PURPOSE: Real-time characterization of colorectal lesions during colonoscopy is important for reducing medical costs, given that the need for a pathological diagnosis can be omitted if the accuracy of the diagnostic modality is sufficiently high. However, it is sometimes difficult for community-based gastroenterologists to achieve the required level of diagnostic accuracy. In this regard, we developed a computer-aided diagnosis (CAD) system based on endocytoscopy (EC) to evaluate cellular, glandular, and vessel structure atypia in vivo. The purpose of this study was to compare the diagnostic ability and efficacy of this CAD system with the performances of human expert and trainee endoscopists. METHODS: We developed a CAD system based on EC with narrow-band imaging that allowed microvascular evaluation without dye (ECV-CAD). The CAD algorithm was programmed based on texture analysis and provided a two-class diagnosis of neoplastic or non-neoplastic, with probabilities. We validated the diagnostic ability of the ECV-CAD system using 173 randomly selected EC images (49 non-neoplasms, 124 neoplasms). The images were evaluated by the CAD and by four expert endoscopists and three trainees. The diagnostic accuracies for distinguishing between neoplasms and non-neoplasms were calculated. RESULTS: ECV-CAD had higher overall diagnostic accuracy than trainees (87.8 vs 63.4%; [Formula: see text]), but similar to experts (87.8 vs 84.2%; [Formula: see text]). With regard to high-confidence cases, the overall accuracy of ECV-CAD was also higher than trainees (93.5 vs 71.7%; [Formula: see text]) and comparable to experts (93.5 vs 90.8%; [Formula: see text]). CONCLUSIONS: ECV-CAD showed better diagnostic accuracy than trainee endoscopists and was comparable to that of experts. ECV-CAD could thus be a powerful decision-making tool for less-experienced endoscopists.
PURPOSE: Real-time characterization of colorectal lesions during colonoscopy is important for reducing medical costs, given that the need for a pathological diagnosis can be omitted if the accuracy of the diagnostic modality is sufficiently high. However, it is sometimes difficult for community-based gastroenterologists to achieve the required level of diagnostic accuracy. In this regard, we developed a computer-aided diagnosis (CAD) system based on endocytoscopy (EC) to evaluate cellular, glandular, and vessel structure atypia in vivo. The purpose of this study was to compare the diagnostic ability and efficacy of this CAD system with the performances of human expert and trainee endoscopists. METHODS: We developed a CAD system based on EC with narrow-band imaging that allowed microvascular evaluation without dye (ECV-CAD). The CAD algorithm was programmed based on texture analysis and provided a two-class diagnosis of neoplastic or non-neoplastic, with probabilities. We validated the diagnostic ability of the ECV-CAD system using 173 randomly selected EC images (49 non-neoplasms, 124 neoplasms). The images were evaluated by the CAD and by four expert endoscopists and three trainees. The diagnostic accuracies for distinguishing between neoplasms and non-neoplasms were calculated. RESULTS: ECV-CAD had higher overall diagnostic accuracy than trainees (87.8 vs 63.4%; [Formula: see text]), but similar to experts (87.8 vs 84.2%; [Formula: see text]). With regard to high-confidence cases, the overall accuracy of ECV-CAD was also higher than trainees (93.5 vs 71.7%; [Formula: see text]) and comparable to experts (93.5 vs 90.8%; [Formula: see text]). CONCLUSIONS: ECV-CAD showed better diagnostic accuracy than trainee endoscopists and was comparable to that of experts. ECV-CAD could thus be a powerful decision-making tool for less-experienced endoscopists.
Authors: Sebastian Gross; Christian Trautwein; Alexander Behrens; Ron Winograd; Stephan Palm; Holger H Lutz; Ramin Schirin-Sokhan; Hartmut Hecker; Til Aach; Jens J W Tischendorf Journal: Gastrointest Endosc Date: 2011-10-13 Impact factor: 9.427
Authors: Linda K Wanders; James E East; Sanne E Uitentuis; Mariska M G Leeflang; Evelien Dekker Journal: Lancet Oncol Date: 2013-11-13 Impact factor: 41.316
Authors: Douglas K Rex; Andrew J Overhiser; Shawn C Chen; Oscar W Cummings; Thomas M Ulbright Journal: Am J Gastroenterol Date: 2009-01 Impact factor: 10.864
Authors: Ralf Kiesslich; Juergen Burg; Michael Vieth; Janina Gnaendiger; Meike Enders; Peter Delaney; Adrian Polglase; Wendy McLaren; Daniela Janell; Steven Thomas; Bernhard Nafe; Peter R Galle; Markus F Neurath Journal: Gastroenterology Date: 2004-09 Impact factor: 22.682
Authors: Sara Moccia; Leonardo S Mattos; Ilaria Patrini; Michela Ruperti; Nicolas Poté; Federica Dondero; François Cauchy; Ailton Sepulveda; Olivier Soubrane; Elena De Momi; Alberto Diaspro; Manuela Cesaretti Journal: Int J Comput Assist Radiol Surg Date: 2018-05-23 Impact factor: 2.924
Authors: Sara Moccia; Elena De Momi; Marco Guarnaschelli; Matteo Savazzi; Andrea Laborai; Luca Guastini; Giorgio Peretti; Leonardo S Mattos Journal: J Med Imaging (Bellingham) Date: 2017-09-29