Maarten R Struyvenberg1, Albert J de Groof1, Roger Fonollà2, Fons van der Sommen2, Peter H N de With2, Erik J Schoon3, Bas L A M Weusten4, Cadman L Leggett5, Allon Kahn6, Arvind J Trindade7, Eric K Ganguly8, Vani J A Konda9, Charles J Lightdale10, Douglas K Pleskow11, Amrita Sethi12, Michael S Smith13, Michael B Wallace14, Herbert C Wolfsen14, Gary J Tearney15, Sybren L Meijer16, Michael Vieth17, Roos E Pouw1, Wouter L Curvers3, Jacques J Bergman1. 1. Department of Gastroenterology and Hepatology, Amsterdam UMC, location AMC, Amsterdam, the Netherlands. 2. Department of Electrical Engineering, VCA group, Eindhoven University of Technology, Eindhoven, the Netherlands. 3. Department of Gastroenterology and Hepatology, Catharina Hospital, Eindhoven, the Netherlands. 4. Department of Gastroenterology and Hepatology, St. Antonius Hospital, Nieuwegein, the Netherlands. 5. Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, Minnesota, USA. 6. Division of Gastroenterology and Hepatology, Mayo Clinic, Scottsdale, Arizona, USA. 7. Division of Gastroenterology and Hepatology, Zucker School of Medicine at Hofstra/Northwell. Long Island Jewish Medical Center, New Hyde Park, New York, USA. 8. Department of Gastroenterology and Hepatology, University of Vermont Medical Center, Burlington, Vermont, USA. 9. Department of Gastroenterology and Hepatology, Baylor University Medical Center at Dallas, Dallas, Texas, USA. 10. Division of Gastroenterology and Hepatology, New York-Presbyterian Hospital, New York, New York, USA. 11. Department of Gastroenterology and Hepatology, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA. 12. Department of Gastroenterology and Hepatology, Columbia University Medical Center, New York, New York, USA. 13. Division of Gastroenterology and Hepatology, Mount Sinai West & Mount Sinai St. Luke's Hospitals, New York, New York, USA. 14. Division of Gastroenterology and Hepatology, Mayo Clinic, Jacksonville, Florida, USA. 15. Department of Pathology, Wellman Center for Photomedicine, Massachusetts General Hospital, Boston, Massachusetts, USA. 16. Department of Pathology, Amsterdam UMC, location AMC, Amsterdam, the Netherlands. 17. Institute of Pathology, Bayreuth Clinic, Bayreuth, Germany.
Abstract
BACKGROUND AND AIMS: Volumetric laser endomicroscopy (VLE) is an advanced imaging modality used to detect Barrett's esophagus (BE) dysplasia. However, real-time interpretation of VLE scans is complex and time-consuming. Computer-aided detection (CAD) may help in the process of VLE image interpretation. Our aim was to train and validate a CAD algorithm for VLE-based detection of BE neoplasia. METHODS: The multicenter, VLE PREDICT study, prospectively enrolled 47 patients with BE. In total, 229 nondysplastic BE and 89 neoplastic (high-grade dysplasia/esophageal adenocarcinoma) targets were laser marked under VLE guidance and subsequently underwent a biopsy for histologic diagnosis. Deep convolutional neural networks were used to construct a CAD algorithm for differentiation between nondysplastic and neoplastic BE tissue. The CAD algorithm was trained on a set consisting of the first 22 patients (134 nondysplastic BE and 38 neoplastic targets) and validated on a separate test set from patients 23 to 47 (95 nondysplastic BE and 51 neoplastic targets). The performance of the algorithm was benchmarked against the performance of 10 VLE experts. RESULTS: Using the training set to construct the algorithm resulted in an accuracy of 92%, sensitivity of 95%, and specificity of 92%. When performance was assessed on the test set, accuracy, sensitivity, and specificity were 85%, 91%, and 82%, respectively. The algorithm outperformed all 10 VLE experts, who demonstrated an overall accuracy of 77%, sensitivity of 70%, and specificity of 81%. CONCLUSIONS: We developed, validated, and benchmarked a VLE CAD algorithm for detection of BE neoplasia using prospectively collected and biopsy-correlated VLE targets. The algorithm detected neoplasia with high accuracy and outperformed 10 VLE experts. (The Netherlands National Trials Registry (NTR) number: NTR 6728.).
BACKGROUND AND AIMS: Volumetric laser endomicroscopy (VLE) is an advanced imaging modality used to detect Barrett's esophagus (BE) dysplasia. However, real-time interpretation of VLE scans is complex and time-consuming. Computer-aided detection (CAD) may help in the process of VLE image interpretation. Our aim was to train and validate a CAD algorithm for VLE-based detection of BE neoplasia. METHODS: The multicenter, VLE PREDICT study, prospectively enrolled 47 patients with BE. In total, 229 nondysplastic BE and 89 neoplastic (high-grade dysplasia/esophageal adenocarcinoma) targets were laser marked under VLE guidance and subsequently underwent a biopsy for histologic diagnosis. Deep convolutional neural networks were used to construct a CAD algorithm for differentiation between nondysplastic and neoplastic BE tissue. The CAD algorithm was trained on a set consisting of the first 22 patients (134 nondysplastic BE and 38 neoplastic targets) and validated on a separate test set from patients 23 to 47 (95 nondysplastic BE and 51 neoplastic targets). The performance of the algorithm was benchmarked against the performance of 10 VLE experts. RESULTS: Using the training set to construct the algorithm resulted in an accuracy of 92%, sensitivity of 95%, and specificity of 92%. When performance was assessed on the test set, accuracy, sensitivity, and specificity were 85%, 91%, and 82%, respectively. The algorithm outperformed all 10 VLE experts, who demonstrated an overall accuracy of 77%, sensitivity of 70%, and specificity of 81%. CONCLUSIONS: We developed, validated, and benchmarked a VLE CAD algorithm for detection of BE neoplasia using prospectively collected and biopsy-correlated VLE targets. The algorithm detected neoplasia with high accuracy and outperformed 10 VLE experts. (The Netherlands National Trials Registry (NTR) number: NTR 6728.).
Authors: Jason Zhang; Tan Nguyen; Benjamin Potsaid; Vijaysekhar Jayaraman; Christopher Burgner; Siyu Chen; Jinxi Li; Kaicheng Liang; Alex Cable; Giovanni Traverso; Hiroshi Mashimo; James G Fujimoto Journal: Biomed Opt Express Date: 2021-03-26 Impact factor: 3.732