Current Controversies Concerning Capsule Endoscopy

The Use of Artificial Intelligence for Endoscopic Evaluation of the Small Bowel

There remains great potential for widespread implementation of artificial intelligence (AI) in managing small bowel disorders. Studies have shown excellent accuracy in diagnosing various diseases and lesions throughout the small bowel, with most showing equivalency or superiority to expert endoscopists or capsule readers. AI has significant potential to improve efficiency in small bowel investigation and, depending on the relative costs of these new technologies, could reduce health care expenditure. AI algorithms for capsule endoscopy will offer many clinical and efficiency benefits but we also must remain alert to new risks, particularly with regard to automation bias and unique cybersecurity considerations.

Inpatient Small Bowel Capsule Endoscopy: Not Associated With Bleeding Site Identification or 30-Day Readmission Prevention

Background The utility of small bowel capsule endoscopy (SBCE) in the inpatient setting is controversial due to retention rates and costs. Aim This study aims to evaluate whether using SBCE significantly improved the identification of potential bleeding sites or reduced the risk of 30-day readmission for overt or occult gastrointestinal bleeding. Methods This was a single-center retrospective cohort study involving inpatients who underwent SBCE at a suburban tertiary care hospital from January 1, 2012, to January 1, 2022, for suspected small bowel bleeding. There was no control group used in this observational study. We used chi-square testing to determine the significance among our categorical variables and t-tests to compare means for our numerical variables. We also did multivariable logistic regression to analyze risk factors for increased hospital stay. All statistical analysis was done in R (R Core Team, 2020, R Foundation for Statistical Computing, Vienna, Austria). Results We identified 514 inpatients who underwent SBCE from January 1, 2012, to January 1, 2022, including 300 (58.4%) men and 214 (41.6%) women. Most (305/514, 59.3%) had no notable findings on SBCE, but 209/514 (40.7%) subsequently underwent endoscopic procedures, and a bleeding site was identified and treated in 168/209 (80.4%). Undergoing a subsequent procedure significantly increased the average number of days between capsule deployment and discharge (9.6 vs. 4.9 days, p < 0.005) without significantly reducing the risk for 30-day readmission (OR 1.33, 95% CI 0.9-1.9, p = 0.2). Among the 209 patients who had a subsequent procedure, identifying and treating a bleeding site did not significantly change readmission rates (OR 1.35, 95% CI 0.6-3.1, p = 0.5) compared to patients who did not have a procedure. Conclusion We did not find that inpatient SBCE significantly affected 30-day readmission rates even if an endoscopic procedure was subsequently done or a potential bleeding site was treated.

Patients on Antithrombotic Agents with Small Bowel Bleeding -Yield of Small Bowel Capsule Endoscopy and Subsequent Management

BACKGROUND AND AIMS

Small bowel gastrointestinal bleeding (GIB) is associated with multiple blood transfusions, prolonged and/or multiple hospital admissions, utilization of significant healthcare resources, and negative effects on patient quality of life. There is a well-recognized association between antithrombotic medications and small bowel GIB. We aimed to identify the diagnostic yield of small bowel capsule endoscopy (SBCE) in patients on antithrombotic medications and the impact of SBCE on treatment course.

METHODS

The electronic medical records of nineteen hundred eighty-six patients undergoing SBCE were retrospectively reviewed.

RESULTS

The diagnostic yield for detecting stigmata of recent bleeding and/or actively bleeding lesions in SBCE was higher in patients that were on antiplatelet agents (21.6%), patients on anticoagulation (22.5%), and in patients that had their SBCE performed while they were inpatient (21.8%), when compared to the patients not on antiplatelet agents (12.1%), patients not on anticoagulation (13.5%), and with patients that had their SBCE performed in the outpatient setting (12%). Of 318 patients who had stigmata of recent bleeding and/or actively bleeding lesion(s) identified on SBCE, SBCE findings prompted endoscopic evaluation (small bowel enteroscopy, esophagogastroduodenoscopy (EGD), and/or colonoscopy) in 25.2%, with endoscopic hemostasis attempted in 52.5%.

CONCLUSIONS

Our study, the largest conducted to date, emphasizes the importance of performing SBCE as part of the evaluation for suspected small bowel bleeding, particularly in patients taking antithrombotic therapy, and especially during their inpatient hospital stay.

