Albert J de Groof1, Maarten R Struyvenberg1, Joost van der Putten2, Fons van der Sommen2, Kiki N Fockens1, Wouter L Curvers3, Sveta Zinger2, Roos E Pouw1, Emmanuel Coron4, Francisco Baldaque-Silva5, Oliver Pech6, Bas Weusten7, Alexander Meining8, Horst Neuhaus9, Raf Bisschops10, John Dent11, Erik J Schoon3, Peter H de With2, Jacques J Bergman12. 1. Department of Gastroenterology and Hepatology, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, The Netherlands. 2. Department of Electrical Engineering, Video Coding & Architectures group, Eindhoven University of Technology, Eindhoven, The Netherlands. 3. Department of Gastroenterology and Hepatology, Catharina Hospital Eindhoven, Eindhoven, The Netherlands. 4. Institut des Maladies de l'Appareil Digestif, University Hospital of Nantes place Alexis Ricordeau, Nantes, France. 5. Department of Digestive Diseases, Karolinska University Hospital and Karolinska Institute, Stockholm, Sweden. 6. Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder, Regensburg, Germany. 7. Department of Gastroenterology and Hepatology, St. Antonius Hospital, Nieuwegein, The Netherlands. 8. Center of Internal Medicine, Ulm University, Ulm, Germany. 9. Internal Medicine, Evangelisches Krankenhaus Düsseldorf, Düsseldorf, Germany. 10. Department of Gastroenterology and Hepatology, University Hospitals Leuven, Leuven, Belgium. 11. Department of Medicine, University of Adelaide and Royal Adelaide Hospital, Adelaide, South Australia. 12. Department of Gastroenterology and Hepatology, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, The Netherlands. Electronic address: j.j.bergman@amsterdamumc.nl.
Abstract
BACKGROUND & AIMS: We aimed to develop and validate a deep-learning computer-aided detection (CAD) system, suitable for use in real time in clinical practice, to improve endoscopic detection of early neoplasia in patients with Barrett's esophagus (BE). METHODS: We developed a hybrid ResNet-UNet model CAD system using 5 independent endoscopy data sets. We performed pretraining using 494,364 labeled endoscopic images collected from all intestinal segments. Then, we used 1704 unique esophageal high-resolution images of rigorously confirmed early-stage neoplasia in BE and nondysplastic BE, derived from 669 patients. System performance was assessed by using data sets 4 and 5. Data set 5 was also scored by 53 general endoscopists with a wide range of experience from 4 countries to benchmark CAD system performance. Coupled with histopathology findings, scoring of images that contained early-stage neoplasia in data sets 2-5 were delineated in detail for neoplasm position and extent by multiple experts whose evaluations served as the ground truth for segmentation. RESULTS: The CAD system classified images as containing neoplasms or nondysplastic BE with 89% accuracy, 90% sensitivity, and 88% specificity (data set 4, 80 patients and images). In data set 5 (80 patients and images) values for the CAD system vs those of the general endoscopists were 88% vs 73% accuracy, 93% vs 72% sensitivity, and 83% vs 74% specificity. The CAD system achieved higher accuracy than any of the individual 53 nonexpert endoscopists, with comparable delineation performance. CAD delineations of the area of neoplasm overlapped with those from the BE experts in all detected neoplasia in data sets 4 and 5. The CAD system identified the optimal site for biopsy of detected neoplasia in 97% and 92% of cases (data sets 4 and 5, respectively). CONCLUSIONS: We developed, validated, and benchmarked a deep-learning computer-aided system for primary detection of neoplasia in patients with BE. The system detected neoplasia with high accuracy and near-perfect delineation performance. The Netherlands National Trials Registry, Number: NTR7072.
BACKGROUND & AIMS: We aimed to develop and validate a deep-learning computer-aided detection (CAD) system, suitable for use in real time in clinical practice, to improve endoscopic detection of early neoplasia in patients with Barrett's esophagus (BE). METHODS: We developed a hybrid ResNet-UNet model CAD system using 5 independent endoscopy data sets. We performed pretraining using 494,364 labeled endoscopic images collected from all intestinal segments. Then, we used 1704 unique esophageal high-resolution images of rigorously confirmed early-stage neoplasia in BE and nondysplastic BE, derived from 669 patients. System performance was assessed by using data sets 4 and 5. Data set 5 was also scored by 53 general endoscopists with a wide range of experience from 4 countries to benchmark CAD system performance. Coupled with histopathology findings, scoring of images that contained early-stage neoplasia in data sets 2-5 were delineated in detail for neoplasm position and extent by multiple experts whose evaluations served as the ground truth for segmentation. RESULTS: The CAD system classified images as containing neoplasms or nondysplastic BE with 89% accuracy, 90% sensitivity, and 88% specificity (data set 4, 80 patients and images). In data set 5 (80 patients and images) values for the CAD system vs those of the general endoscopists were 88% vs 73% accuracy, 93% vs 72% sensitivity, and 83% vs 74% specificity. The CAD system achieved higher accuracy than any of the individual 53 nonexpert endoscopists, with comparable delineation performance. CAD delineations of the area of neoplasm overlapped with those from the BE experts in all detected neoplasia in data sets 4 and 5. The CAD system identified the optimal site for biopsy of detected neoplasia in 97% and 92% of cases (data sets 4 and 5, respectively). CONCLUSIONS: We developed, validated, and benchmarked a deep-learning computer-aided system for primary detection of neoplasia in patients with BE. The system detected neoplasia with high accuracy and near-perfect delineation performance. The Netherlands National Trials Registry, Number: NTR7072.
Authors: Andreas Kleppe; Ole-Johan Skrede; Sepp De Raedt; Knut Liestøl; David J Kerr; Håvard E Danielsen Journal: Nat Rev Cancer Date: 2021-01-29 Impact factor: 60.716