Early detection of skin cancer using AI: Deciphering dermatology images for melanoma detection
Source abstract
Abstract
This Review explores the transformative impact of artificial intelligence (AI) on the early detection of skin cancer, with a specific focus on melanoma, a potentially lethal form of the disease. Beginning with an overview of traditional diagnostic methods and their limitations, this paper delves into the evolution of AI within dermatology, emphasizing its application in image analysis and pattern recognition. A comprehensive examination of AI algorithms for melanoma detection, including machine learning and deep learning models, is provided. This Review critically assesses the performance metrics, training datasets, and comparative analyses with traditional methods. Addressing challenges such as data quality, interpretability, and ethical considerations, this paper outlines future directions, emphasizing ongoing research, algorithm improvements, and integration with clinical practices. Case studies and success stories highlight the real-world impact of AI in dermatology. This Review concludes by summarizing key findings and underlining the pivotal role of AI in revolutionizing early melanoma detection, with implications for personalized medicine and enhanced patient outcomes.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Cutaneous Melanoma Detection and Management · AI in cancer detection · Cell Image Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
ECE, Nehru Institute of Engineering and Technology 1 , Coimbatore, Tamil Nadu, India
Networks and Cybersecurity, Faculty of Information Technology, Al Ahliyya Amman University 2 , Amman, Jordan
Department of Computer Science, Texas Tech University 3 , Lubbock, Texas 79409, USA
Agricultural Engineering, Nehru Institute of Technology 4 , Coimbatore, Tamil Nadu, India
References (31)
Show source-provided references
1. World Health Organization, “Skin cancers” (2021), https://www.who.int/uv/faq/skincancer/en/index1.html.
2. American Cancer Society, “Key statistics for basal and squamous cell skin cancers” (2021), https://www.cancer.org/cancer/basal-and-squamous-cell-skin-cancer/about/key-statistics.html.
3. Final version of 2009 AJCC melanoma staging and classification10.1200/jco.2009.23.4799 ↗
4. Diagnostic accuracy of dermoscopy10.1016/s1470-2045(02)00679-4 ↗
5. Dermatologist-level classification of skin cancer with deep neural networks10.1038/nature21056 ↗
6. Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists10.1093/annonc/mdy166 ↗
7. Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images
8. Deep neural networks are superior to dermatologists in melanoma image classification10.1016/j.ejca.2019.05.023 ↗
9. Human–computer collaboration for skin cancer recognition10.1038/s41591-020-0942-0 ↗
10. Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists10.1371/journal.pmed.1002686 ↗
11. Radiomics of multiparametric MRI for pretreatment prediction of pathologic complete response to neoadjuvant chemotherapy in breast cancer: A multicenter study10.1158/1078-0432.ccr-18-3190 ↗
12. A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task10.1016/j.ejca.2019.02.005 ↗
13. Border detection in dermoscopy images using statistical region merging
14. Epiluminescence microscopy-based classification of pigmented skin lesions using computerized image analysis and an artificial neural network10.1111/j.1600-0846.2008.00301.x ↗
15. Impact of dermoscopy and short-term sequential digital dermoscopy imaging for the management of pigmented lesions in primary care: A sequential intervention trial10.1111/j.1365-2133.2009.09374.x ↗
16. Association between surgical skin markings in dermoscopic images and diagnostic performance of a deep learning convolutional neural network for melanoma recognition10.1001/jamadermatol.2019.1735 ↗
17. Expert-level diagnosis of nonpigmented skin cancer by combined convolutional neural networks10.1001/jamadermatol.2019.4069 ↗
18. Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm10.1016/j.jid.2018.01.028 ↗
19. Deep-learning-based, computer-aided classifier developed with a small dataset of clinical images surpasses board-certified dermatologists in skin tumour diagnosis10.1111/bjd.16924 ↗
20. Results of the 2016 international skin imaging collaboration international symposium on biomedical imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images10.1016/j.jaad.2017.08.016 ↗
21. Computer-aided diagnosis of melanoma through the analysis of dermoscopic images: Recent advances and future promises10.1016/j.compmedimag.2019.05.003 ↗
22. Skin lesion classification with ensembles of image transformations10.1016/j.compbiomed.2019.103348 ↗
23. An efficient deep learning method for dermoscopy image classification based on meta learning10.1109/TNB.2020.3011297 ↗
24. A deep learning algorithm for diagnosis of pigmented skin lesions: Experimental evaluation on an independently collected clinical dataset of 249 patients10.1016/j.compbiomed.2020.103596 ↗
25. Performance of a deep learning algorithm for automated detection and classification of cutaneous lesions in dermoscopic images10.1016/j.artmed.2019.101735 ↗
26. Radiomics analysis using stability selection supervised component analysis for right-censored survival data10.1016/j.compbiomed.2020.103959 ↗
27. Physiological explicit of delayed psychological stress response induced by extra neural regulation10.1016/j.cmpb.2020.105610 ↗
28. Generative adversarial network in medical imaging: A review10.1016/j.media.2019.101552 ↗
29. A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection10.1007/978-3-642-40763-5_50 ↗
30. Diagnosis of nonpigmented skin tumors by video-dermoscopy: A novel two-step method10.1684/ejd.2019.3581 ↗
31. Home virtual visits for outpatient follow-up stroke care: Cross-sectional study10.2196/13734 ↗