Hyperbolic Geometry-Driven Robustness Enhancement for Rare Skin Disease Diagnosis
Hu Y. Chen Y. Xing X. Zhang J. Yerzhanuly B.M. Matkerim B. Xia Y.
2025Institute of Electrical and Electronics Engineers Inc.
IEEE Journal of Biomedical and Health Informatics
2025#29Issue 32161 - 2171 pp.
The automated diagnosis of rare skin diseases using dermoscopy images, known as a few-shot learning (FSL) problem, remains challenging, since traditional FSL research tends to disregard the intrinsic hierarchical nature of rare diseases and data uncertainty. To address these issues, we propose to conduct rare skin disease diagnosis in hyperbolic space, which facilitates implicit class hierarchical structures and precise uncertainty measurement due to pivotal geometrical properties. We propose a Hyperbolic Geometry-driven Robustness Enhancement (HGRE) framework specifically tailored for diagnosing rare skin diseases. The HGRE framework uses implicit hierarchical relation in the hyperbolic space to better represent the features of rare diseases. Moreover, the framework incorporates an Adversarial Proxy Construction (APC) module to address the problem of data uncertainty. Specifically, the APC module uses the distance to the hyperbolic space origin as an indicator of uncertainty to filter and construct adversarial proxies for each uncertain prototype to achieve adversarial robust training. Leveraging the two unique geometrical properties, our HGRE framework effectively addresses the limitations of insufficient hierarchical relation utilization and data uncertainty in FSL-based rare skin disease diagnosis. This enhancement of the models robustness in training has been corroborated by extensive empirical validation on two skin lesion datasets, where HGREs performance notably surpassed existing state-of-the-art FSL methods.
adversarial learning , Few-shot classification , hyperbolic space , rare skin diseases
Text of the article Перейти на текст статьи
Northwestern Polytechnical University, School of Computer Science and Engineering, Xian, 710072, China
Xian Jiaotong University Health Science Center, Department of Cell Biology and Genetics, School of Basic Medical Sciences, Xian, 710061, China
Stanford University, Department of Radiation Oncology, Stanford, 94305, CA, United States
Ningbo No.2 Hospital, Ningbo, 315000, China
Northwestern Polytechnical University Kazakhstan Branch, Almaty, 050040, Kazakhstan
Al-Farabi Kazakh National University, Almaty, 050040, Kazakhstan
Northwestern Polytechnical University
Xian Jiaotong University Health Science Center
Stanford University
Ningbo No.2 Hospital
Northwestern Polytechnical University Kazakhstan Branch
Al-Farabi Kazakh National University
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026