The learning curve, interobserver, and intraobserver agreement of endoscopic confocal laser endomicroscopy in the assessment of mucosal barrier defects

Chang, Jeff; Ip, Matthew H.; Yang, Michael; Wong, Brendon; Power, Theresa; Lin, Lisa; Xuan, Wei; Phan, Tri Giang; Leong, Rupert W.

doi:10.1016/j.gie.2015.08.045

Cited by 30 publications

(36 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These data sit well with another recent study that inter-observer and intra-observer agreement is high in CLE and has a relatively short learning curve that does not require prior histological experience [7].…”

supporting

confidence: 91%

“…Only further clinical trails can answer this question. The development of the probe-based CLE instrument facilitates the collection of CLE images during conventional colonoscopy and requires little experience [7], obviating the need for a dedicated confocal colonoscope, setting the stage for its widespread acceptance, particularly if its clinical benefits are supported by clinical trial data. Nevertheless, it remains to be shown that colonoscopy with or without CLE is superior to simpler and cheaper surrogate markers of mucosal healing such as fecal calprotectin [12].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Confocal Laser Endomicroscopy in the Management of IBD: Clearly Superior?

Watson

2016

Dig Dis Sci

View full text Add to dashboard Cite

supporting

confidence: 91%

mentioning

confidence: 99%

Confocal Laser Endomicroscopy in the Management of IBD: Clearly Superior?

Watson

2016

Dig Dis Sci

View full text Add to dashboard Cite

“…In this study, 155 confocal images were obtained from a previous clinical trial conducted at the Gastroenterology and Liver Services of the Bankstown-Lidcombe Hospital (Sydney, Australia) [3]. Each patient underwent a confocal gastroscopy (Pentax EC-3870FK, Pentax, Tokyo, Japan) under conscious sedation and with a intra-venous aliquots of fluorescein sodium and topical acriflavine hydrocloride to enhance images.…”

Section: Methodsmentioning

confidence: 99%

“…Impaired epithelial barrier function is present in irritable bowel disease (IBD), irritable bowel syndrome (IBS), Crohn's disease and ulcerative colitis. Features have been introduced in the literature to assess intestinal permeability [3], [4]. In particular, for IIP, three features have been defined: Cell Drop-out (CDO), shedding of an enterocyte into the luminal space; Cell Junction Enhancement (CJE), a fluorescein build-up between two epithelial cells representing impaired tight-junction proteins before breakage of the final basal junction, and FL: a fluorescein plume entering the lumen representing loss of apposition between two adjacent cells.…”

Section: Introductionmentioning

confidence: 99%

Superpixel-based automatic segmentation of villi in confocal endomicroscopy

Boschetto

Mirzaei

Leong

et al. 2016

2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)

View full text Add to dashboard Cite

Confocal Laser Endomicroscopy (CLE) is a technique permitting on-site microscopy of the gastrointestinal mucosa after the application of a fluorescent agent, allowing the evaluation of mucosa alterations. These are used as features by skilled technicians to stage the severity of multiple diseases, celiac disease or irritable bowel syndrome among the others. We present an automatic method for villi detection from confocal endoscopy images, whose appearance changes with mucosal alterations. Superpixel segmentation, a well-known technique originating from computer vision, is used to identify and cluster together pixels belonging to uniform regions. Each image in the dataset is analyzed in a multiscale fashion (scale 1, 0.5 and 0.25). From each superpixel, 37 features are extracted at multiple image scales. Each superpixel is classified using a random forest, and a post-processing step is performed to refine the final output. Results in the test set (70 images, 30870 superpixels) show 85.87% accuracy, 92.88% sensitivity, 76.99% specificity in the superpixel space, and 86.36% of accuracy and 87.44% Dice score in the pixel domain.

show abstract

“…According to that study, experienced analysts, inexperienced analysts, and pathologists had overall mean accuracies of 95.9%, 87.8%, and 85.6%, respectively (P < .001) in recognizing CLE features of increased intestinal permeability. 11 Interobserver agreement was highest for experienced analysts than for inexperienced analysts and pathologists, whereas fluorescein leakage had the best interobserver agreement. 11 Attempts to design software for the automated classification of mucosal lesions have been made in prior studies.…”

mentioning

confidence: 90%