Providing Prognostic and Diagnostic Tools towards Melanoma Diagnosis

Abstract

The number of melanoma diagnoses has increased dramatically over the past three decades, outpacing almost all other cancers. Nearly 1 in 4 skin biopsies are of melanocytic lesions, highlighting the clinical and public health importance of correct diagnosis. Pathologists analyze biopsy material at both the cellular and structural level to determine diagnosis and cancer stage. Deep learning image analysis methods may improve and complement current diagnostic and prognostic capabilities. Mitotic figures are surrogate biomarkers of cellular proliferation that can provide prognostic information; thus, their precise detection is an important factor for clinical care. In addition, semantic segmentation of clinically important structures in skin biopsies is a crucial step toward an accurate diagnosis. We aim to provide prognostic and diagnostic information that consists of the detection of cellular level entities, clinically important structures, and other important factors in the diagnosis of skin biopsy images. This dissertation contains four main projects on melanocytic lesion biopsy images: mitotic figure classification, semantic segmentation of clinically important tissue structures, classification of segmented dermal nests, and improving whole slide image diagnosis using segmentation masks.