AI-Powered Diagnosis of Skin Cancer: A Contemporary Review, Open Challenges and Future Research Directions

Abstract

Skin cancer continues to remain one of the major healthcare issues across the globe. If diagnosed early, skin cancer can be treated successfully. While early diagnosis is paramount for an effective cure for cancer, the current process requires the involvement of skin cancer specialists, which makes it an expensive procedure and not easily available and affordable in developing countries. This dearth of skin cancer specialists has given rise to the need to develop automated diagnosis systems. In this context, Artificial Intelligence (AI)-based methods have been proposed. These systems can assist in the early detection of skin cancer and can consequently lower its morbidity, and, in turn, alleviate the mortality rate associated with it. Machine learning and deep learning are branches of AI that deal with statistical modeling and inference, which progressively learn from data fed into them to predict desired objectives and characteristics. This survey focuses on Machine Learning and Deep Learning techniques deployed in the field of skin cancer diagnosis, while maintaining a balance between both techniques. A comparison is made to widely used datasets and prevalent review papers, discussing automated skin cancer diagnosis. The study also discusses the insights and lessons yielded by the prior works. The survey culminates with future direction and scope, which will subsequently help in addressing the challenges faced within automated skin cancer diagnosis.

Current status of artificial intelligence methods for skin cancer survival analysis: a scoping review

“…Epidemiological and clinical investigations improved documentation of skin cancer incidence and prevalence, increasing discussion on prevention and detection. Literature has recognized the paramount importance of early detection and management for skin cancer and the potential for assistance by artificial intelligence (AI) tools at this stage ( 5 ). However, monitoring with survival analysis, along with discovery of survival markers are greatly needed for clinical prognostication.…”

A protocol for annotation of total body photography for machine learning to analyze skin phenotype and lesion classification

“…In dermatology, AI has the potential to reshape diagnostic processes using numerous imaging modalities including dermoscopy and sequential digital dermoscopy imaging (SDDI), wide-field clinical imaging and total body photography (TBP), reflectance cutaneous confocal microscopy (RCM), optical coherence tomography (OCT), line-field confocal OCT (LC-OCT), and lastly digital pathology. The majority of machine learning algorithms are commonly utilized for the analysis of single lesion dermoscopic images, with notable focus on the specific task of detecting melanoma ( 8 ). A landmark study by Esteva et al, reported higher accuracy for algorithms in classifying keratinocyte carcinoma and melanoma, compared to the average accuracy score from 16 expert dermatologists ( 9 ).…”

Leveraging Machine Learning for Accurate Detection and Diagnosis of Melanoma and Nevi: An Interdisciplinary Study in Dermatology

“…The implementation of AI-based approaches holds the potential to enhance accuracy and improve decision-making for melanoma management. Such models have the potential to facilitate detection enable initiation of appropriate treatment and contribute to effective strategies in managing melanoma [ 13 ]. The integration of AI-based detection models for melanoma and nevi into workflows can enhance capabilities, particularly in healthcare settings where access to specialized dermatologists or sufficient resources may be limited [ 14 ].…”