Unsupervised Approaches for Out-Of-Distribution Dermoscopic Lesion Detection
This addresses the challenge of identifying anomalous skin lesions in medical imaging without labeled data, but it appears incremental as it builds on existing techniques like SimCLR and LOF.
The paper tackled the problem of detecting out-of-distribution dermoscopic lesions using unsupervised methods, showing that their SimCLR-LOF algorithm achieves results competitive with state-of-the-art supervised approaches on the ISIC 2019 dataset.
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.