Presentation
7 March 2022 Unsupervised representation learning for detecting out of distribution samples in dermoscopy images of eight types of skin lesions
Max Torop, Wenqian Liu, Dana H. Brooks, Milind Rajadhyaksha, Jennifer G. Dy, Octavia Camps, Sandesh Ghimire, Kivanc Kose
Author Affiliations +
Abstract
We present the initial results of two unsupervised out-of-distribution (OOD) detection algorithms, designed to flag dermoscopic images of lesions from classes not seen during training. When evaluated on the ISIC 2019 dataset - using 6 classes as in-distribution and 2 as OOD - the scores from our algorithms produced AUROC’s of 0.694/0.642. The images in ISIC 2019 mainly come from two datasets - HAM and BCN. When restricting our evaluation to consider only images from HAM the AUROC was 0.758/0.765, and when considering the images from BCN only, the AUROC dropped to 0.645/0.504.
Conference Presentation
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Max Torop, Wenqian Liu, Dana H. Brooks, Milind Rajadhyaksha, Jennifer G. Dy, Octavia Camps, Sandesh Ghimire, and Kivanc Kose "Unsupervised representation learning for detecting out of distribution samples in dermoscopy images of eight types of skin lesions", Proc. SPIE PC11934, Photonics in Dermatology and Plastic Surgery 2022, PC119340H (7 March 2022); https://doi.org/10.1117/12.2609885
Advertisement
Advertisement
KEYWORDS
Skin

Diagnostics

Tumor growth modeling

Dermatology

Detection and tracking algorithms

Image analysis

Image classification

Back to Top