Closing the AI generalization gap by adjusting for dermatology condition distribution differences across clinical settings
Authors:
- Rachna SahasrabudheRSRachna Sahasrabudhe
Preprint
Abstract
Recently, there has been great progress in the ability of artificial intelligence (AI) algorithms to classify dermatological conditions from clinical photographs. However, little is known about the robustness of these algorithms in real-world settings where several factors can lead to a loss of generalizability. Understanding and overcoming these limitations will permit the development of generalizable AI that can aid in the diagnosis of skin conditions across a variety of clinical settings. In this retrospective study, we demonstrate that differences in skin condition distribution, rather than in demographics or image capture mode are the main source of errors when an AI algorithm is evaluated on data from a previously unseen source. We demonstrate a series of steps to close this generalization gap, requiring progressively more information about the new source, ranging from the condition distribution to training data enriched for data less frequently seen during training. Our results also suggest comparable performance from end-to-end fine tuning versus fine tuning solely the classification layer on top of a frozen embedding model. Our approach can inform the adaptation of AI algorithms to new settings, based on the information and resources available.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- A reinforcement learning model for AI-based decision support in skin cancerNature Medicine, 2023
- Quality and Perceived Usefulness of Patient-Submitted Store-and-Forward Teledermatology ImagesJAMA Dermatology, 2022
- Deep Learning in Dermatology: A Systematic Review of Current Approaches, Outcomes, and LimitationsJID Innovations, 2022
- Artificial intelligence-based clinical decision support in pediatricsPediatric Research, 2022
- Analysis of the ISIC image datasets: Usage, benchmarks and recommendationsMedical Image Analysis, 2022
- Seasonal and gender variation in skin disease: A cross-sectional study of 3120 patients at Razi hospitalInternational Journal of Women's Dermatology, 2021
- Big Transfer (BiT): General Visual Representation Learning2020
- A deep learning system for differential diagnosis of skin diseasesNature Medicine, 2020
- Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditionsAnnals of Oncology, 2020
- Keratinocytic Skin Cancer Detection on the Face Using Region-Based Convolutional Neural NetworkJAMA Dermatology, 2020