Tadesse Girmaw Abebe, Cintas Celia, Varshney Kush R, Staar Peter, Agunwa Chinyere, Speakman Skyler, Jia Justin, Bailey Elizabeth E, Adelekun Ademide, Lipoff Jules B, Onyekaba Ginikanwa, Lester Jenna C, Rotemberg Veronica, Zou James, Daneshjou Roxana
IBM Research - Africa, Nairobi, Kenya.
IBM Research - T. J. Watson, New York, NY, USA.
NPJ Digit Med. 2023 Aug 18;6(1):151. doi: 10.1038/s41746-023-00881-0.
Images depicting dark skin tones are significantly underrepresented in the educational materials used to teach primary care physicians and dermatologists to recognize skin diseases. This could contribute to disparities in skin disease diagnosis across different racial groups. Previously, domain experts have manually assessed textbooks to estimate the diversity in skin images. Manual assessment does not scale to many educational materials and introduces human errors. To automate this process, we present the Skin Tone Analysis for Representation in EDucational materials (STAR-ED) framework, which assesses skin tone representation in medical education materials using machine learning. Given a document (e.g., a textbook in .pdf), STAR-ED applies content parsing to extract text, images, and table entities in a structured format. Next, it identifies images containing skin, segments the skin-containing portions of those images, and estimates the skin tone using machine learning. STAR-ED was developed using the Fitzpatrick17k dataset. We then externally tested STAR-ED on four commonly used medical textbooks. Results show strong performance in detecting skin images (0.96 ± 0.02 AUROC and 0.90 ± 0.06 F score) and classifying skin tones (0.87 ± 0.01 AUROC and 0.91 ± 0.00 F score). STAR-ED quantifies the imbalanced representation of skin tones in four medical textbooks: brown and black skin tones (Fitzpatrick V-VI) images constitute only 10.5% of all skin images. We envision this technology as a tool for medical educators, publishers, and practitioners to assess skin tone diversity in their educational materials.
用于培训初级保健医生和皮肤科医生识别皮肤疾病的教育材料中，描绘深肤色的图像明显不足。这可能导致不同种族群体在皮肤疾病诊断方面存在差异。此前，领域专家已手动评估教科书以估计皮肤图像的多样性。手动评估无法扩展到许多教育材料，还会引入人为错误。为了使这一过程自动化，我们提出了教育材料中肤色代表性分析（STAR-ED）框架，该框架使用机器学习评估医学教育材料中的肤色代表性。给定一份文档（例如.pdf格式的教科书），STAR-ED应用内容解析以结构化格式提取文本、图像和表格实体。接下来，它识别包含皮肤的图像，分割这些图像中包含皮肤的部分，并使用机器学习估计肤色。STAR-ED是使用Fitzpatrick17k数据集开发的。然后，我们在四本常用医学教科书上对STAR-ED进行了外部测试。结果显示，在检测皮肤图像（曲线下面积为0.96±0.02，F分数为0.90±0.06）和对肤色进行分类（曲线下面积为0.87±0.01，F分数为0.91±0.00）方面表现出色。STAR-ED量化了四本医学教科书中肤色的不均衡代表性：棕色和黑色肤色（Fitzpatrick V-VI）图像仅占所有皮肤图像的10.5%。我们设想将这项技术作为医学教育工作者、出版商和从业者评估其教育材料中肤色多样性的工具。
