Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection

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

Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection

Image and Video Processing 2021-11-10 v1 Computer Vision and Pattern Recognition Machine Learning

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

View on arXiv ↗ PDF ↗

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.

Keywords

out-of-distribution detection unsupervised learning dermoscopic images simclr-lof medical image analysis isic dataset

Cite

@article{arxiv.2111.04807,
  title  = {Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection},
  author = {Max Torop and Sandesh Ghimire and Wenqian Liu and Dana H. Brooks and Octavia Camps and Milind Rajadhyaksha and Jennifer Dy and Kivanc Kose},
  journal= {arXiv preprint arXiv:2111.04807},
  year   = {2021}
}

Comments

NeurIPS: Medical Imaging Meets NeurIPS Workshop

Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection

Abstract

Keywords

Cite

Comments

Related papers