Challenges and Future of Wireless Capsule Endoscopy

Artificial intelligence to improve polyp detection and screening time in colon capsule endoscopy

Colon Capsule Endoscopy (CCE) is a minimally invasive procedure which is increasingly being used as an alternative to conventional colonoscopy. Videos recorded by the capsule cameras are long and require one or more experts' time to review and identify polyps or other potential intestinal problems that can lead to major health issues. We developed and tested a multi-platform web application, AI-Tool, which embeds a Convolution Neural Network (CNN) to help CCE reviewers. With the help of artificial intelligence, AI-Tool is able to detect images with high probability of containing a polyp and prioritize them during the reviewing process. With the collaboration of 3 experts that reviewed 18 videos, we compared the classical linear review method using RAPID Reader Software v9.0 and the new software we present. Applying the new strategy, reviewing time was reduced by a factor of 6 and polyp detection sensitivity was increased from 81.08 to 87.80%.

Soft hybrid intrinsically motile robot for wireless small bowel enteroscopy

BACKGROUND

Difficulties in establishing diagnosis of small bowel (SB) disorders, prevented their effective treatment. This problem was largely resolved by wireless capsule endoscopy (WCE), which has since become the first line investigation for suspected SB disorders. Several types of WCE pills are now used in clinical practice, despite their limitations and complications. WCE pills are large, rigid and immotile capsules. When swallowed, they provide SB enteroscopy downloaded to a data logger carried by the patient. Most of the complications of WCEs result from lack of intrinsic locomotion: incomplete examination, capsule retention and impaction within strictures. In addition, the rigid nature and size of current generation of WCE pills is accompanied by 0.1% inability to swallow the pill by patients with normal esophageal motility.

METHODS

The aim of this communication is to describe the initial prototype, P1, which is thinner and slightly longer than the current generation of WCEs. In addition, it exhibits intrinsic active locomotion, produced by vibrating silicon legs. These generate a controlled-skid locomotion on the small bowel mucosal surface, rendered slippery by surface mucus and intraluminal surfactant bile salts. We demonstrate the mechanism responsible for the active locomotion of P1, which we consider translatable into a working prototype, suitable for further R&D for eventual clinical translation.

RESULTS

The shape and attachment of the rubber vibrating legs to vibrating actuators, have been designed specifically to produce a tight clockwise circular motion. When inserted inside a circular tube in vitro of equivalent diameter to human small intestine, the intrinsic circular clockwise motion of P1 translates into a linear locomotion by the constraints imposed by the surrounding circular walls of SB and rest of the gastrointestinal tract. This design ensures device stability during transit, essential for imaging and targeting lesions encountered during the enteroscopy. We preformed two experiments: (i) transit of P1 through a phantom consisting of a segment of PVC tube placed on a horizontal surface and (ii) transit through a transparent slippery nylon sleeve insufflated with air. In the PVC tube, its transit rate averages 15.6 mm/s, which is too fast for endoscopy: whereas inside the very slippery nylon sleeve insufflated with air, the average transit rate of P1 is reduced to 5.9 mm/s, i.e., ideal for inspection endoscopy.

CONCLUSIONS

These in-vitro experiments indicate that the P1 hybrid soft robot prototype has the potential specifically for clinical translation for SB enteroscopy.

A systematic review of symptomatic hamartomas of the jejunum and ileum

INTRODUCTION

Gastrointestinal hamartomas are rarely encountered benign growths made of an abnormal mixture of tissues normally found in the body where the growth occurs. Most hamartomas are asymptomatic and diagnosed incidentally. Evidence regarding symptomatic hamartomas of the jejunum and ileum is limited and restricted to anecdotal case reports. We aim to provide a contemporary overview to clarify various aspects linked to symptomatic hamartomas, helping aide management and clinical decision-making.

METHODS

The search terms 'small bowel', 'small intestine', 'jejunum' and 'ileum' were combined with 'hamartoma'. Embase, Medline, PubMed searches and Google Scholar hand-searches were conducted. All English language papers from 1 January 2000 to 1 June 2020 were included.

