Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets

Recent advances in computer vision and deep learning have led to breakthroughs in the development of automated skin image analysis. In particular, skin cancer classification models have achieved performance higher than trained expert dermatologists. However, no attempt has been made to evaluate the...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Kinyanjui, Newton M, Odonga, Timothy, Cintas, Celia, Codella, Noel C F, Panda, Rameswar, Sattigeri, Prasanna, Varshney, Kush R
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 29.10.2019
Subjects
Artificial intelligence
Benchmarks
Cancer
Collection
Computer vision
Correlation analysis
Datasets
Dermatology
Image analysis
Image classification
Image detection
Image segmentation
Machine learning
Medical imaging
Populations
Representations
Skin cancer
Online AccessGet full text

Cover

More Information
Summary:Recent advances in computer vision and deep learning have led to breakthroughs in the development of automated skin image analysis. In particular, skin cancer classification models have achieved performance higher than trained expert dermatologists. However, no attempt has been made to evaluate the consistency in performance of machine learning models across populations with varying skin tones. In this paper, we present an approach to estimate skin tone in benchmark skin disease datasets, and investigate whether model performance is dependent on this measure. Specifically, we use individual typology angle (ITA) to approximate skin tone in dermatology datasets. We look at the distribution of ITA values to better understand skin color representation in two benchmark datasets: 1) the ISIC 2018 Challenge dataset, a collection of dermoscopic images of skin lesions for the detection of skin cancer, and 2) the SD-198 dataset, a collection of clinical images capturing a wide variety of skin diseases. To estimate ITA, we first develop segmentation models to isolate non-diseased areas of skin. We find that the majority of the data in the the two datasets have ITA values between 34.5{\deg} and 48{\deg}, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets. We also find no measurable correlation between performance of machine learning model and ITA values, though more comprehensive data is needed for further validation.
ISSN:2331-8422