Bowel cleansing quality evaluation in colon capsule endoscopy: what is the reference standard?

Background: The diagnostic accuracy of colon capsule endoscopy (CCE) depends on a well-cleansed bowel. Evaluating the cleansing quality can be difficult with a substantial interobserver variation. Objectives: Our primary aim was to establish a standard of agreement for bowel cleansing in CCE based on evaluations by expert readers. Then, we aimed to investigate the interobserver agreement on bowel cleansing. Design: We conducted an interobserver agreement study on bowel cleansing quality. Methods: Readers with different experience levels in CCE and colonoscopy evaluated bowel cleansing quality on the Leighton-Rex scale and Colon Capsule CLEansing Assessment and Report (CC-CLEAR), respectively. All evaluations were reported on an image level. A total of 24 readers rated 500 images on each scale. Results: An expert opinion-based agreement standard could be set for poor and excellent cleansing but not for the spectrum in between, as the experts agreed on only a limited number of images representing fair and good cleansing. The overall interobserver agreement on the Leighton-Rex full scale was good (intraclass correlation coefficient (ICC) 0.84, 95% CI (0.82-0.85)) and remained good when stratified by experience level. On the full CC-CLEAR scale, the overall agreement was moderate (ICC 0.62, 95% CI (0.59-0.65)) and remained so when stratified by experience level. Conclusion: The interobserver agreement was good for the Leighton-Rex scale and moderate for CC-CLEAR, irrespective of the reader's experience level. It was not possible to establish an expert-opinion standard of agreement for cleansing quality in CCE images. Dedicated training in using the scales may improve agreement and enable future algorithm calibration for artificial intelligence supported cleansing evaluation. Trial registration: All included images were derived from the CAREforCOLON 2015 trial (Registered with The Regional Health Research Ethics Committee (Registration number: S-20190100), the Danish data protection agency (Ref. 19/29858), and ClinicalTrials.gov (registration number: NCT04049357)).

KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes.

BACKGROUND AND AIMS: Capsule endoscopy (CE) has revolutionized small-bowel (SB) investigation. Computational methods can enhance diagnostic yield (DY); however, incorporating machine learning algorithms (MLAs) into CE reading is difficult as large amounts of image annotations are required for training. Current databases lack graphic annotations of pathologies and cannot be used. A novel database, KID, aims to provide a reference for research and development of medical decision support systems (MDSS) for CE. METHODS: Open-source software was used for the KID database. Clinicians contribute anonymized, annotated CE images and videos. Graphic annotations are supported by an open-access annotation tool (Ratsnake). We detail an experiment based on the KID database, examining differences in SB lesion measurement between human readers and a MLA. The Jaccard Index (JI) was used to evaluate similarity between annotations by the MLA and human readers. RESULTS: The MLA performed best in measuring lymphangiectasias with a JI of 81 ±â€Š6 %. The other lesion types were: angioectasias (JI 64 ±â€Š11 %), aphthae (JI 64 ±â€Š8 %), chylous cysts (JI 70 ±â€Š14 %), polypoid lesions (JI 75 ±â€Š21 %), and ulcers (JI 56 ±â€Š9 %). CONCLUSION: MLA can perform as well as human readers in the measurement of SB angioectasias in white light (WL). Automated lesion measurement is therefore feasible. KID is currently the only open-source CE database developed specifically to aid development of MDSS. Our experiment demonstrates this potential.

Capsule Endoscopy and Deep Enteroscopy in Irritable Bowel Disease.

In approximately one-third of Crohn's disease patients, the disease is confined to the small bowel, inaccessible to the reach of standard endoscopy. Thorough and complete evaluation of the small bowel is crucial in such patients for the initial diagnosis, prognostication, and disease monitoring. Video capsule endoscopy and device-assisted enteroscopy have revolutionized the ability to visualize the small-bowel mucosa. This article reviews the literature pertaining to the use of capsule endoscopy and deep enteroscopy in established Crohn's disease, including the major indications, applications, and safety issues.

Prediction of patency capsule retention in known Crohn's disease patients by using magnetic resonance imaging.

BACKGROUND AND AIMS: Evaluation of small-bowel patency is recommended before swallowing video capsule endoscopy to prevent capsule retention. This study aimed to evaluate the ability of magnetic resonance enterography (MRE) to predict patency capsule (PC) retention in patients with Crohn's disease and to identify the most predictive imaging features for retention. METHODS: Fifty-seven patients prospectively underwent MRE and PC. Two radiologists predicted PC retention. Interrater reliability was determined by using Cohen's κ coefficient. The sensitivity, specificity, and positive and negative predictive values were calculated for the predictions. Evaluation of the imaging features was done using the t test and receiver-operating characteristics; t-tests were also performed on the clinical parameters. RESULTS: The κ value for interrater reliability was 0.58. The sensitivity, specificity, PPV, and NPV for the predictions by the 2 radiologists were 92.3%, 59%, 40%, 96.3%, and 100%, 52.3%, 38.2%, 100%, respectively. The maximal stricture length (9.7 ± 3.66 cm vs 7.0 ± 3.08 cm, P = .04) and the number of prestenotic dilations (1.9 ± 1.07 vs 1.0 ± 1.38, P = .03) were associated with PC retention. The area under the receiver-operating characteristic curves was 0.69 for the maximal stricture length and 0.751 for the number of prestenotic dilations. The phenotype of the disease was the only clinical parameter significantly correlated with PC retention. CONCLUSIONS: MRE has a high NPV and sensitivity for PC retention. When capsule retention is suggested by MRE, PC should be performed before the video capsule endoscopy examination. The maximal stricture length and the number of prestenotic dilations were found to be the most predictive imaging features for PC retention.

Video capsule endoscopy of the small bowel (PillCam SB).

PURPOSE OF REVIEW: It is 4 years since capsule endoscopy was first introduced. This disposable 27 mm x 11 mm video capsule containing its own optical dome, light source, batteries, transmitter and antenna is swallowed with water after a 12 h fast. The capsule is propelled via peristalsis through the gastrointestinal tract, capturing about 60 000 digital images and is excreted naturally. In a relatively short period, capsule endoscopy has become an important investigative tool in patients with occult gastrointestinal bleeding, suspected small bowel tumors and other abnormalities. The aim of this review is to update the reader with the main indications, performance and complications of the technique. RECENT FINDINGS: There are some clear indications for capsule endoscopy: occult gastrointestinal bleeding, suspected small bowel tumor, suspected Crohn's disease, surveillance of inherited polyposis syndromes, drug-induced small bowel injury or any abnormal small bowel imaging. Problematic areas include defining what are normal findings and the inability to take biopsies and thus differentiate between entities. SUMMARY: Capsule endoscopy has become a first-line tool to detect abnormalities in the small bowel, and is superior to all other imaging technologies. Its interplay with the new technique of double balloon enteroscopy enables the small bowel to receive proper attention, similar to other gastrointestinal organs.