Small bowel capsule endoscopy examination and open access database with artificial intelligence: The SEE-artificial intelligence project

OBJECTIVES

Artificial intelligence (AI) may be practical for image classification of small bowel capsule endoscopy (CE). However, creating a functional AI model is challenging. We attempted to create a dataset and an object detection CE AI model to explore modeling problems to assist in reading small bowel CE.

METHODS

We extracted 18,481 images from 523 small bowel CE procedures performed at Kyushu University Hospital from September 2014 to June 2021. We annotated 12,320 images with 23,033 disease lesions, combined them with 6161 normal images as the dataset, and examined the characteristics. Based on the dataset, we created an object detection AI model using YOLO v5 and we tested validation.

RESULTS

We annotated the dataset with 12 types of annotations, and multiple annotation types were observed in the same image. We test validated our AI model with 1396 images, and sensitivity for all 12 types of annotations was about 91%, with 1375 true positives, 659 false positives, and 120 false negatives detected. The highest sensitivity for individual annotations was 97%, and the highest area under the receiver operating characteristic curve was 0.98, but the quality of detection varied depending on the specific annotation.

CONCLUSIONS

Object detection AI model in small bowel CE using YOLO v5 may provide effective and easy-to-understand reading assistance. In this SEE-AI project, we open our dataset, the weights of the AI model, and a demonstration to experience our AI. We look forward to further improving the AI model in the future.

Endoscopic Treatment of Small Bowel Bleeding

Approximately 5% of all gastrointestinal (GI) bleeding originates from the small bowel. Endoscopic therapy of small bowel bleeding should only be undertaken after consideration of the different options, and the risks, benefits, and alternatives of each option. Endoscopic therapy options for small bowel bleeding are like those treatments used for other forms of bleeding in the upper and lower GI tract. Available endoscopic treatment options include thermal therapy (eg, argon plasma coagulation and bipolar cautery), mechanical therapy (eg, hemoclips), and medical therapy (eg, diluted epinephrine injection). Patients with complicated comorbidities would benefit from evaluation and planning of available treatment options, including conservative and/or medical treatments, beyond endoscopic therapy.

Computer vision-based solutions to overcome the limitations of wireless capsule endoscopy

Endoscopic investigation plays a critical role in the diagnosis of gastrointestinal (GI) diseases. Since 2001, Wireless Capsule Endoscopy (WCE) has been available for small bowel exploration and is in continuous development. Over the last decade, WCE has achieved impressive improvements in areas such as miniaturisation, image quality and battery life. As a result, WCE is currently a very useful alternative to wired enteroscopy in the investigation of various small bowel abnormalities and has the potential to become the leading screening technique for the entire gastrointestinal tract. However, commercial solutions still have several limitations, namely incomplete examination and limited diagnostic capacity. These deficiencies are related to technical issues, such as image quality, motion estimation and power consumption management. Computational methods, based on image processing and analysis, can help to overcome these challenges and reduce both the time required by reviewers and human interpretation errors. Research groups have proposed a series of methods including algorithms for locating the capsule or lesion, assessing intestinal motility and improving image quality.In this work, we provide a critical review of computational vision-based methods for WCE image analysis aimed at overcoming the technological challenges of capsules. This article also reviews several representative public datasets used to evaluate the performance of WCE techniques and methods. Finally, some promising solutions of computational methods based on the analysis of multiple-camera endoscopic images are presented.

Capsule endoscopy retention in Zenker´s diverticulum

Clinical case of a patient who underwent small bowel examination with endoscopic capsule which was never recovered and two years later presented with dysphagia and was found with the capsule inside a Zenker´s diverticulum.

Prognostic Analysis of Liver Cirrhosis Patients with Cerebral Infarction and/or Gastrointestinal Hemorrhage: A Retrospective Cohort Study

Background

To explore the risk factors of gastrointestinal hemorrhage and/or cerebral infarction complications in liver cirrhosis and provide evidence for early prevention, clinical diagnosis, and treatment of liver cirrhosis.

