DDI - Diverse Dermatology Images

Artificial intelligence (AI) may aid in triaging skin diseases. However, most AI models have not been rigorously assessed on images of diverse skin tones or uncommon diseases. To ascertain potential biases in algorithm performance in this context, we curated the Diverse Dermatology Images (DDI) dataset—the first publicly available, deeply curated, and pathologically confirmed image dataset with diverse skin tones. The DDI was retrospectively selected from reviewing pathology reports in Stanford Clinics from 2010-2020 with further details provided in the methods. After filtering out images that were poor quality (see methods), there were a total of 656 images representing 570 unique patients (Supplemental Table 2 and 3). The dataset comprised a retrospective convenience sample across all images of FST I-VI but was also designed to allow direct comparison between FST I-II and FST V-VI by matching diagnostic category, age within 10 years, gender, and date of photograph within 3 years (online methods). There was no significant difference in photo quality scores between FST I-II photos and FST V-VI photos (Mann-Whitney U, p = 0.33). There were a total of 208 images of FST I-II (159 benign, 49 malignant), 241 images of FST III-IV (167 benign, 74 malignant), and 207 images of FST V-VI (159 benign and 48 malignant).

人工智能（AI）可辅助皮肤病分诊。然而，当前绝大多数AI模型尚未针对不同肤色或罕见皮肤病的影像进行严格评估。为明确此类场景下算法性能可能存在的偏倚，我们构建了多样化皮肤病影像（Diverse Dermatology Images, DDI）数据集——这是首个公开可用、经深度整理且经病理确认的多肤色皮肤病影像数据集。该数据集的影像回溯选取自2010至2020年斯坦福诊所的病理报告，详细信息参见研究方法部分。经筛选剔除质量不佳的影像后（筛选标准参见研究方法），最终共保留656张影像，对应570名独特患者（详见补充表2与表3）。本数据集为回顾性方便抽样，涵盖FST I至VI型所有影像，同时通过匹配诊断类别、年龄差≤10岁、性别以及拍摄时间差≤3年的方式，实现FST I-II型与FST V-VI型影像的直接对照（在线方法部分有详细说明）。FST I-II型与FST V-VI型影像的质量评分无显著差异（曼-惠特尼U检验，p=0.33）。其中FST I-II型影像共208张（良性159张，恶性49张），FST III-IV型影像共241张（良性167张，恶性74张），FST V-VI型影像共207张（良性159张，恶性48张）

搜集汇总

背景与挑战

背景概述

DDI - Diverse Dermatology Images 是一个首个公开、深度整理且病理确认的多样肤色皮肤病图像数据集，旨在评估AI模型在多样肤色和罕见疾病上的潜在偏见。该数据集包含656张回顾性选取的图像，覆盖FST I-VI所有肤色类型，并设计为允许直接比较不同肤色组（如FST I-II与FST V-VI），匹配诊断、年龄、性别等关键变量，以促进无偏见的AI研究。