Assessing the Generalizability of Deep Neural Networks-Based Models for Black Skin Lesions

Melanoma is the most severe type of skin cancer due to its ability to cause metastasis. It is more common in black people, often affecting acral regions: palms, soles, and nails. Deep neural networks have shown tremendous potential for improving clinical care and skin cancer diagnosis. Nevertheless, prevailing studies predominantly rely on datasets of white skin tones, neglecting to report diagnostic outcomes for diverse patient skin tones. In this work, we evaluate supervised and self-supervised models in skin lesion images extracted from acral regions commonly observed in black individuals. Also, we carefully curate a dataset containing skin lesions in acral regions and assess the datasets concerning the Fitzpatrick scale to verify performance on black skin. Our results expose the poor generalizability of these models, revealing their favorable performance for lesions on white skin. Neglecting to create diverse datasets, which necessitates the development of specialized models, is unacceptable. Deep neural networks have great potential to improve diagnosis, particularly for populations with limited access to dermatology. However, including black skin lesions is necessary to ensure these populations can access the benefits of inclusive technology.

黑色素瘤（Melanoma）是最为凶险的皮肤癌亚型，因其具备引发远处转移的能力。该癌症在黑人群体中更为高发，常累及肢端区域：手掌、足底及指甲。深度神经网络（Deep Neural Networks）在改善临床诊疗与皮肤癌诊断方面展现出巨大潜力。然而，当前主流研究大多依赖于浅肤色人群的数据集，未针对不同肤色患者报告其诊断性能。本研究针对从黑人群体常见肢端部位提取的皮肤病变图像，对监督学习与自监督学习模型开展评估。此外，我们精心构建了包含肢端皮肤病变的数据集，并基于菲茨帕特里克肤色分型（Fitzpatrick scale）对该数据集进行标注，以验证模型在黑人肤色病变上的诊断性能。研究结果显示，此类模型的泛化能力较差，仅在浅肤色人群的皮肤病变上表现优异。忽视构建多样化数据集的做法不可接受——这将制约适配不同人群的专用模型开发。深度神经网络在提升皮肤癌诊断水平方面具备巨大潜力，尤其对于难以获取皮肤科诊疗服务的人群而言意义重大。然而，必须纳入黑人肤色的皮肤病变数据，才能确保这些人群能够享受到普惠性技术带来的诊疗益处。