Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy Video
Artificial-intelligence-based computer-aided diagnosis (CAD) systems have developed remarkably in recent years. These systems can help increase the adenoma detection rate (ADR), an important quality indicator in colonoscopies. While there have been many still-image-based studies on the usefulness of...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/12/14/4840 |
| _version_ | 1797588808134295552 |
|---|---|
| author | Yoshitsugu Misumi Kouichi Nonaka Miharu Takeuchi Yu Kamitani Yasuhiro Uechi Mai Watanabe Maiko Kishino Teppei Omori Maria Yonezawa Hajime Isomoto Katsutoshi Tokushige |
| author_facet | Yoshitsugu Misumi Kouichi Nonaka Miharu Takeuchi Yu Kamitani Yasuhiro Uechi Mai Watanabe Maiko Kishino Teppei Omori Maria Yonezawa Hajime Isomoto Katsutoshi Tokushige |
| author_sort | Yoshitsugu Misumi |
| collection | DOAJ |
| description | Artificial-intelligence-based computer-aided diagnosis (CAD) systems have developed remarkably in recent years. These systems can help increase the adenoma detection rate (ADR), an important quality indicator in colonoscopies. While there have been many still-image-based studies on the usefulness of CAD, few have reported on its usefulness using actual clinical videos. However, no studies have compared the CAD group and control groups using the exact same case videos. This study aimed to determine whether CAD or endoscopists were superior in identifying colorectal neoplastic lesions in videos. In this study, we examined 34 lesions from 21 cases. CAD performed better than four of the six endoscopists (three experts and three beginners), including all the beginners. The time to lesion detection with beginners and experts was 2.147 ± 1.118 s and 1.394 ± 0.805 s, respectively, with significant differences between beginners and experts (<i>p</i> < 0.001) and between beginners and CAD (both <i>p</i> < 0.001). The time to lesion detection was significantly shorter for experts and CAD than for beginners. No significant difference was found between experts and CAD (<i>p</i> = 1.000). CAD could be useful as a diagnostic support tool for beginners to bridge the experience gap with experts. |
| first_indexed | 2024-03-11T00:57:19Z |
| format | Article |
| id | doaj.art-0e6a12682475438990f204f795d4db39 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-11T00:57:19Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-0e6a12682475438990f204f795d4db392023-11-18T19:54:46ZengMDPI AGJournal of Clinical Medicine2077-03832023-07-011214484010.3390/jcm12144840Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy VideoYoshitsugu Misumi0Kouichi Nonaka1Miharu Takeuchi2Yu Kamitani3Yasuhiro Uechi4Mai Watanabe5Maiko Kishino6Teppei Omori7Maria Yonezawa8Hajime Isomoto9Katsutoshi Tokushige10Department of Digestive Endoscopy, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanDepartment of Digestive Endoscopy, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanDepartment of Digestive Endoscopy, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanDepartment of Digestive Endoscopy, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanDepartment of Digestive Endoscopy, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanDepartment of Digestive Endoscopy, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanDepartment of Digestive Endoscopy, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanInstitute of Gastroenterology, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanInstitute of Gastroenterology, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanDivision of Gastroenterology and Nephrology, Department of Multidisciplinary Internal Medicine, Faculty of Medicine, Tottori University, 36-1, Nishi-Chou, Yonago 683-8504, JapanInstitute of Gastroenterology, Tokyo Women’s Medical University Hospital, 8-1, Kawada-Chou, Shinjuku-Ku, Tokyo 162-8666, JapanArtificial-intelligence-based computer-aided diagnosis (CAD) systems have developed remarkably in recent years. These systems can help increase the adenoma detection rate (ADR), an important quality indicator in colonoscopies. While there have been many still-image-based studies on the usefulness of CAD, few have reported on its usefulness using actual clinical videos. However, no studies have compared the CAD group and control groups using the exact same case videos. This study aimed to determine whether CAD or endoscopists were superior in identifying colorectal neoplastic lesions in videos. In this study, we examined 34 lesions from 21 cases. CAD performed better than four of the six endoscopists (three experts and three beginners), including all the beginners. The time to lesion detection with beginners and experts was 2.147 ± 1.118 s and 1.394 ± 0.805 s, respectively, with significant differences between beginners and experts (<i>p</i> < 0.001) and between beginners and CAD (both <i>p</i> < 0.001). The time to lesion detection was significantly shorter for experts and CAD than for beginners. No significant difference was found between experts and CAD (<i>p</i> = 1.000). CAD could be useful as a diagnostic support tool for beginners to bridge the experience gap with experts.https://www.mdpi.com/2077-0383/12/14/4840computer-aided detection/diagnosiscolorectal polypcolonoscopy |
| spellingShingle | Yoshitsugu Misumi Kouichi Nonaka Miharu Takeuchi Yu Kamitani Yasuhiro Uechi Mai Watanabe Maiko Kishino Teppei Omori Maria Yonezawa Hajime Isomoto Katsutoshi Tokushige Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy Video Journal of Clinical Medicine computer-aided detection/diagnosis colorectal polyp colonoscopy |
| title | Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy Video |
| title_full | Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy Video |
| title_fullStr | Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy Video |
| title_full_unstemmed | Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy Video |
| title_short | Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy Video |
| title_sort | comparison of the ability of artificial intelligence based computer aided detection cad systems and endoscopists to detect colorectal neoplastic lesions on endoscopy video |
| topic | computer-aided detection/diagnosis colorectal polyp colonoscopy |
| url | https://www.mdpi.com/2077-0383/12/14/4840 |
| work_keys_str_mv | AT yoshitsugumisumi comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT kouichinonaka comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT miharutakeuchi comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT yukamitani comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT yasuhirouechi comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT maiwatanabe comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT maikokishino comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT teppeiomori comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT mariayonezawa comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT hajimeisomoto comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo AT katsutoshitokushige comparisonoftheabilityofartificialintelligencebasedcomputeraideddetectioncadsystemsandendoscopiststodetectcolorectalneoplasticlesionsonendoscopyvideo |