AI performance in oral cytology for differentiating poorly defined tumor cells from reactive atypia
Discriminating ill-defined tumor cells from atypical non-neoplastic cells based solely on morphology is challenging. Classifying suspicious cells as cancer often results in numerous false positives. Conversely, AI trained on normal and cancer can reveal previously unnoticed cancerous features in suspicious cells.
Authors
- Masakuni Okamoto
- Yuko Kondo (ORCID: https://orcid.org/0000-0001-5353-3351)
- Kaori Oya (ORCID: https://orcid.org/0000-0003-3815-0656)
- Kazunori Nozaki (ORCID: https://orcid.org/0000-0003-3378-0915)
- Satoru Toyosawa (ORCID: https://orcid.org/0000-0002-0338-0251)
- Kazuma Kokomoto
- Sunao Sato (ORCID: https://orcid.org/0000-0002-1959-5943)
- Mitsunobu Kishino
Institutions
- Takarazuka University of Medical and Health Care (JP)
- Osaka University Hospital (JP)
- The University of Osaka (JP)
Publication Details
- Journal
- Journal of Oral Biology and Craniofacial Research
- Published
- 2025-10-18
- DOI
- https://doi.org/10.1016/j.jobcr.2025.10.003
- Citations
- 3
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 7.44