Methods

200 liver cirrhosis patients were analyzed: liver cirrhosis (n = 78), liver cirrhosis complicated with cerebral infarction (n = 43), liver cirrhosis complicated with gastrointestinal hemorrhage (n = 57), and liver cirrhosis complicated with gastrointestinal hemorrhage and cerebral infarction (n = 22). The incidence of disease in each group of patients at different times was calculated. Multivariate logistic regression was used to analyze the risk factors of liver cirrhosis patients with gastrointestinal hemorrhage and cerebral infarction. After 12 months of follow-up, the mortality rate of each group was calculated.

Results

The incidences of gastrointestinal hemorrhage, cerebral infarction, and gastrointestinal hemorrhage combined with cerebral infarction in patients with liver cirrhosis were 21.5%, 28.5%, and 11%, respectively. The width of the portal vein, D-2 polymer, albumin (ALB), and hemoglobin (Hb) were predictors of gastrointestinal hemorrhage and cerebral infarction in patients with liver cirrhosis. Age, hypertension, bleeding history, infection, portal vein width, and D-2 polymer were confirmed as risk factors for gastrointestinal hemorrhage and cerebral infarction in patients with liver cirrhosis. ALB and Hb were independent protective factors. Patients with liver cirrhosis and gastrointestinal hemorrhage with cerebral infarction had the worst survival.

Conclusion

Age, hypertension, bleeding history, infection, portal vein width, and D-2 polymer are all independent risk factors for gastrointestinal bleeding and cerebral infarction, while ALB and Hb are independent protective factors.

Impact of Early Video Capsule Endoscopy on Hospitalization and Post-hospitalization Outcomes: A Propensity Score-Matching Analysis

INTRODUCTION

Video capsule endoscopy (VCE) has become the accepted evaluation of choice for patients with suspected small bowel bleeding. Our aim was to evaluate the impact of early as compared to delayed inpatient VCE on post-index hospitalization readmission rates.

METHODS

We performed a retrospective study using medical claims from the IBM® Marketscan® Commercial Database from January 1, 2004, through September 30, 2018, including adult patients that underwent an inpatient VCE. Early VCE was defined as occurring on days 0, 1, or 2 of the index hospitalizations, whereas delayed VCE was performed on days 3-7. Propensity matching was performed to create an analytic cohort, and outcomes were assessed using logistic regression.

RESULTS

Following propensity score matching, 607 patients undergoing early VCE were matched 1:1 with 607 patients undergoing delayed VCE. The median patient age was 65 (IQR: 56-78) years, and 560 (37.9%) of the included patients were female. The mean time to VCE was 1.6 (± 0.6) days for the early VCE group and 4.0 (± 1.2) days from admission for delayed VCE. In unadjusted comparisons, we found no significant difference between early VCE and delayed VCE with respect to 90-day all-cause readmission (18.6% vs. 17.0%, P = 0.5) or 90-day rebleeding risk (10.5% vs. 8.7%, P = 0.331). Patients undergoing an early VCE had a shorter hospital LOS and less total hospitalization charges.

CONCLUSION

Early as compared to delayed inpatient VCE was associated with a reduction in index hospitalization resource utilization. No differences were found with respect to reductions in readmissions or rebleeding events.

Capsule endoscopy in airway: a difficult extraction

Foreign bodies of different nature are identified in airway. Extraction of foreign bodies given their dimension and character requires proper set of instruments with right technique to ensure safe removal. Different tools have been discussed to optimally withdraw the object in various articles which have been applied. However, we talk about a case of removal of a pill camera from an elderly patient’s right main bronchus with a certain positioning of the patient after multiple unsuccessful attempts with instruments alone. In conclusion, pill camera as being useful for surveillance for gastrointestinal pathology can have the potential of aspiration.

Magnetically controlled capsule endoscopy in one-time gastro-small intestinal joint examination: a two-centre experience

BACKGROUND

The lesions of certain diseases are widely distributed in both stomach and small intestine, while the step-by-step strategy of gastroscopy followed by enteroscopy can be burdensome and costly. We aimed to determine if magnetically controlled capsule endoscopy (MCE) could be used in one-time gastro-small intestine (GSI) joint examination.

