Unique ID issued by UMIN | UMIN000058207 |
---|---|
Receipt number | R000066548 |
Scientific Title | Evaluation of deep learning model for enhancing surgeons' intraoperative organ recognition ability |
Date of disclosure of the study information | 2025/06/18 |
Last modified on | 2025/06/18 02:44:00 |
Evaluation of deep learning model for enhancing surgeons' intraoperative organ recognition ability
Intraoperative organ recognition ability enhancement evaluation test
Evaluation of deep learning model for enhancing surgeons' intraoperative organ recognition ability
Intraoperative organ recognition ability enhancement evaluation test
Japan |
Uterine fibroids, Adenomyosis, uterine cancer
Obstetrics and Gynecology |
Others
NO
This study aimed to develop an artificial intelligence (AI) model to assist with the intraoperative recognition of the ureter and bladder and evaluate the impact of the model on physicians' organ recognition ability.
Efficacy
Sensitivity and specificity of organ recognition tests by physicians with and without AI support
Sensitivity and specificity of organ recognition tests by physicians with and without AI support according to surgical skill level
Observational
18 | years-old | <= |
Not applicable |
Male and Female
Gynecologists who meet any of the following criteria will be included in this study.
1) Non-specialists: Obstetricians and gynecologists who do not meet the criteria in 2)
2) Specialists: Obstetricians and gynecologists who are certified by the Japan Society of Obstetrics and Gynecology and have at least five years of clinical experience in gynecology, including initial clinical training
Physicians who supervised the correct answers will be excluded from this test. Obstetricians and gynecologists deemed inappropriate by the principal investigator
16
1st name | Hiroshi |
Middle name | |
Last name | Tanabe |
National Cancer Center Hospital East
Gynecology
2778577
6-5-1 Kashiwanoha, Kashiwa-shi, Chiba
04-7133-1111
htanabe@east.ncc.go.jp
1st name | Shin |
Middle name | |
Last name | Takenaka |
National Cancer Center Hospital East
Gynecology
2778577
6-5-1 Kashiwanoha, Kashiwa-shi, Chiba
04-7133-1111
stakenak@east.ncc.go.jp
National Cancer Center
Jmees Inc.
Profit organization
National Cancer Center Ethics Committee
1-1, Tsukiji 5-chome, Chuo-ku, Tokyo
03-3542-2511
irst@ncc.go.jp
NO
2025 | Year | 06 | Month | 18 | Day |
Unpublished
16
AI assistance significantly improved sensitivity for ureter detection (43.5-58.1%, p < 0.001) and bladder detection (54.2-70.0%, p < 0.001) without reducing specificity. The additive effect of AI was greater in less experienced surgeons, with sensitivity improvements of 27.3% for ureter and 26.8% for bladder recognition. Ureter recognition was stable across surgical phases, while bladder recognition demonstrated moderate variability.
2025 | Year | 06 | Month | 18 | Day |
Main results already published
2021 | Year | 11 | Month | 01 | Day |
2022 | Year | 02 | Month | 13 | Day |
2022 | Year | 03 | Month | 01 | Day |
2026 | Year | 06 | Month | 30 | Day |
Materials and Methods: A deep learning model was trained on 13,934 ureter and 4,940 bladder images sourced from 41 institutions. Model performance was evaluated using the Dice coefficient. The performance of 16 surgeons from eight facilities was evaluated for identifying the ureter and bladder in pre-recorded surgical videos with and without AI support. Sensitivity and specificity were compared between AI-assisted and non-assisted conditions, stratified by surgeon experience.
2025 | Year | 06 | Month | 18 | Day |
2025 | Year | 06 | Month | 18 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000066548