Published January 10, 2026 | Version v1

AI-POWERED EARLY DETECTION OF MELANOMA. ADVANCES, CHALLENGES, AND FUTURE DIRECTIONS.

Description

Early and accurate identification of malignant melanoma continues to be a major challenge for clinicians in the field. Traditional diagnostic approaches, including physical examination, histology, imaging, and nodal assessments, are frequently costly, require significant expertise, and can display large variations among clinicians. These factors may result in missed or misdiagnosis, which often significantly affects a patient’s prognosis. We examine in detail how the application of AI methods such as machine learning and deep learning can be used to advance early detection and identification of melanoma. We review various AI algorithms, including standard classifiers, ensemble techniques, and complex deep learning models. Hybrid models that combine convolutional neural networks (CNNs) and support vector machines (SVMs) are emphasized in this review, as they show enhanced performance and improved resistance to variations in the diagnostician’s input. Better utility of transfer learning and data augmentation approaches is discussed to overcome the challenges posed by small and unbalanced medical datasets. The authors consider the combination of various types of medical information for more effective cancer diagnosis. However, significant obstacles, including model explain ability, privacy safeguarding, and clinical evaluation, still need to be addressed. Extensive efforts are needed to overcome these barriers if AI systems are to be effectively adopted within healthcare environments. We suggest that AI offers the opportunity to revolutionize melanoma care by enabling rapid decision support and individualized treatment plans. Realizing this opportunity will depend on effective partnerships between researchers, clinicians, and industry to bring together advances in technology.

Files

AI-POWERED EARLY DETECTION OF MELANOMA. ADVANCES, CHALLENGES, AND FUTURE DIRECTIONS..pdf

Additional details

Dates

Submitted
2026-01-10
Skin cancer, particularly malignant melanoma, is known to yield 80% of skin cancer fatalities due to two reasons, namely, its aggressive behavior and ability to metastasize. Early detection is moreover central to increasing survival rates; however, traditional differential diagnostic methods are limited by their reliability and inter-observer variability. To meet these challenges, new diagnostic modalities have evolved that include diagnostic technologies. Recent innovations in imaging, like the Mela Find, are very sensitive and accurate when it comes to melanoma detection and could therefore enhance biopsy choices. Electronic clinical decision support systems offer objective and, therefore, less variable results in terms of inter- and interobservers variations. These systems utilize several feature extractions approaches, such as texture analysis, border smoothness evaluation, and time series analysis of the borders of lesions. Biosensors have also been identified as feasible rapid diagnostic devices in melanoma diagnosis at the point of care. These advancements are about extending and refining the accuracy and reliability of very early detection to finally provide benefits to patients and the healthcare system. The latest research revealed that melanoma detection has a big potential for the development of artificial intelligence (AI). Indices of sensitivity and specificity of melanoma classification from dermoscopic images using a logistic regression approach are satisfactory, equal to 76.36% and 87.04%, respectively. Still, deep learning approaches, especially convolutional neural networks (CNNs), have proven to perform better in terms of accuracy. For example, using the Inception V3 model, it was possible to classify melanoma with an accuracy of 93.74%, a sensitivity of 94.36%, and a specificity of 85.64%. Beyond the detection method, artificial neural networks have also been used in prognosis and treatment response prediction and clinical, dermoscopic, and histopathologic image analysis. Nevertheless, there are problems with data quality and its interpretation. During the process of machine learning, AI has the potential to transform first-stage melanoma diagnostics and even surpass traditional methods with further enhancements to increase the number of saves.

References

  • [1] Chatzilakou E., Hu Y., Jiang N., and Yetisen A. K., Biosensors for Melanoma Skin Cancer Diagnostics, Biosensors and Bioelectronics. (2024) 250. [2] Leong S. P., Nosrati M., Wu M. C. et al., Preoperative and Intraoperative Identification of Sentinel Lymph Nodes in Melanoma Surgery [3] Nagaoka T., Recent Advances in Diagnostic Technologies for Melanoma, Advanced Biomedical Engineering. (2016) 5, no. 0, 111–117, https://doi.org/10.14326/abe.5.111. [4] Daghrir J., Tlig L., Bouchouicha M., and Sayadi M., Melanoma Skin Cancer Detection Using Deep Learning and Classical Machine Learning Techniques: A Hybrid Approach, 2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), May 2020, Sousse, Tunisia, 1–5, https://doi.org/10.1109/atsip49331.2020.9231544. [5] Cui X., Wei R., Gong L. et al., Assessing the Effectiveness of Artificial Intelligence Methods for Melanoma: A Retrospective Review, Journal of the American Academy of Dermatology. (2019) 81, no. 5, 1176–1180, https://doi.org/10.1016/j.jaad.2019.06.042, 2-s2.0-85072189150. [6] Koczkodaj P., Sulkowska U., Didkowska J., Rutkowski P., and Mańczuk M., Melanoma Mortality Trends in 28 European Countries: a Retrospective Analysis for the Years 1960–2020, Cancers. (2023) 15, no. 5, https://doi.org/10.3390/cancers15051514. [7] Jicman P. A., Smart H., Ayello E. A., and Sibbald R. G., Early Malignant Melanoma Detection, Especially in Persons with Pigmented Skin, Advances in Skin & Wound Care. (2023) 36, no. 2, 69–77, https://doi.org/10.1097/01.asw.0000911156.19843.fb. [8] Sreedhar A., Aguilera-Aguirre L., and Singh K. K., Mitochondria in Skin Health, Aging, and Disease, Cell Death & Disease. (2020) 11, no. 6, https://doi.org/10.1038/s41419-020-2649-z. [9] Mhaske H., Patil M., Thote J., Shendage A., and Tallapalli R., A Review on Melanoma Cancer Detection Using Artificial Intelligence, International Journal for Research in Applied Science and Engineering Technology. (2023) 11, no. 2, 1335–1339, https://doi.org/10.22214/ijraset.2023.49231. Yap H. Y., Tee S. Z. Y., Wong M. M. T., Chow S. K., Peh S. C., and Teow S. Y., Pathogenic Role of Immune Cells in Rheumatoid Arthritis: Implications in Clinical Treatment and Biomarker Development, Cells. (2018) 7, no. 10, https://doi.org/10.3390/cells7100161