Background And Aims: Current artificial intelligence (AI)-based solutions for capsule endoscopy (CE) interpretation are proprietary. We aimed to evaluate an AI solution trained on a specific CE system (Pillcam®, Medtronic) for the detection of angiectasias on images captured by a different proprietary system (MiroCam®, Intromedic).
Material And Methods: An advanced AI solution (Axaro®, Augmented Endoscopy), previously trained on Pillcam® small bowell images, was evaluated on independent datasets with more than 1200 Pillcam® and MiroCam® still frames (equally distributed, with or without angiectasias). Images were reviewed by experts before and after AI interpretation.
Results: Sensitivity for the diagnosis of angiectasia was 97.4% with Pillcam® images and 96.1% with Mirocam® images, with specificity of 98.8% and 97.8%, respectively. Performances regarding the delineation of regions of interest and the characterization of angiectasias were similar in both groups (all above 95%). Processing time was significantly shorter with Mirocam® (20.7 ms) than with Pillcam® images (24.6 ms, p<0.0001), possibly related to technical differences between systems.
Conclusion: This proof-of-concept study on still images paves the way for the development of resource-sparing, "universal" CE databases and AI solutions for CE interpretation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.dld.2021.08.026 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A multisystem-compatible deep learning-based algorithm for detection and characterization of angiectasias in small-bowel capsule endoscopy. A proof-of-concept study.
Dig Liver Dis
December 2021
Sorbonne Université, Centre d'Endoscopie Digestive, Hôpital Saint-Antoine, APHP, Paris, France; ETIS UMR 8051 (CY Paris Cergy University, ENSEA, CNRS), Cergy, France. Electronic address:
Background And Aims: Current artificial intelligence (AI)-based solutions for capsule endoscopy (CE) interpretation are proprietary. We aimed to evaluate an AI solution trained on a specific CE system (Pillcam®, Medtronic) for the detection of angiectasias on images captured by a different proprietary system (MiroCam®, Intromedic).
Material And Methods: An advanced AI solution (Axaro®, Augmented Endoscopy), previously trained on Pillcam® small bowell images, was evaluated on independent datasets with more than 1200 Pillcam® and MiroCam® still frames (equally distributed, with or without angiectasias).
Ocular manifestations in hereditary hemorrhagic telangiectasia (Rendu-Osler-Weber disease): a case-series.
Ophthalmic Genet
March 2011
Eye Clinic, Second University of Naples, Naples, Italy.
Background: Hereditary hemorrhagic telangiectasia (Rendu-Osler-Weber disease) is an autosomal dominant vascular disorder characterized by severe and recurrent nosebleeds, muco-cutaneous telangiectasias, and, in some cases, life-threatening visceral arteriovenous malformations. Ocular abnormalities include conjunctival telangiectasia, arteriovenous fistula, angiectasia, phlebectasia, and angioma.
Material And Methods: We describe the ocular abnormalities in 8 patients from a pedigree with hereditary hemorrhagic telangiectasia.
Diagnostic yield and clinical implications of push enteroscopy: results from a nonspecialized center.
J Clin Gastroenterol
March 2003
Departmentof Medicine, Division of Gastroenterology and Hepatology, University of Alabama at Birmingham, 35294, USA.
BACKGROUND Push enteroscopy is increasingly used as an investigative tool for the evaluation of gastrointestinal bleeding, and studies from specialized centers have shown an overall diagnostic yield of push enteroscopy in such patients ranging from 38% to 75%. The aim of our study was to characterize the yield and clinical effect of push enteroscopy to determine the applicability of prior observations to other academic centers. STUDY We retrospectively studied patients who underwent push enteroscopy between January 1995 and December 2000 at our institution.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!