Rokken logo
English

Research on an AI Model for Real-Time Ureteral Orifice Recognition During Cystoscopy Published in Scientific Reports

Published on

【Announcement】

Rokken Inc. is pleased to announce that a collaborative research paper entitled “Development and validation of a real-time AI model for ureteral orifice recognition during cystoscopy for fluorescence ureteral navigation” has been published in Scientific Reports.
The study was conducted by Dr. Shunjin Ryu and colleagues from the Department of Digestive Surgery at Kawaguchi Municipal Medical Center, with Rokken participating as a research collaborator.

The study developed an AI model that identifies and highlights ureteral orifices in real time from cystoscopy video, supporting the placement of fluorescent ureteral catheters.　　

The model’s performance was also validated using an independent set of videos that had not been used for training or tuning.

The evaluation demonstrated the model’s ability to identify and highlight ureteral orifices in real time. This research represents a step toward the practical application of AI-assisted catheter placement for fluorescence ureteral navigation.
Further validation across diverse clinical settings is expected to expand the potential for AI use in clinical practice.

Yasukazu Sakamoto, Kengo Toyama, Maxime Lenfant, Thomas Henn, Clement Jacquet, and Ian Ledig from Rokken contributed as co-authors, participating in AI model development and technical implementation.

We invite those interested in this research to read the paper.

News