- Browse by Author
Browsing by Author "Mori, Yuichi"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Artificial Intelligence Improves Detection at Colonoscopy: Why aren’t we all already using it?(ScienceDirect, 2022) Rex, Douglas K.; Berzin, Tyler M.; Mori, Yuichi; Medicine, School of MedicineItem Combination of Mucosa-Exposure Device and Computer-Aided Detection for Adenoma Detection During Colonoscopy: A Randomized Trial(Elsevier, 2023-07) Spadaccini, Marco; Hassan, Cesare; Rondonotti, Emanuele; Antonelli, Giulio; Andrisani, Gianluca; Lollo, Gianluca; Auriemma, Francesco; Iacopini, Federico; Facciorusso, Antonio; Maselli, Roberta; Fugazza, Alessandro; Bambina Bergna, Irene Maria; Cereatti, Fabrizio; Mangiavillano, Benedetto; Radaelli, Franco; Di Matteo, Francesco; Gross, Seth A.; Sharma, Prateek; Mori, Yuichi; Bretthauer, Michael; Rex, Douglas K.; Repici, Alessandro; Medicine, School of MedicineBackground & Aims Both computer-aided detection (CADe)-assisted and Endocuff-assisted colonoscopy have been found to increase adenoma detection. We investigated the performance of the combination of the 2 tools compared with CADe-assisted colonoscopy alone to detect colorectal neoplasias during colonoscopy in a multicenter randomized trial. Methods Men and women undergoing colonoscopy for colorectal cancer screening, polyp surveillance, or clincial indications at 6 centers in Italy and Switzerland were enrolled. Patients were assigned (1:1) to colonoscopy with the combinations of CADe (GI-Genius; Medtronic) and a mucosal exposure device (Endocuff Vision [ECV]; Olympus) or to CADe-assisted colonoscopy alone (control group). All detected lesions were removed and sent to histopathology for diagnosis. The primary outcome was adenoma detection rate (percentage of patients with at least 1 histologically proven adenoma or carcinoma). Secondary outcomes were adenomas detected per colonoscopy, advanced adenomas and serrated lesions detection rate, the rate of unnecessary polypectomies (polyp resection without histologically proven adenomas), and withdrawal time. Results From July 1, 2021 to May 31, 2022, there were 1316 subjects randomized and eligible for analysis; 660 to the ECV group, 656 to the control group). The adenoma detection rate was significantly higher in the ECV group (49.6%) than in the control group (44.0%) (relative risk, 1.12; 95% CI, 1.00–1.26; P = .04). Adenomas detected per colonoscopy were significantly higher in the ECV group (mean ± SD, 0.94 ± 0.54) than in the control group (0.74 ± 0.21) (incidence rate ratio, 1.26; 95% CI, 1.04–1.54; P = .02). The 2 groups did not differ in term of detection of advanced adenomas and serrated lesions. There was no significant difference between groups in mean ± SD withdrawal time (9.01 ± 2.48 seconds for the ECV group vs 8.96 ± 2.24 seconds for controls; P = .69) or proportion of subjects undergoing unnecessary polypectomies (relative risk, 0.89; 95% CI, 0.69–1.14; P = .38). Conclusions The combination of CADe and ECV during colonoscopy increases adenoma detection rate and adenomas detected per colonoscopy without increasing withdrawal time compared with CADe alone.Item Comparative Performance of Artificial Intelligence Optical Diagnosis Systems for Leaving in Situ Colorectal Polyps(Elsevier, 2023-03) Hassan, Cesare; Sharma, Prateek; Mori, Yuichi; Bretthauer, Michael; Rex, Douglas K.; COMBO Study Group; Repici, Alessandro; Medicine, School of MedicineItem Quality Assurance of Computer-Aided Detection and Diagnosis in Colonoscopy(Elsevier, 2019) Vinsard, Daniela Guerrero; Mori, Yuichi; Misawa, Masashi; Kudo, Shin-ei; Rastogi, Amit; Bagci, Ulas; Rex, Douglas K.; Wallace, Michael B.; Medicine, School of MedicineRecent breakthroughs in artificial intelligence (AI), specifically via its emerging sub-field “Deep Learning,” have direct implications for computer-aided detection and diagnosis (CADe/CADx) for colonoscopy. AI is expected to have at least 2 major roles in colonoscopy practice; polyp detection (CADe) and polyp characterization (CADx). CADe has the potential to decrease polyp miss rate, contributing to improving adenoma detection, whereas CADx can improve the accuracy of colorectal polyp optical diagnosis, leading to reduction of unnecessary polypectomy of non-neoplastic lesions, potential implementation of a resect and discard paradigm, and proper application of advanced resection techniques. A growing number of medical-engineering researchers are developing both, CADe and CADx systems, some of which allow real-time recognition of polyps or in vivo identification of adenomas with over 90% accuracy. However, the quality of the developed AI systems as well as that of the study designs vary significantly, hence raising some concerns regarding the generalization of the proposed AI systems. Initial studies were conducted in an exploratory or retrospective fashion using stored images and likely overestimating the results. These drawbacks potentially hinder smooth implementation of this novel technology into colonoscopy practice. The aim of this article is to review both contributions and limitations in recent machine learning based CADe/CADx colonoscopy studies and propose some principles that should underlie system development and clinical testing.Item Strengths and weaknesses of an artificial intelligence polyp detection program as assessed by a high detecting endoscopist(ScienceDirect, 2022-04-12) Rex, Douglas K.; Mori, Yuichi; Sharma, Prateek; Lahr, Rachel E.; Vemulapalli, Krishna C.; Hassan, Cesare; Medicine, School of Medicine