Jorge D Machicado1, Wei-Lun Chao2, David E Carlyn2, Tai-Yu Pan2, Sarah Poland3, Victoria L Alexander3, Tassiana G Maloof3, Kelly Dubay4, Olivia Ueltschi4, Dana M Middendorf3, Muhammed O Jajeh5, Aadit B Vishwanath6, Kyle Porter7, Phil A Hart8, Georgios I Papachristou8, Zobeida Cruz-Monserrate8, Darwin L Conwell8, Somashekar G Krishna8. 1. Division of Gastroenterology and Hepatology, Mayo Clinic Health System, Eau Claire, Wisconsin, USA. 2. Department of Computer Science and Engineering, College of Engineering, The Ohio State University, Columbus, Ohio, USA. 3. The Ohio State University College of Medicine, Columbus, Ohio, USA. 4. The Comprehensive Cancer Center-Arthur G. James Cancer Hospital and Richard J. Solove Research Institute, The Ohio State University, Columbus, Ohio, USA. 5. Ohio University Heritage College of Osteopathic Medicine, Athens, Ohio, USA. 6. Department of Biomedical Engineering, University of Michigan, Ann Arbor, Michigan, USA. 7. Center for Biostatistics, The Ohio State University Wexner Medical Center, Columbus, Ohio, USA. 8. Division of Gastroenterology, Hepatology, and Nutrition, Division of Internal Medicine, The Ohio State University Wexner Medical Center, Columbus, Ohio, USA.
Abstract
BACKGROUND AND AIMS: EUS-guided needle-based confocal laser endomicroscopy (EUS-nCLE) can differentiate high-grade dysplasia/adenocarcinoma (HGD-Ca) in intraductal papillary mucinous neoplasms (IPMNs) but requires manual interpretation. We sought to derive predictive computer-aided diagnosis (CAD) and artificial intelligence (AI) algorithms to facilitate accurate diagnosis and risk stratification of IPMNs. METHODS: A post hoc analysis of a single-center prospective study evaluating EUS-nCLE (2015-2019; INDEX study) was conducted using 15,027 video frames from 35 consecutive patients with histopathologically proven IPMNs (18 with HGD-Ca). We designed 2 CAD-convolutional neural network (CNN) algorithms: (1) a guided segmentation-based model (SBM), where the CNN-AI system was trained to detect and measure papillary epithelial thickness and darkness (indicative of cellular and nuclear stratification), and (2) a reasonably agnostic holistic-based model (HBM) where the CNN-AI system automatically extracted nCLE features for risk stratification. For the detection of HGD-Ca in IPMNs, the diagnostic performance of the CNN-CAD algorithms was compared with that of the American Gastroenterological Association (AGA) and revised Fukuoka guidelines. RESULTS: Compared with the guidelines, both n-CLE-guided CNN-CAD algorithms yielded higher sensitivity (HBM, 83.3%; SBM, 83.3%; AGA, 55.6%; Fukuoka, 55.6%) and accuracy (SBM, 82.9%; HBM, 85.7%; AGA, 68.6%; Fukuoka, 74.3%) for diagnosing HGD-Ca, with comparable specificity (SBM, 82.4%; HBM, 88.2%; AGA, 82.4%; Fukuoka, 94.1%). Both CNN-CAD algorithms, the guided (SBM) and agnostic (HBM) models, were comparable in risk stratifying IPMNs. CONCLUSION: EUS-nCLE-based CNN-CAD algorithms can accurately risk stratify IPMNs. Future multicenter validation studies and AI model improvements could enhance the accuracy and fully automatize the process for real-time interpretation.
BACKGROUND AND AIMS: EUS-guided needle-based confocal laser endomicroscopy (EUS-nCLE) can differentiate high-grade dysplasia/adenocarcinoma (HGD-Ca) in intraductal papillary mucinous neoplasms (IPMNs) but requires manual interpretation. We sought to derive predictive computer-aided diagnosis (CAD) and artificial intelligence (AI) algorithms to facilitate accurate diagnosis and risk stratification of IPMNs. METHODS: A post hoc analysis of a single-center prospective study evaluating EUS-nCLE (2015-2019; INDEX study) was conducted using 15,027 video frames from 35 consecutive patients with histopathologically proven IPMNs (18 with HGD-Ca). We designed 2 CAD-convolutional neural network (CNN) algorithms: (1) a guided segmentation-based model (SBM), where the CNN-AI system was trained to detect and measure papillary epithelial thickness and darkness (indicative of cellular and nuclear stratification), and (2) a reasonably agnostic holistic-based model (HBM) where the CNN-AI system automatically extracted nCLE features for risk stratification. For the detection of HGD-Ca in IPMNs, the diagnostic performance of the CNN-CAD algorithms was compared with that of the American Gastroenterological Association (AGA) and revised Fukuoka guidelines. RESULTS: Compared with the guidelines, both n-CLE-guided CNN-CAD algorithms yielded higher sensitivity (HBM, 83.3%; SBM, 83.3%; AGA, 55.6%; Fukuoka, 55.6%) and accuracy (SBM, 82.9%; HBM, 85.7%; AGA, 68.6%; Fukuoka, 74.3%) for diagnosing HGD-Ca, with comparable specificity (SBM, 82.4%; HBM, 88.2%; AGA, 82.4%; Fukuoka, 94.1%). Both CNN-CAD algorithms, the guided (SBM) and agnostic (HBM) models, were comparable in risk stratifying IPMNs. CONCLUSION: EUS-nCLE-based CNN-CAD algorithms can accurately risk stratify IPMNs. Future multicenter validation studies and AI model improvements could enhance the accuracy and fully automatize the process for real-time interpretation.