Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets

by   Newton M. Kinyanjui, et al.

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 and 48, 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.


page 6

page 7

page 8


Out-of-Distribution Detection in Dermatology using Input Perturbation and Subset Scanning

Recent advances in deep learning have led to breakthroughs in the develo...

Model Patching: Closing the Subgroup Performance Gap with Data Augmentation

Classifiers in machine learning are often brittle when deployed. Particu...

Towards Highly Expressive Machine Learning Models of Non-Melanoma Skin Cancer

Pathologists have a rich vocabulary with which they can describe all the...

The HAM10000 Dataset: A Large Collection of Multi-Source Dermatoscopic Images of Common Pigmented Skin Lesions

Training of neural networks for automated diagnosis of pigmented skin le...

Recent advances in deep learning applied to skin cancer detection

Skin cancer is a major public health problem around the world. Its early...

AI-Skin : Skin Disease Recognition based on Self-learning and Wide Data Collection through a Closed Loop Framework

There are a lot of hidden dangers in the change of human skin conditions...

Please sign up or login with your details

Forgot password? Click here to reset