Validation of a Rule-Based Automated Method for RPE Cell Detection Using Adaptive Optics Transscleral Flood Illumination
Masakazu Hiraoka, Marika Taniguchi, Leandre Fura, Shuhei Kimura, Michiko Mandai, Masayo Takahashi, Yasuo Kurimoto, Akiko Maeda · 2026
Read Validation of a Rule-Based Automated Method for RPE Cell Detection Using Adaptive Optics Transscleral Flood Illumination by Masakazu Hiraoka, Marika Taniguchi, Leandre Fura, Shuhei Kimura, Michiko Mandai, Masayo Takahashi, Yasuo Kurimoto, Akiko Maeda (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13225296.txt.
Description
Counting the light-sensing support cells of the retina by hand is slow, and Masakazu Hiraoka and co-authors validate an automatic counter. Their images come from an adaptive optics camera that shines light through the white of the eye to photograph the retinal pigment layer. The rule-based method finds cells as bright peaks, filters them by spacing, and was tuned on thirty sample regions.
On thirty-nine fresh regions from healthy eyes and eyes with retinitis pigmentosa, the scores for how well the method matched hand counts ran from fifty-five hundredths up to ninety-two hundredths. The mean score was eighty hundredths. Two human graders agreed with each other more than either agreed with the machine, and that gap held for both kinds of eye. The scores stayed steady as image noise varied.
Catalog record
| CREATOR | Masakazu Hiraoka, Marika Taniguchi, Leandre Fura, Shuhei Kimura, Michiko Mandai, Masayo Takahashi, Yasuo Kurimoto, Akiko Maeda |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |