Quantitative assessment of mucosal architecture using computer-based analysis of confocal laser endomicroscopy in inflammatory bowel diseases

Abstract

Confirming these results using prospective validation cohorts can substantiate that computer-based analysis of CLE images may provide new biomarkers for the diagnosis and characterization of IBD.

Many Patients With Irritable Bowel Syndrome Have Atypical Food Allergies Not Associated With Immunoglobulin E

“…In contrast to IBD or other chronic intestinal diseases, for which no challenge can be or has been performed, we could observe an immediate response to food challenge, setting our study apart from prior studies on intestinal inflammatory diseases. 16,17 In the few patients with IBD whom we subjected to CLE food challenges outside of this study, no dynamic changes were seen to any of these food antigens, except for 1 IBD patient who proved allergic to cow's milk protein.…”

Optical biopsy in gastroenterology: Focus on confocal laser endomicroscopy

“…It is likely that fully automated computer-aided diagnosis will reduce the dependence on optical diagnosis obtained in real time through CLE. In addition, it may reduce the interobserver variability associated with qualitative CLE analysis of images [33,34].…”

Computer-aided confocal laser endomicroscopy in inflammatory bowel disease: probing deeper into what it means

“…1 Given the potential for in vivo assessment, this technology has the potential to improve our real-time assessment of mucosa-based disease during endoscopy. [2][3][4] One area with emerging data regarding the use of CLE for disease-specific assessment is inflammatory bowel disease (IBD). Various studies have examined whether CLE can detect mucosal changes related to inflammation, and they have described features of inflamed mucosa such as irregular or tortuous crypts, wider lumens, and fluorescein leakage to the interstitial space.…”

“…The authors also found differences between CD and UC, and when they calculated a score to differentiate the 2 conditions it had a 92% sensitivity (75%; 99%) and 91% specificity (72%; 99%). 4 The ability of CLE to differentiate between CD and UC may prove useful and has been evaluated in prior studies. Tontini et al 10 previously introduced a CLE-IBD differentiation score based on endomicroscopy assessment of key features such as presence or absence of architecture distortion, irregular surface, decreased crypt density, discontinuous crypt architectural abnormality, focal cryptitis, and discontinuous inflammation assessed at a minimum of 5 random sites in the colon.…”

“…9,12 As an example, automated classification software has been developed to diagnose benign and dysplastic colorectal lesions, and it has been confirmed to have high performance in compared with offline interpretation by expert endoscopists. 12 The study by Queneherve et al, 4 with its computer-based tool, may minimize training time and interpretation difference and reduce procedure time. This computer-based recognition program is a promising approach to confocal image interpretation.…”