We herein report the first use, to our knowledge, of computed tomography-ultrasound (US) fusion technique to follow-up Crohn’s disease complications. This novel technique employs real-time reconstructed fusion of previously obtained tomographic images onto the US image software, allowing accurate bedside spatial resolution, localization, and lesion characterization by US.
Introduction The use of intestinal ultrasound (IUS) for the diagnosis and follow-up of inflammatory bowel disease is steadily growing. Although access to educational platforms of IUS is feasible, novice ultrasound operators lack experience in performing and interpreting IUS. An artificial intelligence (AI)–based operator supporting system that automatically detects bowel wall inflammation may simplify the use of IUS by less experienced operators. Our aim was to develop and validate an artificial intelligence module that can distinguish bowel wall thickening (a surrogate of bowel inflammation) from normal bowel images of IUS. Methods We used a self-collected image data set to develop and validate a convolutional neural network module that can distinguish bowel wall thickening >3 mm (a surrogate of bowel inflammation) from normal bowel images of IUS. Results The data set consisted of 1008 images, distributed uniformly (50% normal images, 50% abnormal images). Execution of the training phase and the classification phase was performed using 805 and 203 images, respectively. The overall accuracy, sensitivity, and specificity for detection of bowel wall thickening were 90.1%, 86.4%, and 94%, respectively. The network exhibited an average area under the ROC curve of 0.9777 for this task. Conclusions We developed a machine-learning module based on a pretrained convolutional neural network that is highly accurate in the recognition of bowel wall thickening on intestinal ultrasound images in Crohn’s disease. Incorporation of convolutional neural network to IUS may facilitate the use of IUS by inexperienced operators and allow automatized detection of bowel inflammation and standardization of IUS imaging interpretation.
Objectives: Three-dimensional virtual reality (3D VR) permits precise reconstruction of computed tomography (CT) images, and these allow precise measurements of colonic anatomical parameters. Colonoscopy proves challenging in a subset of patients, and thus CT colonoscopy (CTC) is often required to visualize the entire colon. The aim of the study was to determine whether 3D reconstructions of the colon could help identify and quantify the key anatomical features leading to colonoscopy failure. Design: Retrospective observational study. Methods: Using 3D VR technology, we reconstructed and compared the length of various colonic segments and number of bends and colonic width in 10 cases of CTC in technically failed prior colonoscopies to 10 cases of CTC performed for non-technically failure indications. Results: We found significant elongation of the sigmoid colon (71 ± 23 cm versus 35 ± 9; p = 0.01) and of pancolonic length (216 ± 38 cm versus 158 ± 20 cm; p = 0.001) in cases of technically failed colonoscopy. There was also a significant increase in the number of colonic angles (17.7 ± 3.2 versus 12.7 ± 2.4; p = 0.008) in failed colonoscopy cases. Conclusion: Increased sigmoid and pancolonic length and more colonic bends are novel factors associated with technical failure of colonoscopy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.