Diagnostic and Prognostic Deep Learning Applications for Histological Assessment of Cutaneous Melanoma

SIMPLE SUMMARY: Melanoma is one of the most common malignancies in the United States. For the diagnosis of melanoma, histology images are examined by a trained pathologist. While this is the current gold standard for cancer diagnosis, this process requires substantial time and work and at a considerable cost. Moreover, histological diagnosis also adds diagnostic variability. Artificial intelligence is a valuable tool to aid this process. It can detect small image features that are unrecognizable to the human eye and improve diagnostic accuracy and prognostic classification. Here, we comprehensively review recent studies on the application of artificial intelligence for diagnosing and assessing the prognosis of melanoma based on pathology images. ABSTRACT: Melanoma is among the most devastating human malignancies. Accurate diagnosis and prognosis are essential to offer optimal treatment. Histopathology is the gold standard for establishing melanoma diagnosis and prognostic features. However, discrepancies often exist between pathologists, and analysis is costly and time-consuming. Deep-learning algorithms are deployed to improve melanoma diagnosis and prognostication from histological images of melanoma. In recent years, the development of these machine-learning tools has accelerated, and machine learning is poised to become a clinical tool to aid melanoma histology. Nevertheless, a review of the advances in machine learning in melanoma histology was lacking. We performed a comprehensive literature search to provide a complete overview of the recent advances in machine learning in the assessment of melanoma based on hematoxylin eosin digital pathology images. In our work, we review 37 recent publications, compare the methods and performance of the reviewed studies, and highlight the variety of promising machine-learning applications in melanoma histology.