Pushpak Taunk1, Christopher D Atkinson2, David Lichtenstein3, Eladio Rodriguez-Diaz4, Satish K Singh5,6. 1. Division of Digestive Diseases and Nutrition, University of South Florida Morsani College of Medicine, Tampa, FL, USA. 2. Department of Medicine, Section of Gastroenterology, VA Boston Healthcare System, Boston, MA, USA. 3. Boston Medical Center, Boston University School of Medicine, Boston, MA, USA. 4. Research Service, VA Boston Healthcare System, Boston, MA, USA. 5. Department of Medicine, Section of Gastroenterology, VA Boston Healthcare System, Boston, MA, USA. Satish.Singh@va.gov. 6. Boston University School of Medicine & College of Engineering, Boston University, Boston, MA, USA. Satish.Singh@va.gov.
Abstract
INTRODUCTION: Probe-based confocal laser endomicroscopy (pCLE) is a promising modality for classifying polyp histology in vivo, but decision making in real-time is hampered by high-magnification targeting and by the learning curve for image interpretation. The aim of this study is to test the feasibility of a system combining the use of a low-magnification, wider field-of-view pCLE probe and a computer-assisted diagnosis (CAD) algorithm that automatically classifies colonic polyps. METHODS: This feasibility study utilized images of polyps from 26 patients who underwent colonoscopy with pCLE. The pCLE images were reviewed offline by two expert and five junior endoscopists blinded to index histopathology. A subset of images was used to train classification software based on the consensus of two GI histopathologists. Images were processed to extract image features as inputs to a linear support vector machine classifier. We compared the CAD algorithm's prediction accuracy against the classification accuracy of the endoscopists. RESULTS: We utilized 96 neoplastic and 93 non-neoplastic confocal images from 27 neoplastic and 20 non-neoplastic polyps. The CAD algorithm had sensitivity of 95%, specificity of 94%, and accuracy of 94%. The expert endoscopists had sensitivities of 98% and 95%, specificities of 98% and 96%, and accuracies of 98% and 96%, while the junior endoscopists had, on average, a sensitivity of 60%, specificity of 85%, and accuracy of 73%. CONCLUSION: The CAD algorithm showed comparable performance to offline review by expert endoscopists and improved performance when compared to junior endoscopists and may be useful for assisting clinical decision making in real time.
INTRODUCTION: Probe-based confocal laser endomicroscopy (pCLE) is a promising modality for classifying polyp histology in vivo, but decision making in real-time is hampered by high-magnification targeting and by the learning curve for image interpretation. The aim of this study is to test the feasibility of a system combining the use of a low-magnification, wider field-of-view pCLE probe and a computer-assisted diagnosis (CAD) algorithm that automatically classifies colonic polyps. METHODS: This feasibility study utilized images of polyps from 26 patients who underwent colonoscopy with pCLE. The pCLE images were reviewed offline by two expert and five junior endoscopists blinded to index histopathology. A subset of images was used to train classification software based on the consensus of two GI histopathologists. Images were processed to extract image features as inputs to a linear support vector machine classifier. We compared the CAD algorithm's prediction accuracy against the classification accuracy of the endoscopists. RESULTS: We utilized 96 neoplastic and 93 non-neoplastic confocal images from 27 neoplastic and 20 non-neoplastic polyps. The CAD algorithm had sensitivity of 95%, specificity of 94%, and accuracy of 94%. The expert endoscopists had sensitivities of 98% and 95%, specificities of 98% and 96%, and accuracies of 98% and 96%, while the junior endoscopists had, on average, a sensitivity of 60%, specificity of 85%, and accuracy of 73%. CONCLUSION: The CAD algorithm showed comparable performance to offline review by expert endoscopists and improved performance when compared to junior endoscopists and may be useful for assisting clinical decision making in real time.
Authors: Muhammad W Shahid; Anna M Buchner; Michael G Heckman; Murli Krishna; Massimo Raimondo; Timothy Woodward; Michael B Wallace Journal: Am J Gastroenterol Date: 2011-11-08 Impact factor: 10.864
Authors: Douglas K Rex; Charles Kahi; Michael O'Brien; T R Levin; Heiko Pohl; Amit Rastogi; Larry Burgart; Tom Imperiale; Uri Ladabaum; Jonathan Cohen; David A Lieberman Journal: Gastrointest Endosc Date: 2011-03 Impact factor: 9.427
Authors: Prateek Sharma; Alexander R Meining; Emmanuel Coron; Charles J Lightdale; Herbert C Wolfsen; Ajay Bansal; Monther Bajbouj; Jean-Paul Galmiche; Julian A Abrams; Amit Rastogi; Neil Gupta; Joel E Michalek; Gregory Y Lauwers; Michael B Wallace Journal: Gastrointest Endosc Date: 2011-07-13 Impact factor: 9.427
Authors: Sidney J Winawer; Ann G Zauber; Robert H Fletcher; Jonathon S Stillman; Michael J O'Brien; Bernard Levin; Robert A Smith; David A Lieberman; Randall W Burt; Theodore R Levin; John H Bond; Durado Brooks; Tim Byers; Neil Hyman; Lynne Kirk; Alan Thorson; Clifford Simmang; David Johnson; Douglas K Rex Journal: Gastroenterology Date: 2006-05 Impact factor: 22.682
Authors: Marcia Irene Canto; Sharmila Anandasabapathy; William Brugge; Gary W Falk; Kerry B Dunbar; Zhe Zhang; Kevin Woods; Jose Antonio Almario; Ursula Schell; John Goldblum; Anirban Maitra; Elizabeth Montgomery; Ralf Kiesslich Journal: Gastrointest Endosc Date: 2013-11-09 Impact factor: 9.427
Authors: Matti Sievert; Konstantinos Mantsopoulos; Sarina K Mueller; Markus Eckstein; Robin Rupp; Marc Aubreville; Florian Stelzle; Nicolai Oetter; Andreas Maier; Heinrich Iro; Miguel Goncalves Journal: Acta Otorhinolaryngol Ital Date: 2022-02-07 Impact factor: 2.618