Article
Health Care Sciences & Services
Ka Luen Thomas Lui, Sze Hang Kevin Liu, Kathy Leung, Joseph T. Wu, Ann G. Zauber, Wai Keung Leung
Summary: The widespread adoption of computer-aided detection (CADe) in detecting colorectal polyps would result in shorter surveillance intervals for patients, particularly according to the US Multi-Society Task Force on Colorectal Cancer (USMSTF) guideline. Based on simulation, CADe application would lead to approximately 19.1% and 1.9% of patients requiring shorter surveillance intervals, as recommended by the USMSTF and European Society of Gastrointestinal Endoscopy (ESGE) guidelines, respectively. Specifically, all or 2.7% of patients initially scheduled for 3-5 years of surveillance would have their intervals shortened to 3 years, according to the USMSTF guideline.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2023)
Article
Gastroenterology & Hepatology
Michael B. Wallace, Prateek Sharma, Pradeep Bhandari, James East, Giulio Antonelli, Roberto Lorenzetti, Micheal Vieth, Ilaria Speranza, Marco Spadaccini, Madhav Desai, Frank J. Lukens, Genci Babameto, Daisy Batista, Davinder Singh, William Palmer, Francisco Ramirez, Rebecca Palmer, Tisha Lunsford, Kevin Ruff, Elizabeth Bird-Liebermann, Victor Ciofoaia, Sophie Arndtz, David Cangemi, Kirsty Puddick, Gregory Derfus, Amitpal S. Johal, Mohammed Barawi, Luigi Longo, Luigi Moro, Alessandro Repici, Cesare Hassan
Summary: This study demonstrates that the use of artificial intelligence can significantly reduce the miss rate of colorectal neoplasia, especially for small and subtle lesions. This is of great importance in improving the prevention of colorectal cancer.
Review
Health Care Sciences & Services
Scarlet Nazarian, Ben Glover, Hutan Ashrafian, Ara Darzi, Julian Teare
Summary: Artificial intelligence technologies show great potential in improving the detection and characterization of colorectal polyps, ultimately reducing the incidence of colorectal cancer. The current generation of AI-based systems demonstrate impressive accuracy in detecting and characterizing colorectal polyps.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Article
Medical Informatics
Mariusz Madalinski, Roger Prudham
Summary: By utilizing artificial intelligence methods to improve the quality of colonoscopy, all polyps with malignant potential can be removed, reducing cancer incidence. The integration of deep learning methodology with CADe systems has the potential to increase adenoma detection rates in bowel cancer screening.
JMIR MEDICAL INFORMATICS
(2021)
Review
Oncology
Edward Young, Louisa Edwards, Rajvinder Singh
Summary: Artificial intelligence (AI) systems have become increasingly available in the field of endoscopy, particularly in colonoscopy. This comprehensive review focuses on the application of AI in detecting and characterizing colorectal polyps, with the goal of improving the efficacy of colorectal cancer screening and prevention. AI-driven algorithms show potential in addressing the challenge of overlooked polyps and empowering gastroenterologists to accurately characterize polyps without extensive training in advanced mucosal imaging. By integrating AI technologies into routine colonoscopy, the detection and characterization of polyps can be advanced, potentially leading to more effective colorectal cancer screening and prevention.
Article
Gastroenterology & Hepatology
Jeremy R. Glissen Brown, Nabil M. Mansour, Pu Wang, Maria Aguilera Chuchuca, Scott B. Minchenberg, Madhuri Chandnani, Lin Liu, Seth A. Gross, Neil Sengupta, Tyler M. Berzin
Summary: In a U.S. multicenter tandem colonoscopy randomized controlled trial, the use of a CADe-system was shown to decrease AMR and SSL miss rate while increasing first-pass APC compared to HDWL colonoscopy alone.
CLINICAL GASTROENTEROLOGY AND HEPATOLOGY
(2022)
Article
Gastroenterology & Hepatology
Nikhil R. Thiruvengadam, Gregory A. Cote, Shashank Gupta, Medora Rodrigues, Yecheskel Schneider, Mustafa A. Arain, Pejman Solaimani, Steve Serrao, Michael L. Kochman, Monica Saumoy
Summary: This study aimed to evaluate the cost-effectiveness requirements of computer-aided detection (CAD) in colorectal cancer (CRC) screening/surveillance and its impact on adenoma detection by endoscopists with different ADRs. The findings showed that CAD significantly improved ADR and reduced CRC incidence and mortality. Therefore, in clinical implementation, CAD needs to improve ADR to at least 30% or have a cost of less than $579 per colonoscopy to be cost-effective.
