Visual Diagnosis of Dermatological Disorders: Human and Machine Performance
It addresses the global health burden of skin conditions by evaluating automated diagnostic tools, but it is incremental as it synthesizes existing research without introducing new methods.
This report reviews machine learning approaches for classifying skin diseases from images and compares their performance to human dermatologists, highlighting that recent studies show machines achieving comparable diagnostic accuracy.
Skin conditions are a global health concern, ranking the fourth highest cause of nonfatal disease burden when measured as years lost due to disability. As diagnosing, or classifying, skin diseases can help determine effective treatment, dermatologists have extensively researched how to diagnose conditions from a patient's history and the lesion's visual appearance. Computer vision researchers are attempting to encode this diagnostic ability into machines, and several recent studies report machine level performance comparable with dermatologists. This report reviews machine approaches to classify skin images and consider their performance when compared to human dermatologists. Following an overview of common image modalities, dermatologists' diagnostic approaches and common tasks, and publicly available datasets, we discuss approaches to machine skin lesion classification. We then review works that directly compare human and machine performance. Finally, this report addresses the limitations and sources of errors in image-based skin disease diagnosis, applicable to both machines and dermatologists in a teledermatology setting.