Machine Learning-based Analysis of UF-5000 Scattergrams Improves the Identification of Urinary Dysmorphic Red Blood Cells
A scattergram-based ML model improves the accuracy and reliability of urinary RBC morphological classification based on UF-5000 scattergrams and may help reduce reliance on invasive diagnostics. Prospective, multicenter studies should validate generalizability and assess integration into routine workflows.
Authors
- Rin Yokoyama (ORCID: https://orcid.org/0009-0000-5524-8087)
- Takashi Hisasue (ORCID: https://orcid.org/0009-0002-8385-6308)
- Kenichi Shukuya (ORCID: https://orcid.org/0000-0002-8405-4262)
- Teruhiko Yoshida (ORCID: https://orcid.org/0000-0002-2049-7347)
- Makoto Kurano (ORCID: https://orcid.org/0000-0002-2596-1145)
- Yoshifumi Morita (ORCID: https://orcid.org/0000-0001-9129-0223)
- Naru Nakatsuka (ORCID: https://orcid.org/0009-0001-3867-7389)
- Yumeto ONO (ORCID: https://orcid.org/0009-0000-4739-1983)
- Masami Tanaka (ORCID: https://orcid.org/0009-0002-4829-6077)
Institutions
- Juntendo University (JP)
- University of Tokyo Hospital (JP)
- The University of Tokyo (JP)
Publication Details
- Journal
- Annals of Laboratory Medicine
- Published
- 2025-11-05
- DOI
- https://doi.org/10.3343/alm.2025.0227
- Primary Topic
- Digital Holography and Microscopy
- Type
- article
- Field-Weighted Citation Impact
- 0.00