METHODS

In this study, data of patients in Chinese PLA General Hospital and Changhai Hospital who underwent MCE GSI examination from January 2020 to August 2021 were retrospectively analysed. The primary outcome of this study was the success rate of one-time GSI joint examination, and secondary outcomes included visualization and cleanliness of gastrointestinal tract, gastrointestinal transit times, diagnostic yield and safety of MCE examination.

RESULTS

A total of 768 patients were included. The success rate of one-time GSI joint examination was 92.58%. There were 94.92% MCEs observed > 90% gastric mucosa in the 6 anatomic landmarks. The rate of complete small bowel examination was 97.40%. The median gastric examination time, gastric transit time and small intestine transit time were 8.18 min, 63.89 min and 4.89 h, respectively. Magnetic steering of MCE significantly decreased gastric transit time (8.92 min vs. 79.68 min, P = 0.001) and increased duodenal lesion detection rate (13.47% vs. 6.26%, P = 0.001) when compared with non-magnetic steering group. Two capsules were retained and were removed by enteroscopy or spontaneously excreted.

CONCLUSIONS

MCE is feasible to complete GSI joint examination and the detection of both gastric and small intestinal diseases can be achieved simultaneously. Trial registration Clinical Trial Registration ClinicalTrials.gov, ID: NCT05069233.

Diagnostic value of capsule endoscopy and double-balloon enteroscopy in small bowel diseases

OBJECTIVE

To analyze the diagnostic value of capsule endoscopy (CE) and double-balloon enteroscopy (DBE) in small bowel diseases.

METHODS

The clinical data of 134 cases of CE and 109 cases of DBE examined in our gastroscopy room from January 2016 to December 2019 were retrospectively analyzed. The two groups of patients were compared as to disease diagnostic rate, examination time, examination tolerance, and incidence of adverse reactions.

RESULTS

The two groups showed no significant difference in general data (all P>0.05). The DBE group showed a higher disease diagnostic rate than the CE group (P<0.05). Significantly higher rates of suspected intestinal bleeding were observed in the DBE group than those of the CE group (P<0.05), but no significant differences were found in the diagnosis of unexplained abdominal pain, abdominal distension, and others (all P>0.05). The DBE group required a longer examination time, and had a higher incidence of adverse reactions, and a lower examination tolerance than the CE group (P<0.05).

CONCLUSION

Both DBE and CE are effective in small bowel diseases diagnoses, but DBE demonstrated greater potential in diagnosing small bowel bleeding.

Undiagnosed Endoscopy Capsule Retention Causing Delayed Intestinal Obstruction in a Patient with a Small Bowel Neuroendocrine Tumor

BACKGROUND Capsule endoscopy has played a significant role in small bowel investigation, providing the opportunity of detecting neoplastic lesions to a greater degree and at an earlier stage than other diagnostic procedures. Failure to excrete the capsule with the feces within 48 h can lead to capsule retention with increased risk of further complications such as bowel obstruction and perforation. Capsule retention can remain undetected in case of incomplete follow-up and poor patient compliance. Acute small bowel obstruction as late as many months following capsule endoscopy investigation is very rare, with only a few cases reported in the published literature. We herein report a rare case of prolonged capsule retention which remained undiagnosed, resulting in small bowel obstruction 6 months after the initial investigation. CASE REPORT An 82-year-old woman presented with abdominal pain and symptoms suggestive of intestinal obstruction. The patient history included a capsule endoscopy investigation because of episodes of abdominal pain 6 months prior to admission. Both the outcome of the investigation and the excretion of the capsule remained undetermined due to her history of dementia and follow-up failure. Radiologic investigations identified the capsule causing small bowel obstruction. Upon surgery, the capsule was found to be impacted in a stenotic small bowel lesion, and a segmental small bowel resection was performed. Histologic examination revealed the presence of a stenotic small bowel neuroendocrine tumor. CONCLUSIONS Appropriate follow-up is necessary to diagnose the complication of capsule retention which, if it remains unrecognized, can cause life-threatening complications as late as many months after capsule endoscopy.

Assessment of Video Capsule Endoscopy in the Management of Acute Gastrointestinal Bleeding During the COVID-19 Pandemic

IMPORTANCE

Evaluation of acute gastrointestinal (GI) bleeding using invasive endoscopic procedures comprising the standard of care (SOC)-upper endoscopy and colonoscopy-can expose the endoscopy staff to SARS-CoV-2. Video capsule endoscopy (VCE) does not generate aerosols and only requires 1 person to manage the procedure.

