Work

Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection

Year: 2021

Type: preprint

Abstract: There are limited works showing the efficacy of unsupervised Out-of-Distribution (OOD) methods on complex medical data. Here, we present preliminary findings of our unsupervised OOD detection algorithm, SimCLR-LOF, as well as a recent state of the art approach (SSD), applied on medical images. SimCLR-LOF learns semantically meaningful features using SimCLR and uses LOF for scoring if a test sample is OOD. We evaluated on the multi-source International Skin Imaging Collaboration (ISIC) 2019 dataset, and show results that are competitive with SSD as well as with recent supervised approaches applied on the same data.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2111.04807

Authors: Torop, Max, Ghimire, Sandesh, Liu, Wenqian, Brooks, Dana H., Camps, Octavia, Rajadhyaksha, Milind, Dy, Jennifer, Kose, Kivanc

Institutions: Northeastern University, Memorial Sloan Kettering Cancer Center

Language: English

Topic: Cutaneous Melanoma Detection and Management

Subfield: Oncology

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: green

Funders: National Science Foundation, Memorial Sloan-Kettering Cancer Center, National Institutes of Health, National Cancer Institute

Awards: Confocal video-mosaicking microscopy to guide surgery of superficially spreading skin cancers, G289723095, Automated Image Guidance for Diagnosing Skin Cancer With Confocal Microscopy, CPS:Medium: Safe Learning-Enabled Cyberphysical Systems, G7194429559, RI:Small: Dynamic and Statistical Based Invariants on Manifolds for Video Analysis, Cancer Center Support Grant

OpenAlex ID: W3214278233

Cites: 12

Cited by: 1

Related to: 10