Detection of the DEJ and Segmentation of Its Morphological Patterns in RCM Images of Melanocytic Skin Lesions
Apr 20, 2020·
,,,,,·
0 min read
Kivanc Kose
Alican Bozkurt
Christi Alessi-Fox
Melissa Gill
Dana H. Brooks
Jennifer G. Dy
Milind Rajadhyaksha
Abstract
The dermo-epidermal junction (DEJ) is a key anatomical boundary in skin that is clinically important for diagnosing melanocytic lesions using reflectance confocal microscopy (RCM). In this work, we present a deep learning method for detecting the DEJ layer and segmenting the characteristic morphological patterns observed at the DEJ in RCM images of melanocytic skin lesions.
Type
Publication
In Biophotonics Congress: Biomedical Optics 2020 (Microscopy, Histopathology, and Analytics), paper MW2A.1
Authors
AI Scientist
I am an AI Scientist at Paige AI. I did my Ph.D. with Jennifer Dy, Dana Brooks, and Jan-Willem van de Meent at Northeastern University. My main research interests are machine learning with emphasis on probabilistic programming, deep neural networks, and their applications in biomedical image processing. I am one of the developers of Probabilistic Torch, a library for deep generative models that extends PyTorch. I am also one of the maintainers of the PyTorch distributions module.