fmed.2025.1681542.

[7] B. Jandoubi & M. A. Akhloufi, ``Multimodal artificial intelligence in medical diagnostics'', Information 16 (2025) 591. https://doi.org/10.3390/info16070591.

[8] T. G. Debelee, ``Skin lesion classification and detection using machine learning techniques: A systematic review'', Diagnostics 13 (2023) 3147. https://doi.org/10.3390/diagnostics13193147.

[9] M. Tan & Q. V. Le, ``EfficientNet: Rethinking model scaling for convolutional neural networks'', 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, 2019, pp. 6105--6114. https://proceedings.mlr.press/v97/tan19a.html.

[10] G. Huang, Z. Liu, L. van der Maaten & K. Q. Weinberger, ``Densely connected convolutional networks'', IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, USA, 2017, pp. 2261--2269. https://doi.org/10.1109/CVPR.2017.243.

[11] A. Howard, M. Sandler, G. Chu, L.-C. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan, Q. V. Le & H. Adam, ``Searching for MobileNetV3'', IEEE/CVF International Conference on Computer Vision (ICCV 2019), Seoul, Republic of Korea, 2019, pp. 1314--1324. https://doi.org/10.1109/ICCV.2019.00140.

[12] B. H. M. van der Velden, H. J. Kuijf, K. G. A. Gilhuijs & M. A. Viergever, ``Explainable artificial intelligence (XAI) in deep learning-based medical image analysis'', Medical Image Analysis 79 (2022) 102470. https://doi.org/10.1016/j.media.2022.102470.

[13] X. Liu, D. Huang, J. Yao, J. Dong, L. Song, H. Wang, C. Yao & W. Chu, ``From black box to glass box: A practical review of explainable artificial intelligence (XAI)'', AI 6 (2025) 285. https://doi.org/10.3390/ai6110285.

[14] A. O. Agbeyangi & H. Suleman, ``Advances and challenges in low-resource-environment software systems: A survey'', Informatics 11 (2024) 90. https://doi.org/10.3390/informatics11040090.

[15] P. Tschandl, C. Rosendahl & H. Kittler, ``The HAM10000 dataset: A large collection of multi-source dermatoscopic images of common pigmented skin lesions'', Scientific Data 5 (2018) 180161. https://doi.org/10.1038/sdata.2018.161.

[16] A. Krizhevsky, I. Sutskever & G. E. Hinton, ``ImageNet classification with deep convolutional neural networks'', Advances in Neural Information Processing Systems 25 (NIPS 2012), Lake Tahoe, Nevada, USA, 2012, pp. 1097--1105. https://proceedings.neurips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html.

[17] O. Oktay, J. Schlemper, L. Le Folgoc, M. Lee, M. Heinrich, K. Misawa, K. Mori, S. McDonagh, N. Y. Hammerla, B. Kainz, B. Glocker & D. Rueckert, ``Attention U-Net: Learning where to look for the pancreas'', arXiv preprint (2018) arXiv:1804.03999. https://doi.org/10.48550/arXiv.1804.03999.

[18] S. Abd ElGhany, M. R. Ibraheem, M. Alruwaili & M. Elmogy, ``Diagnosis of various skin cancer lesions based on fine-tuned ResNet50 deep network'', Computers, Materials & Continua 68 (2021) 117. https://doi.org/10.32604/cmc.2021.016102.

[19] A. Rahmouni, E. M. Ayou, M. A. Sabri & A. Aarab, ``Enhancing skin lesion classification with ResNet and ViT: A study on feature combination and selection'', 2025 International Conference on Circuit, Systems and Communication (ICCSC), Fez, Morocco, 2025, pp. 1--6. https://doi.org/10.1109/ICCSC66714.2025.11135413.

[20] A.-M. Prisăcariu & L. Ferariu, ``Skin cancer diagnosis using CNN with attention mechanisms based on Grad-CAM'', 28th International Conference on System Theory, Control and Computing (ICSTCC), Sinaia, Romania, 2024, pp. 107--112. https://doi.org/10.1109/ICSTCC62912.2024.10744754.

[21] C. A. Vidales-Basurto & M. Rivera, ``A deep learning framework for skin lesion classification using ResNet50 and ELM'', Computer Methods and Programs in Biomedicine Update 9 (2026) 100253. https://doi.org/10.1016/j.cmpbup.2026.100253.

[22] K. Preechakul, S. Sriswasdi, B. Kijsirikul & E. Chuangsuwanich, ``Improved image classification explainability with high-accuracy heatmaps'', iScience 25 (2022) 103933. https://doi.org/10.1016/j.isci.2022.103933.

[23] Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh & J. Liang, ``UNet++: A nested U-Net architecture for medical image segmentation'', in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer, Cham, Switzerland, 2018, pp. 3--11. https://doi.org/10.1007/978-3-030-00889-5_1.