Review
Medicine, General & Internal
Lei Shao, Xinzong Yan, Chengjiang Liu, Can Guo, Baojia Cai
Summary: Artificial intelligence-assisted colonoscopy (AIAC) can effectively reduce the missed detection rate and improve the detection rate of adenoma, especially for small adenomas. However, more in-depth studies are needed to improve the clinical application of AIAC.
Article
Surgery
Frederick H. Koh, Jasmine Ladlad, Eng-Kiong Teo, Cui-Li Lin, Fung-Joon Foo
Summary: This study evaluates the performance of real-time AI-aided colonoscopy in the detection of colonic polyps. The results show that using real-time AI-aided colonoscopy can improve the detection rate of colonic polyps, even for experienced endoscopists. This will improve the quality of colonoscopy.
SURGICAL ENDOSCOPY AND OTHER INTERVENTIONAL TECHNIQUES
(2023)
Article
Gastroenterology & Hepatology
Ping Shen, Wei Zhi Li, Jia Xin Li, Zheng Cun Pei, Yu Xuan Luo, Jin Bao Mu, Wen Li, Xi Mo Wang
Summary: The study found that the real-time CADe system significantly increased the PDR and PPC under conditions of high polyp detection rate, indicating that CADe-assisted colonoscopy can enhance polyp detection rate.
JOURNAL OF DIGESTIVE DISEASES
(2021)
Review
Surgery
Shuen-Ern Chin, Fang-Ting Wan, Jasmine Ladlad, Koy-Min Chue, Eng-Kiong Teo, Cui-Li Lin, Fung-Joon H. Foo, Frederick Koh
Summary: This study evaluates the 1-year performance of AI-aided colonoscopy, showing that it is a cost-effective means of improving colonoscopy quality and advancing colorectal cancer screening in Singapore.
SURGICAL ENDOSCOPY AND OTHER INTERVENTIONAL TECHNIQUES
(2023)
Article
Gastroenterology & Hepatology
Shun Kato, Shin-ei Kudo, Yosuke Minegishi, Yuki Miyata, Yasuharu Maeda, Takanori Kuroki, Yuki Takashina, Kenichi Mochizuki, Eri Tamura, Masahiro Abe, Yuta Sato, Tatsuya Sakurai, Yuta Kouyama, Kenta Tanaka, Yushi Ogawa, Hiroki Nakamura, Katsuro Ichimasa, Noriyuki Ogata, Tomokazu Hisayuki, Takemasa Hayashi, Kunihiko Wakamura, Hideyuki Miyachi, Toshiyuki Baba, Fumio Ishida, Tetsuo Nemoto, Masashi Misawa, Collaborators
Summary: This study evaluated the additional diagnostic value of computer-aided characterization in colonoscopy practice. It found that this technique improves the sensitivity and negative predictive value for colorectal polyps and enhances the high-confidence diagnosis rate.
DIGESTIVE ENDOSCOPY
(2023)
Article
Gastroenterology & Hepatology
Wenxi Jiang, Linying Xin, Shefeng Zhu, Zhaoxue Liu, Jiali Wu, Feng Ji, Chaohui Yu, Zhe Shen
Summary: Nearly a quarter of polyps were missed during routine colonoscopy. Diminutive, flat, sessile, and right-side colon polyps were at higher risk of missing. The risk of missing polyps was higher in older men, current smokers, and individuals with multiple polyps detected in the first colonoscopy than their counterparts.
DIGESTIVE DISEASES AND SCIENCES
(2023)
Review
Medicine, General & Internal
Shenghan Lou, Fenqi Du, Wenjie Song, Yixiu Xia, Xinyu Yue, Da Yang, Binbin Cui, Yanlong Liu, Peng Han
Summary: AI-aided colonoscopy significantly enhances the detection of colorectal neoplasia by reducing the miss rate. However, future studies should focus on evaluating the cost-effectiveness and long-term benefits of AI-aided colonoscopy in reducing cancer incidence.
Article
Gastroenterology & Hepatology
Joel Troya, Boban Sudarevic, Adrian Krenzer, Michael Banck, Markus Brand, Benjamin M. Walter, Frank Puppe, Wolfram G. Zoller, Alexander Meining, Alexander Hann
Summary: This study compares the performance of different CADe systems, updates, and configuration modes, providing help for clinicians to select the most appropriate system for their specific needs.