An explainable unsupervised learning approach for anomaly detection on corneal in vivo confocal microscopy images
This study presents an efficient and interpretable unsupervised anomaly detection model for IVCM images, effectively identifying corneal abnormalities without requiring labeled pathological samples. The proposed method enhances screening efficiency, reduces annotation costs, and holds great potential for scalable intelligent diagnosis of corneal diseases.
Authors
- Jimmy Xiangji Huang (ORCID: https://orcid.org/0000-0003-1292-1491)
- Y. H. Meng (ORCID: https://orcid.org/0000-0002-6734-8779)
- Qianqian Lan (ORCID: https://orcid.org/0000-0001-8917-6659)
- Xipeng Pan (ORCID: https://orcid.org/0000-0003-2581-0520)
- Fan Xu (ORCID: https://orcid.org/0000-0002-1504-2356)
- Rushi Lan (ORCID: https://orcid.org/0000-0002-9488-8236)
- Daizai Lei (ORCID: https://orcid.org/0000-0002-7001-8172)
- Yikun Qin
- Huadeng Wang (ORCID: https://orcid.org/0000-0003-0966-5781)
- Shanshan Huang (ORCID: https://orcid.org/0000-0003-2757-6184)
- Fen Tang (ORCID: https://orcid.org/0000-0001-9762-5231)
- Qi Chen (ORCID: https://orcid.org/0000-0003-3773-4641)
- Li Jiang (ORCID: https://orcid.org/0000-0001-7058-6957)
- Ningning Tang (ORCID: https://orcid.org/0000-0002-5804-0369)
- Wenjing He
- L. Huang
Institutions
- Guangxi Medical University (CN)
- Beibu Gulf University (CN)
- Guilin University of Electronic Technology (CN)
Publication Details
- Journal
- Frontiers in Bioengineering and Biotechnology
- Published
- 2025-06-06
- DOI
- https://doi.org/10.3389/fbioe.2025.1576513
- Primary Topic
- Anomaly Detection Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Natural Science Foundation of Guangxi Province
- Guangxi Key Research and Development Program