RESULTS

In total 39 cases were reviewed: 29 adults and 10 paediatric (0-16 years). Presenting symptoms included abdominal pain (87%), vomiting (56%), gastrointestinal bleeding (20.5%) and weight loss (5%); 36 of 39 cases (92%) presented as emergencies. Diagnostic investigations included: abdominal x-ray (49%), endoscopy (38%), computed tomography (56%), magnetic resonance imaging (5%), contrast study (15%) and video capsule endoscopy (5%). Initial management strategy was either open (30) or laparoscopic (7) surgery or endoscopy (2). All cases required surgery for definitive management. Twenty-five cases recorded hamartoma size, and mean maximum diameter was 3.56cm (1.2-8cm) with stricturing in seven cases. Nine of the 39 cases were associated with hamartomatous syndromes. Two mortalities were recorded.

CONCLUSIONS

This is the first published review addressing symptomatic hamartomas of the jejunum and ileum. New data relating to demographic cohort, symptom profile, investigations, management strategies, and morbidity and mortality provide greater insight to those encountering this challenging clinical finding in the future.

Artificial intelligence for cancer detection in upper gastrointestinal endoscopy, current status, and future aspirations

This minireview discusses the benefits and pitfalls of machine learning, and artificial intelligence in upper gastrointestinal endoscopy for the detection and characterization of neoplasms. We have reviewed the literature for relevant publications on the topic using PubMed, IEEE, Science Direct, and Google Scholar databases. We discussed the phases of machine learning and the importance of advanced imaging techniques in upper gastrointestinal endoscopy and its association with artificial intelligence.

Effect of Nonsteroidal Anti-inflammatory Agents on Small Intestinal Injuries as Evaluated by Capsule Endoscopy

BACKGROUND

Currently, because the population is aging, use of medications has been increasing, including use of nonsteroidal anti-inflammatory drugs (NSAIDs) and antithrombotic agents.

AIMS

This study aims to investigate whether NSAIDs can cause damage to the small bowel (SB) mucosa.

METHODS

Endoscopic videos of subjects who had undergone capsule endoscopy (CE) were evaluated by three experts in order to identify SB injury. All medications taken within 2 weeks from the time of CE were investigated. Cases with a final diagnosis of intestinal tuberculosis, inflammatory bowel disease, Behcet's disease, Peutz-Jeghers syndrome, small bowel lymphoma, or Henoch-Schönlein purpura were excluded from the analysis.

RESULTS

Among the 273 subjects, 125 (45.8%) had SB erosions or ulcers (erosion group) and the remaining 148 (54.2%) did not (no erosion group). SB erosions or ulcers were more common in females, patients aged > 60 years, and subjects taking NSAIDs (p = 0.048, 0.032, and < 0.001, respectively). No statistically significant differences were found between the two groups in the following variables: history of cancer and GI surgery, reasons for the test, comorbidities, and use of anticoagulants and antiplatelet agents. Multivariate analysis showed that use of NSAIDs [OR 4.191 (95% CI 1.858-9.458), p < 0.001] was an independent risk factor for SB erosions or ulcers.

CONCLUSIONS

Use of NSAIDs is the only independent risk factor for SB injury identified in this study. Antithrombotic agents do not cause or exacerbate damage to the SB, according to our results.

CLINICAL TRIAL REGISTRATION

KCT0004795.

The Optimal Timing for Using Capsule Endoscopy for Patients with Gastrointestinal Bleeding

Objectives

Capsule endoscopy (CE) is a useful diagnostic modality for patients with occult gastrointestinal (GI) bleeding. However, most previous studies utilizing CE have focused on techniques, patient characteristics, safety and feasibility, and case analyses. Studies evaluating the optimal timing for utilizing CE, which is an essential factor for obtaining a better diagnostic yield, remain scarce in the literature. Considering that a CE examination is expensive, we, therefore, undertook this study to evaluate, analyze, and determine the optimal time for performing CE in patients with occult GI bleeding.

