AI ‐based anatomical recognition for bladder neck dissection in robot‐assisted radical prostatectomy
BJU International · 2026-11 · 138 (5) · 852-859
DOI: 10.1111/bju.70390 ↗Kurz gefasst
Fachartikel in der Zeitschrift BJU International, online erschienen am 26.07.2026. Verfasst von Shinnosuke Fujiwara und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, Keio University School of Medicine, Tokyo, Japan. Hauptthemen laut MEDLINE: Prostatectomy, Robotic Surgical Procedures, Artificial Intelligence, Urinary Bladder. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Japan Society for the Promotion of Science, Public Foundation of Chubu Science and Technology Center, the Japanese Society of Endourology and Robotics.
Abstract (Originalsprache)
Objective
To develop an artificial intelligence (AI) system for anatomical recognition that can automatically identify key anatomical structures during bladder neck dissection in robot‐assisted radical prostatectomy (RARP), a critical yet technically demanding step. Materials and Methods We constructed an AI model and evaluated its accuracy using 210 RARP videos from two institutions. A total of 1353 frames of bladder neck dissection were extracted from 25 videos, and the boundaries of the prostate, bladder and retrotrigonal layer were annotated. The DeepLabV3+ model was employed in developing the anatomical recognition AI model. An active learning approach was applied by iteratively retraining the model using frames with poor initial performance. The model was further evaluated using 202 independent test frames derived from seven surgeons. Segmentation performance was evaluated using the intersection over union (IoU) and Dice similarity coefficient.
Results
The IoU of the initial AI model was 0.41 for the prostate and 0.44 for the bladder. The retrained model demonstrated improved segmentation performance, with final IoU values of 0.75 and 0.68, respectively. In an independent test dataset derived from seven surgeons, segmentation performance for the prostate and bladder was maintained.
Conclusion
We developed an AI system for anatomical recognition and improved its accuracy by using retraining processes. The retrained AI model demonstrated high accuracy, and its use is anticipated to support surgeons and aid in the education of novice surgeons.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Urology, Keio University School of Medicine, Tokyo, Japan.
- Department of Surgery, Keio University School of Medicine, Tokyo, Japan.
- Department of Urology, Saiseikai Yokohamashi Tobu Hospital, Yokohama-shi, Japan.
ORCID-Profile: Shinnosuke Fujiwara, Keishiro Fukumoto, Masashi Takeuchi, Toshikazu Takeda, Kazuhiro Matsumoto, Hirofumi Kawakubo
Förderung
- Japan Society for the Promotion of Science
- Public Foundation of Chubu Science and Technology Center
- the Japanese Society of Endourology and Robotics
Zitieren
APA
Fujiwara, S., Fukumoto, K., Takeuchi, M., Konnai, Y., Yasumizu, Y., Tanaka, N., Takeda, T., Matsumoto, K., Kosaka, T., Kawakubo, H., Ishida, M., Kitagawa, Y., & Oya, M. (2026). AI ‐based anatomical recognition for bladder neck dissection in robot‐assisted radical prostatectomy. BJU International, 138(5), 852-859. https://doi.org/10.1111/bju.70390
Vancouver
Fujiwara S, Fukumoto K, Takeuchi M, Konnai Y, Yasumizu Y, Tanaka N, et al. AI ‐based anatomical recognition for bladder neck dissection in robot‐assisted radical prostatectomy. BJU International. 2026;138(5):852-859. doi:10.1111/bju.70390
BibTeX
@article{Fujiwara2026,
author = {Fujiwara, Shinnosuke and Fukumoto, Keishiro and Takeuchi, Masashi and Konnai, Yuichiro and Yasumizu, Yota and Tanaka, Nobuyuki and Takeda, Toshikazu and Matsumoto, Kazuhiro and Kosaka, Takeo and Kawakubo, Hirofumi and Ishida, Masaru and Kitagawa, Yuko and Oya, Mototsugu},
title = {AI ‐based anatomical recognition for bladder neck dissection in robot‐assisted radical prostatectomy},
journal = {BJU International},
year = {2026},
volume = {138},
number = {5},
pages = {852--859},
doi = {10.1111/bju.70390}
}
EUVIMED