Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot Study
Objectives: Studies have suggested that computer-aided polyp detection using artificial intelligence improves adenoma identification during colonoscopy. However, its real-world effectiveness remains unclear. Therefore, this study evaluated the usefulness of computer-aided detection during regular su...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Japan Society of Coloproctology
2025-01-01
|
| Series: | Journal of the Anus, Rectum and Colon |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/jarc/9/1/9_2024-055/_pdf/-char/en |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832584919031742464 |
|---|---|
| author | Shin Morimoto Hidenori Tanaka Yudai Takehara Noriko Yamamoto Fumiaki Tanino Yuki Kamigaichi Ken Yamashita Hidehiko Takigawa Yuji Urabe Toshio Kuwai Shiro Oka |
| author_facet | Shin Morimoto Hidenori Tanaka Yudai Takehara Noriko Yamamoto Fumiaki Tanino Yuki Kamigaichi Ken Yamashita Hidehiko Takigawa Yuji Urabe Toshio Kuwai Shiro Oka |
| author_sort | Shin Morimoto |
| collection | DOAJ |
| description | Objectives: Studies have suggested that computer-aided polyp detection using artificial intelligence improves adenoma identification during colonoscopy. However, its real-world effectiveness remains unclear. Therefore, this study evaluated the usefulness of computer-aided detection during regular surveillance colonoscopy.
Methods: Consecutive patients who underwent surveillance colonoscopy with computer-aided detection between January and March 2023 and had undergone colonoscopy at least twice during the past 3 years were recruited. The clinicopathological findings of lesions identified using computer-aided detection were evaluated. The detection ability was sub-analyzed based on the expertise of the endoscopist and the presence of diminutive adenomas (size 5 mm).
Results: A total of 78 patients were included. Computer-aided detection identified 46 adenomas in 28 patients; however, no carcinomas were identified. The mean withdrawal time was 824 ± 353 s, and the mean tumor diameter was 3.3 mm (range, 2-8 mm). The most common gross type was 0-Is (70%), followed by 0-Isp (17%) and 0-IIa (13%). The most common tumor locations were the ascending colon and sigmoid colon (28%), followed by the transverse colon (26%), cecum (7%), descending colon (7%), and rectum (4%). Overall, 34.1% and 38.2% of patients with untreated diminutive adenomas and those with no adenomas, respectively, had newly detected adenomas. Endoscopist expertise did not affect the results.
Conclusions: Computer-aided detection may help identify adenomas during surveillance colonoscopy for patients with untreated diminutive adenomas and those with a history of endoscopic resection. |
| format | Article |
| id | doaj-art-31fdb618b7d54b5eb4ebd0e1dfecb4ca |
| institution | Kabale University |
| issn | 2432-3853 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | The Japan Society of Coloproctology |
| record_format | Article |
| series | Journal of the Anus, Rectum and Colon |
| spelling | doaj-art-31fdb618b7d54b5eb4ebd0e1dfecb4ca2025-01-27T10:02:40ZengThe Japan Society of ColoproctologyJournal of the Anus, Rectum and Colon2432-38532025-01-019112713310.23922/jarc.2024-0552024-055Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot StudyShin Morimoto0Hidenori Tanaka1Yudai Takehara2Noriko Yamamoto3Fumiaki Tanino4Yuki Kamigaichi5Ken Yamashita6Hidehiko Takigawa7Yuji Urabe8Toshio Kuwai9Shiro Oka10Department of Gastroenterology, Hiroshima University HospitalDepartment of Gastroenterology, Hiroshima University HospitalDepartment of Gastroenterology, Hiroshima University HospitalDepartment of Gastroenterology, Hiroshima University HospitalDepartment of Gastroenterology, Hiroshima University HospitalDepartment of Gastroenterology, Hiroshima University HospitalDepartment of Gastroenterology, Hiroshima University HospitalDepartment of Gastroenterology, Hiroshima University HospitalDepartment of Gastroenterology, Hiroshima University HospitalGastrointestinal Endoscopy and Medicine, Hiroshima University HospitalDepartment of Gastroenterology, Hiroshima University HospitalObjectives: Studies have suggested that computer-aided polyp detection using artificial intelligence improves adenoma identification during colonoscopy. However, its real-world effectiveness remains unclear. Therefore, this study evaluated the usefulness of computer-aided detection during regular surveillance colonoscopy. Methods: Consecutive patients who underwent surveillance colonoscopy with computer-aided detection between January and March 2023 and had undergone colonoscopy at least twice during the past 3 years were recruited. The clinicopathological findings of lesions identified using computer-aided detection were evaluated. The detection ability was sub-analyzed based on the expertise of the endoscopist and the presence of diminutive adenomas (size 5 mm). Results: A total of 78 patients were included. Computer-aided detection identified 46 adenomas in 28 patients; however, no carcinomas were identified. The mean withdrawal time was 824 ± 353 s, and the mean tumor diameter was 3.3 mm (range, 2-8 mm). The most common gross type was 0-Is (70%), followed by 0-Isp (17%) and 0-IIa (13%). The most common tumor locations were the ascending colon and sigmoid colon (28%), followed by the transverse colon (26%), cecum (7%), descending colon (7%), and rectum (4%). Overall, 34.1% and 38.2% of patients with untreated diminutive adenomas and those with no adenomas, respectively, had newly detected adenomas. Endoscopist expertise did not affect the results. Conclusions: Computer-aided detection may help identify adenomas during surveillance colonoscopy for patients with untreated diminutive adenomas and those with a history of endoscopic resection.https://www.jstage.jst.go.jp/article/jarc/9/1/9_2024-055/_pdf/-char/enadenomaartificial intelligencecolorectal neoplasmcost-effectiveness analysisearly diagnosis |
| spellingShingle | Shin Morimoto Hidenori Tanaka Yudai Takehara Noriko Yamamoto Fumiaki Tanino Yuki Kamigaichi Ken Yamashita Hidehiko Takigawa Yuji Urabe Toshio Kuwai Shiro Oka Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot Study Journal of the Anus, Rectum and Colon adenoma artificial intelligence colorectal neoplasm cost-effectiveness analysis early diagnosis |
| title | Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot Study |
| title_full | Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot Study |
| title_fullStr | Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot Study |
| title_full_unstemmed | Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot Study |
| title_short | Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot Study |
| title_sort | efficiency of real time computer aided polyp detection during surveillance colonoscopy a pilot study |
| topic | adenoma artificial intelligence colorectal neoplasm cost-effectiveness analysis early diagnosis |
| url | https://www.jstage.jst.go.jp/article/jarc/9/1/9_2024-055/_pdf/-char/en |
| work_keys_str_mv | AT shinmorimoto efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT hidenoritanaka efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT yudaitakehara efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT norikoyamamoto efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT fumiakitanino efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT yukikamigaichi efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT kenyamashita efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT hidehikotakigawa efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT yujiurabe efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT toshiokuwai efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy AT shirooka efficiencyofrealtimecomputeraidedpolypdetectionduringsurveillancecolonoscopyapilotstudy |