Authors : Dr. Arvind Jagtap; Nisarg M. Jogdande; Tejasvini V. Shelar; Sahil S. Jadhav; Divya R. Lokhande

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/nhm2fh9y

Scribd : https://tinyurl.com/4hp94mhz

DOI : https://doi.org/10.38124/ijisrt/26apr1616

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Cutaneous malignancies pose a major worldwide health concern, requiring rapid and accurate detection. Traditional diagnostic approaches, including clinical inspection and biopsy procedures, are time-intensive and necessitate advanced dermatological proficiency. Advancements in artificial intelligence, particularly convolutional neural network models, have demonstrated superior efficacy in classifying dermatological imagery. The research proposes a diagnostic system for skin cancer detection based on MobileNetV2 via transfer learning. It employs the HAM10000 dataset, encompassing 10,015 dermoscopic images across seven lesion types. The pipeline integrates image preparation, model training, multiclass classification in Python, and web deployment through Flask. Evaluation on the test set yielded 71.38% accuracy, with mean precision of 85.77% and recall of 60.42%. Such a system equips medical professionals with an automated aid for prognostic assessments in clinical practice. Prospective improvements could include dataset augmentation and advanced network designs.

Keywords : Skin Lesion Identification; Deep Neural Networks; CNN Models; Transfer Learning Techniques; MobileNetV2 Framework; Medical Image Evaluation; Dermoscopy Datasets (HAM10000); Image Preparation Methods; Image Categorization Tasks; CAD Tools; AI-Driven Healthcare Solutions; Automated Screening Systems; Clinical Image Processing.

References :

1. R. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, 2017.
2. H. A. Haenssle et al., “Man against machine: Diagnostic performance of a deep learning CNN for dermoscopic melanoma recognition,” Annals of Oncology, vol. 29, no. 8, pp. 1836–1842, 2018.
3. T. J. Brinker et al., “Deep neural networks are superior to dermatologists in melanoma image classification,” European Journal of Cancer, vol. 119, pp. 11–17, 2019.
4. G. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, 2017.
5. N. C. Codella et al., “Deep learning ensembles for melanoma recognition,” IBM Journal of Research and Development, vol. 61, no. 4, 2017.
6. M. Abdar et al., “A new nested ensemble technique for automated diagnosis of skin cancer,” IEEE Access, vol. 8, pp. 8147–8165, 2020.
7. S. Dorj et al., “The skin cancer classification using deep convolutional neural network,” Multimedia Tools and Applications, vol. 77, pp. 9909–9924, 2018.
8. J. Kawahara et al., “Deep features to classify skin lesions,” IEEE ISBI, pp. 1397–1400, 2016.
9. A. Krizhevsky et al., “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems, 2012.
10. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
11. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” ICLR, 2015.
12. C. Szegedy et al., “Going deeper with convolutions,” IEEE CVPR, 2015.
13. F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” IEEE CVPR, 2017.
14. A. G. Howard et al., “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv:1704.04861, 2017.
15. M. Sandler et al., “MobileNetV2: Inverted residuals and linear bottlenecks,” IEEE CVPR, 2018.
16. K. Korotkov and R. Garcia, “Computerized analysis of pigmented skin lesions,” Artificial Intelligence in Medicine, vol. 56, no. 2, pp. 69–90, 2012.
17. M. E. Celebi et al., “Lesion border detection in dermoscopy images,” Computerized Medical Imaging and Graphics, vol. 33, no. 2, pp. 148–153, 2009.
18. A. Esteva et al., “A guide to deep learning in healthcare,” Nature Medicine, vol. 25, no. 1, pp. 24–29, 2019.
19. World Health Organization, “Skin cancers,” WHO, 2023.
20. International Skin Imaging Collaboration (ISIC), “ISIC Archive for skin lesion analysis,” Dataset Repository, 2023.