Amelanotic melanoma: Diagnostic challenges, treatment innovations, and the emerging role of in early detection

Abstract

Amelanotic melanoma (AM) is a rare, yet aggressive melanoma subtype often overlooked due to its minimal pigmentation and atypical presentations. Conventional diagnostic tools, such as the “ABCDE” criteria and dermoscopy, frequently fail to detect AM in early stages, leading to delayed diagnoses and advanced disease. Advanced imaging techniques like reflectance confocal microscopy (RCM) and optical coherence tomography (OCT) have improved detection accuracy, but underdiagnosis remains a significant challenge. Recent molecular insights, including TERT promoter mutations and BRAF/KIT alterations, have refined risk stratification and guided personalized treatments. However, immunoresistance and diagnostic complexity continue to hinder outcomes in advanced cases. Artificial intelligence (AI) offers transformative potential by addressing these gaps through its ability to analyze subtle vascular and morphological patterns often missed by clinicians. When integrated with molecular diagnostics, AI enables earlier detection, precise staging, and tailored therapeutic strategies. For instance, AI-powered tools can incorporate genetic and imaging data to predict treatment responses and optimize patient selection. Emerging approaches, such as SPION-functionalized CAR-T cells, liquid biopsies, and multimodal AI tools, promise further advancements in diagnostic precision and treatment efficacy. This review highlights the importance of combining AI with molecular diagnostics to achieve more precise, personalized, and equitable care for AM. Collaborative efforts among dermatologists and oncologists, and data scientists are essential to translate these innovations into practice and address disparities in outcomes for this challenging melanoma subtype.