Methods

Seventy-five patients were initially recruited, but finally, sixty patients with significant GI bleeding with an unknown etiology after traditional endoscopic examinations were included in the study. All data were collected from a local hospital in Taiwan, encompassing the period from 2010 to 2018. The relationship between the timing of CE examination and the diagnostic correction rate (DCR) was then analyzed statistically.

Results

More female (58.3%) and older adult (68.3%) patients were in our study. Based on the four analytical models used in the study, the results showed that the most optimal time to perform CE is within three days after GI bleeding occurs.

Oral ingestion versus endoscopic delivery of endoscopic capsule in patients with previous gastrointestinal surgery (ORENCES study): A Spanish multicentre observational study

BACKGROUND

Small Bowel Capsule Endoscopy is the first-choice technique for investigating the majority of small bowel diseases. Its most common complications are related to incomplete examinations and capsule retention. There is no consensus on how patients with previous gastrointestinal surgery should receive the capsule.

OBJECTIVE

The primary endpoint was to compare the rate of complete small-bowel examinations (completion rate) between oral ingestion and endoscopic delivery of the capsule. The secondary endpoint was to compare diagnostic yield and adverse events in the two groups.

METHODS

A retrospective observational study was conducted in nine hospitals in Spain. Demographic data, previous surgery, indication for capsule endoscopy, intestinal transit time, diagnosis, completion rate (percentage of capsules reaching the caecum), diagnostic yield (percentage of results compatible with indication for the exam) and adverse events were collected.

RESULTS

From January 2009 to May 2019 fifty-seven patients were included (39 male, mean age 66±15 years). The most common indications for the exam were "overt" (50.9%) and "occult" (35.1%) small bowel bleeding. Previous Billroth II gastrectomy and Roux-en-Y gastric bypass were present in 52.6% and 17.5% of patients respectively. The capsule was swallowed in 34 patients and placed endoscopically in 23 patients. No significant differences were observed between the oral ingestion and endoscopic delivery groups in terms of completion rate (82.4% vs. 78.3%; p=0.742), diagnostic yield (41.2% vs. 52.2%; p=0.432) or small bowel transit time (301 vs. 377min, p=0.118). No capsule retention occurred. Only one severe adverse event (anastomotic perforation) was observed in the endoscopic delivery group.

CONCLUSIONS

In our case series, there were no significant differences between oral ingestion and endoscopic delivery in terms of completion rate, diagnostic yield or safety. Being less invasive, oral ingestion of the capsule should be the first-choice method in patients with previous gastrointestinal surgery.

Current Status of Interpretation of Small Bowel Capsule Endoscopy

Capsule endoscopy (CE) has revolutionized direct small bowel imaging and is widely used in clinical practice. Remote visualization of bowel images enables painless, well-tolerated endoscopic examinations. Small bowel CE has a high diagnostic yield and the ability to examine the entire small bowel. The diagnostic yield of CE relies on lesion detection and interpretation. In this review, issues related to lesion detection and interpretation of CE have been addressed, and the current status of automated reading software development has been reviewed. Clinical significance of an external real-time image viewer has also been described.

Small bowel villous atrophy: celiac disease and beyond

Small bowel villous atrophy can represent a diagnostic challenge for gastroenterologists and pathologists. In Western countries small bowel atrophy and mild non-atrophic alterations are frequently caused by celiac disease. However, other pathology can mimic celiac disease microscopically, widening the differential diagnosis. The several novelties on this topic and the introduction of the device-assisted enteroscopy in the diagnostic flowchart make an update of the literature necessary. Areas covered: In this review, a description of the different clinical scenarios when facing with small bowel mucosal damage, particularly small bowel atrophy, is described. The published literature on this subject has been summarized and reviewed. Expert commentary: When an intestinal mucosal alteration is histologically demonstrated, the pathology report forms part of a more complex workup including serological data, clinical presentation and clinical history. A multidisciplinary team, including pathologists and enteroscopy-devoted endoscopists, is frequently required to manage patients with small bowel alterations, especially in cases of severe malabsorption syndrome.