OBJECTIVE

To examine the safety of VCE for the initial evaluation of GI bleeding at the peak of the COVID-19 pandemic to identify signs of active bleeding while minimizing patient and personnel exposure, saving personal protective equipment, and avoiding invasive or unnecessary procedures.

DESIGN, SETTING, AND PARTICIPANTS

A multicenter (UMass Memorial Medical Center and Louisiana State University Health Sciences Center) retrospective cohort study including 146 patients with COVID-19 who received VCE as the first-line diagnostic modality was conducted from March 15 to June 15, 2020, compared with SOC in January 2020 for evaluation of GI bleeding. The association between treatment and outcomes was estimated using multivariable regression adjusting for potential confounders. Propensity score matching was used to verify the results.

MAIN OUTCOMES AND MEASURES

The primary end point was detection of active bleeding or stigmata of recent bleeding. Secondary end points included the number of patients requiring any invasive procedures, number of additional procedures, rates of rebleeding and rehospitalization, transfusion requirements, and mortality.

RESULTS

Among 146 patients, 92 (63.0%) were men; mean (SD) age was 64.93 (14.13) years in the COVID-19 group and 61.33 (13.39) years in the SOC group. Active bleeding or stigmata of recent bleeding was observed in 44 (59.5%) patients in the COVID-19 group compared with 18 (25.0%) in the SOC group (adjusted odds ratio, 5.23; 95% CI, 2.23 to 12.27). Only 36 patients (48.7%) in the COVID-19 group required any invasive procedure during the hospitalization compared with 70 (97.2%) in the SOC group (adjusted odds ratio, 0.01; 95% CI, 0.001 to 0.08). The mean (SD) number of invasive procedures was 0.59 (0.77) per patient in the COVID-19 group compared with 1.18 (0.48) per patient in the SOC group (adjusted difference, -0.54; 95% CI, -0.77 to -0.31). Both approaches appeared to be safe and there was no significant difference in transfusion requirements, rebleeding, rehospitalization, or in-hospital mortality. No mortality was attributed to GI bleeding in either group.

CONCLUSIONS AND RELEVANCE

In this cohort study, first-line diagnostic evaluation of acute GI bleeding using VCE appeared to be a safe and useful alternative to the traditional approach of upper endoscopy and colonoscopy. Use of VCE was associated with increased detection of active bleeding and a reduced number of invasive procedures and unnecessary exposure of personnel to SARS-CoV-2 and use of personal protective equipment.

Kvasir-Capsule, a video capsule endoscopy dataset

Artificial intelligence (AI) is predicted to have profound effects on the future of video capsule endoscopy (VCE) technology. The potential lies in improving anomaly detection while reducing manual labour. Existing work demonstrates the promising benefits of AI-based computer-assisted diagnosis systems for VCE. They also show great potential for improvements to achieve even better results. Also, medical data is often sparse and unavailable to the research community, and qualified medical personnel rarely have time for the tedious labelling work. We present Kvasir-Capsule, a large VCE dataset collected from examinations at a Norwegian Hospital. Kvasir-Capsule consists of 117 videos which can be used to extract a total of 4,741,504 image frames. We have labelled and medically verified 47,238 frames with a bounding box around findings from 14 different classes. In addition to these labelled images, there are 4,694,266 unlabelled frames included in the dataset. The Kvasir-Capsule dataset can play a valuable role in developing better algorithms in order to reach true potential of VCE technology.

Training, Reading, and Reporting for Small Bowel Video Capsule Endoscopy

Video capsule endoscopy (VCE) is an established modality for examining the small bowel. Formal training in interpretation and reporting of VCE examinations, along with assessment of performance metrics, is advocated for all gastroenterology fellowship programs. This review provides an overview of VCE minimum training requirements and competency assessment, cognitive and technical aspects of interpretation, and standardized reporting of findings. In order to optimize and advance the clinical utility of VCE, efforts must continue to promote and encourage consensus and standardization of training, definition and assessment of competence, enhancements of VCE reading tools, and use of appropriate nomenclature in VCE reports.