Background And Study Aims: An endocytoscope system (ECS) has recently been developed with the possibility of super-high magnification of gastrointestinal mucosa, thus allowing in vivo imaging of living cells. The aim of the present study was to assess the potential of ECS in the prediction of histology in both normal gastrointestinal mucosa and neoplastic lesions.
Patients And Methods: In total, 76 patients (57 men, 19 women; age range 37-86 years) with neoplastic lesions in the esophagus, stomach, or colon were enrolled into the study and underwent esophagogastroduodenoscopy or colonoscopy. After staining with 1% methylene blue, the mucosa was examined with the ECS probe (x 450 and x 1100 magnification), and video sequences were recorded on video disk. Biopsies from the examined areas were taken for histology and served as the gold standard. The endocytoscope video sequences were evaluated by two blinded pathologists. Finally the results were compared with those resulting from the evaluation of an experienced endoscopist who was aware of the macroscopic endoscopic pictures and the endocytoscope image results.
Results: A total of 25 patients with esophageal lesions, 28 patients with colonic lesions, and 23 patients with gastric lesions were examined. The sensitivity and specificity for the evaluation of the blinded pathologists was 81% and 100%, respectively, in the esophagus, 56% and 89% in the stomach, and 79% and 90% in the colon. If an endoscopist evaluated the endocytoscopic pictures in combination with the macroscopic endoscopic images sensitivity and specificity increased significantly.
Conclusions: First experiences with ECS show good sensitivity rates even by blinded assessment for esophageal and colonic lesions. Sensitivity for neoplastic lesions in the stomach is lower because of gastric mucous secretion. Combining the endoscopic and cytoscopic appearance of the lesion may further enhance the diagnostic value of the method.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1055/s-2007-966446 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Feasibility of new-generation endocytoscopy for the real-time diagnosis of ampullary lesions: A pilot study (with video).
J Gastroenterol Hepatol
July 2024
Department of Internal Medicine, College of Medicine, National Taiwan University, Taipei, Taiwan.
Background And Aim: An early and accurate diagnosis of ampullary neoplasia is crucial; however, sampling bias is still a major concern. New-generation endocytoscopy enables real-time visualization of cellular structures and enables an accurate pathological prediction; however, its feasibility for small ampullary lesions has never been investigated.
Methods: We developed a novel endocytoscopic (EC) classification system for ampullary lesions after an expert review and agreement from five experienced endoscopists and one pathologist.
Optical Biopsy of Dysplasia in Barrett's Oesophagus Assisted by Artificial Intelligence.
Cancers (Basel)
March 2023
Department of Gastroenterology and Hepatology, University Medical Center Groningen, University of Groningen, 9713 GZ Groningen, The Netherlands.
Optical biopsy in Barrett's oesophagus (BE) using endocytoscopy (EC) could optimize endoscopic screening. However, the identification of dysplasia is challenging due to the complex interpretation of the highly detailed images. Therefore, we assessed whether using artificial intelligence (AI) as second assessor could help gastroenterologists in interpreting endocytoscopic BE images.
View Article and Find Full Text PDFEndocytoscopy for assessing histologic inflammation in ulcerative colitis: development and prospective validation of the ELECT (ErLangen Endocytoscopy in ColiTis) score (with videos).
Gastrointest Endosc
January 2023
Department of Medicine I, Division of Gastroenterology, Ludwig Demling Endoscopy Center of Excellence, University Hospital of Erlangen, University Erlangen-Nürnberg, Erlangen, Germany.
Background And Aims: Apart from endoscopic healing as an established treatment goal in patients with inflammatory bowel disease (IBD), histologic remission is an emerging endpoint that might even better predict disease outcome, especially in ulcerative colitis (UC). Within this study, we aimed to evaluate whether endocytoscopy (EC) as an in vivo contact microscopy technology can accurately assess histologic inflammation and predict the further course of disease in UC patients.
Methods: Initially, a new and intuitive EC score reflecting the entire spectrum of microscopic disease activity in UC was consensually developed.
Background: Endocytoscopy (ECS) aids early gastric cancer (EGC) diagnosis by visualization of cells. However, it is difficult for non-experts to accurately diagnose EGC using ECS. In this study, we developed and evaluated a convolutional neural network (CNN)-based system for ECS-aided EGC diagnosis.
View Article and Find Full Text PDFAI analysis and modified type classification for endocytoscopic observation of esophageal lesions.
Dis Esophagus
September 2022
AI Medical Service Inc., Tokyo, Japan.
Endocytoscopy (EC) facilitates real-time histological diagnosis of esophageal lesions in vivo. We developed a deep-learning artificial intelligence (AI) system for analysis of EC images and compared its diagnostic ability with that of an expert pathologist and nonexpert endoscopists. Our new AI was based on a vision transformer model (DeiT) and trained using 7983 EC images of the esophagus (2368 malignant and 5615 nonmalignant).
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!