Artificial Intelligence Applied to Non-Invasive Imaging Modalities in Identification of Nonmelanoma Skin Cancer: A Systematic Review.

BACKGROUND: The objective of this study is to systematically analyze the current state of the literature regarding novel artificial intelligence (AI) machine learning models utilized in non-invasive imaging for the early detection of nonmelanoma skin cancers. Furthermore, we aimed to assess their potential clinical relevance by evaluating the accuracy, sensitivity, and specificity of each algorithm and assessing for the risk of bias. METHODS: Two reviewers screened the MEDLINE, Cochrane, PubMed, and Embase databases for peer-reviewed studies that focused on AI-based skin cancer classification involving nonmelanoma skin cancers and were published between 2018 and 2023. The search terms included skin neoplasms, nonmelanoma, basal-cell carcinoma, squamous-cell carcinoma, diagnostic techniques and procedures, artificial intelligence, algorithms, computer systems, dermoscopy, reflectance confocal microscopy, and optical coherence tomography. Based on the search results, only studies that directly answered the review objectives were included and the efficacy measures for each were recorded. A QUADAS-2 risk assessment for bias in included studies was then conducted. RESULTS: A total of 44 studies were included in our review; 40 utilizing dermoscopy, 3 using reflectance confocal microscopy (RCM), and 1 for hyperspectral epidermal imaging (HEI). The average accuracy of AI algorithms applied to all imaging modalities combined was 86.80%, with the same average for dermoscopy. Only one of the three studies applying AI to RCM measured accuracy, with a result of 87%. Accuracy was not measured in regard to AI based HEI interpretation. CONCLUSION: AI algorithms exhibited an overall favorable performance in the diagnosis of nonmelanoma skin cancer via noninvasive imaging techniques. Ultimately, further research is needed to isolate pooled diagnostic accuracy for nonmelanoma skin cancers as many testing datasets also include melanoma and other pigmented lesions.

Oxidative Stress in Melanoma: Beneficial Antioxidant and Pro-Oxidant Therapeutic Strategies.

Cutaneous melanoma ranks as the fifth most common cancer in the United States and represents one of the deadliest forms of skin cancer. While recent advances in systemic targeted therapies and immunotherapies have positively impacted melanoma survival, the survival rate of stage IV melanoma remains at a meager 32%. Unfortunately, tumor resistance can impede the effectiveness of these treatments. Oxidative stress is a pivotal player in all stages of melanoma progression, with a somewhat paradoxical function that promotes tumor initiation but hinders vertical growth and metastasis in later disease. As melanoma progresses, it employs adaptive mechanisms to lessen oxidative stress in the tumor environment. Redox metabolic rewiring has been implicated in acquired resistance to BRAF/MEK inhibitors. A promising approach to enhance the response to therapy involves boosting intracellular ROS production using active biomolecules or targeting enzymes that regulate oxidative stress. The complex interplay between oxidative stress, redox homeostasis, and melanomagenesis can also be leveraged in a preventive context. The purpose of this review is to provide an overview of oxidative stress in melanoma, and how the antioxidant system may be manipulated in a therapeutic context for improved efficacy and survival.

Dermoscopic features associated with 3-GEP PLA: LINC00518, PRAME, and TERT expression in suspicious pigmented lesions.

Utilization of dermoscopy and novel molecular triage technologies augments visual triage of pigmented skin lesions, promoting early detection of melanoma. One emerging in vivo genomic test, 3-GEP pigmented lesion assay (3-GEP PLA) aids in pigmented lesion triage by noninvasively detecting the presence of three genes associated with melanoma: LINC00518, PRAME, and TERT. The purpose of our retrospective case-control study was to identify dermoscopic features uniquely associated with the presence of LINC00518, PRAME, or TERT in the stratum corneum as determined by 3-GEP PLA testing. Images of suspicious pigmented lesions that had undergone 3-GEP PLA testing and received a definitive positive or negative result (n = 393) were evaluated for the presence of specific clinical and dermoscopic features associated with melanoma. We found that asymmetry of color was a significant predictor for PRAME expression (Odds Ratio (OR) 5.5, 95% Confidence Interval (CI) 1.6-34.5, p = 0.004), blue color and negative pigment network were significant predictors for LINC00518 expression (adjusted OR 2.7, 95% CI 1.2-5.5, p = 0.014 and adjusted OR 5.4, 95% CI 1.6-16.9, p = 0.010, respectively), and atypical polymorphous vessels present in a pigmented skin lesion were a significant predictor for TERT promoter mutations (OR 5.8, 95% CI 1.3-23.4, p = 0.022). The results presented suggest a hierarchy in the significance of these dermoscopic features and may help guide evaluation and management of pigmented skin lesions.

NRF2 and Key Transcriptional Targets in Melanoma Redox Manipulation.

Melanocytes are dendritic, pigment-producing cells located in the skin and are responsible for its protection against the deleterious effects of solar ultraviolet radiation (UVR), which include DNA damage and elevated reactive oxygen species (ROS). They do so by synthesizing photoprotective melanin pigments and distributing them to adjacent skin cells (e.g., keratinocytes). However, melanocytes encounter a large burden of oxidative stress during this process, due to both exogenous and endogenous sources. Therefore, melanocytes employ numerous antioxidant defenses to protect themselves; these are largely regulated by the master stress response transcription factor, nuclear factor erythroid 2-related factor 2 (NRF2). Key effector transcriptional targets of NRF2 include the components of the glutathione and thioredoxin antioxidant systems. Despite these defenses, melanocyte DNA often is subject to mutations that result in the dysregulation of the proliferative mitogen-activated protein kinase (MAPK) pathway and the cell cycle. Following tumor initiation, endogenous antioxidant systems are co-opted, a consequence of elevated oxidative stress caused by metabolic reprogramming, to establish an altered redox homeostasis. This altered redox homeostasis contributes to tumor progression and metastasis, while also complicating the application of exogenous antioxidant treatments. Further understanding of melanocyte redox homeostasis, in the presence or absence of disease, would contribute to the development of novel therapies to aid in the prevention and treatment of melanomas and other skin diseases.

The Role of the Vitamin D Receptor in the Pathogenesis, Prognosis, and Treatment of Cutaneous Melanoma.

Melanoma is the malignant transformation of melanocytes and represents the most lethal form of skin cancer. While early-stage melanoma localized to the skin can be cured with surgical excision, metastatic melanoma often requires a multi-pronged approach and even then can exhibit treatment resistance. Understanding the molecular mechanisms involved in the pathogenesis of melanoma could lead to novel diagnostic, prognostic, and therapeutic strategies to ultimately decrease morbidity and mortality. One emerging candidate that may have value as both a prognostic marker and in a therapeutic context is the vitamin D receptor (VDR). VDR is a nuclear steroid hormone receptor activated by 1,25 dihydroxy-vitamin D3 [calcitriol, 1,25(OH)2D3]. While 1,25 dihydroxy-vitamin D3 is typically thought of in relation to calcium metabolism, it also plays an important role in cell proliferation, differentiation, programmed-cell death as well as photoprotection. This review discusses the role of VDR in the crosstalk between keratinocytes and melanocytes during melanomagenesis and summarizes the clinical data regarding VDR polymorphisms, VDR as a prognostic marker, and potential uses of vitamin D and its analogs as an adjuvant treatment for melanoma.