The impact of panenteric capsule endoscopy on the management of Crohn's disease

Pan-Enteric Capsule Endoscopy: Current Applications and Future Perspectives

BACKGROUND

The role of capsule endoscopy in the evaluation of the small bowel is well established, and current guidelines position it as a first-line test in a variety of clinical scenarios. The advent of double-headed capsules further enabled the endoscopic assessment of colonic mucosa and the opportunity for a one-step noninvasive examination of the entire bowel (pan-enteric capsule endoscopy [PCE]).

SUMMARY

We reviewed the technical procedure and preparation of patients for PCE, as well as its current clinical applications and future perspectives. In non-stricturing and non-penetrating Crohn's disease affecting the small bowel and colon, PCE monitors disease activity by assessing mucosal healing, a major treatment outcome, with a higher diagnostic yield than cross-sectional imaging or conventional colonoscopy. Also in ulcerative colitis, double-headed capsules have been used to monitor disease activity noninvasively. Currently, validated scoring systems have been specifically devised for these double-headed capsules and permit a standardized assessment of the inflammatory burden. In suspected mid-lower digestive bleeding, some exploratory studies have demonstrated the feasibility and high diagnostic yield of PCE, which may work as a filter indicating which patients may benefit of further invasive procedures, namely, for planned hemostatic procedures. The possibility of using PCE is also discussed in the context of polyposis syndromes with simultaneous involvement of the small intestine and colon.

KEY MESSAGES

PCE is a feasible, effective, and safe diagnostic procedure to evaluate the small bowel and colon. It has been increasingly explored in the setting of inflammatory bowel diseases and, more recently, in suspected mid-lower digestive bleeding. PCE is expected to reduce the demand for invasive procedures and expand the scope of noninvasive intestinal evaluation in the coming future.

Influence of training and expertise on deep neural network attention and human attention during a medical image classification task

In many different domains, experts can make complex decisions after glancing very briefly at an image. However, the perceptual mechanisms underlying expert performance are still largely unknown. Recently, several machine learning algorithms have been shown to outperform human experts in specific tasks. But these algorithms often behave as black boxes and their information processing pipeline remains unknown. This lack of transparency and interpretability is highly problematic in applications involving human lives, such as health care. One way to "open the black box" is to compute an artificial attention map from the model, which highlights the pixels of the input image that contributed the most to the model decision. In this work, we directly compare human visual attention to machine visual attention when performing the same visual task. We have designed a medical diagnosis task involving the detection of lesions in small bowel endoscopic images. We collected eye movements from novices and gastroenterologist experts while they classified medical images according to their relevance for Crohn's disease diagnosis. We trained three state-of-the-art deep learning models on our carefully labeled dataset. Both humans and machine performed the same task. We extracted artificial attention with six different post hoc methods. We show that the model attention maps are significantly closer to human expert attention maps than to novices', especially for pathological images. As the model gets trained and its performance gets closer to the human experts, the similarity between model and human attention increases. Through the understanding of the similarities between the visual decision-making process of human experts and deep neural networks, we hope to inform both the training of new doctors and the architecture of new algorithms.

The Future of Minimally Invasive Capsule Panendoscopy: Robotic Precision, Wireless Imaging and AI-Driven Insights

In the early 2000s, the introduction of single-camera wireless capsule endoscopy (CE) redefined small bowel study. Progress continued with the development of double-camera devices, first for the colon and rectum, and then, for panenteric assessment. Advancements continued with magnetic capsule endoscopy (MCE), particularly when assisted by a robotic arm, designed to enhance gastric evaluation. Indeed, as CE provides full visualization of the entire gastrointestinal (GI) tract, a minimally invasive capsule panendoscopy (CPE) could be a feasible alternative, despite its time-consuming nature and learning curve, assuming appropriate bowel cleansing has been carried out. Recent progress in artificial intelligence (AI), particularly in the development of convolutional neural networks (CNN) for CE auxiliary reading (detecting and diagnosing), may provide the missing link in fulfilling the goal of establishing the use of panendoscopy, although prospective studies are still needed to validate these models in actual clinical scenarios. Recent CE advancements will be discussed, focusing on the current evidence on CNN developments, and their real-life implementation potential and associated ethical challenges.

Smart Endoscopy Is Greener Endoscopy: Leveraging Artificial Intelligence and Blockchain Technologies to Drive Sustainability in Digestive Health Care

The surge in the implementation of artificial intelligence (AI) in recent years has permeated many aspects of our life, and health care is no exception. Whereas this technology can offer clear benefits, some of the problems associated with its use have also been recognised and brought into question, for example, its environmental impact. In a similar fashion, health care also has a significant environmental impact, and it requires a considerable source of greenhouse gases. Whereas efforts are being made to reduce the footprint of AI tools, here, we were specifically interested in how employing AI tools in gastroenterology departments, and in particular in conjunction with capsule endoscopy, can reduce the carbon footprint associated with digestive health care while offering improvements, particularly in terms of diagnostic accuracy. We address the different ways that leveraging AI applications can reduce the carbon footprint associated with all types of capsule endoscopy examinations. Moreover, we contemplate how the incorporation of other technologies, such as blockchain technology, into digestive health care can help ensure the sustainability of this clinical speciality and by extension, health care in general.

Feasibility of patency capsule and colon capsule endoscopy in patients with suspected gastrointestinal stenosis: a prospective study

Patency capsule (PC) can evaluate the patency of gastrointestinal (GI) tract. We hypothesized preceding patient selection using PC would improve the successful rate of colon capsule endoscopy (CCE). Therefore, a prospective single-arm study using PC followed by CCE was conducted with a control group of CCE alone. Patients with suspected or known GI stenosis scheduled for CCE were enrolled. CCE was performed only when the PC was excreted out of the body within 33 hours of ingestion. Primary endpoint was the rate of observation of the entire GI tract within the duration of examination. The secondary endpoints were complications and CCE findings. Twenty-three patients (17 men) were enrolled. The mean age was 50.5±19.8 years. Suspected stenotic sites were 8, 5, and 10 in the small, large, and small and large bowel, respectively. Sixteen, 12, and 10 patients had abdominal pain, active inflammatory bowel disease, and history of surgery for suspected stenosis, respectively. Patency of GI tract was confirmed in 96% (22/23) of the patients by administered PC. Of the 22 patients who underwent CCE, the entire GI tract was observed in 86% (19/22). No complications were observed. The median transit times in the small bowel and colon were 99 (21-682) and 160 (5-328) minutes, respectively. CCE findings revealed ulcers, erosions, and diverticula in 5, 9, and 4 patients, respectively. In conclusion, CCE with PC might be a safer and useful modality to observe the large colon for patients with suspected GI stenosis.

Wireless Capsule Endoscopy for Diagnosis and Management of Post-Operative Recurrence of Crohn's Disease

Despite aggressive medical therapy, many patients with Crohn's disease require surgical intervention over time. After surgical resection, disease recurrence is common. Ileo-colonoscopy and the Rutgeerts score are commonly used for diagnosis and monitoring of post-operative endoscopic recurrence. The latter is the precursor of clinical recurrence and therefore it impacts prognosis and patient management. However, due to the limited length of bowel assessed by ileo-colonoscopy, this procedure can miss out-of-reach, more proximal lesions in the small bowel. This limitation introduces an important uncertainty when evaluating post-operative relapse by ileo-colonoscopy. In addition, the Rutgeerts score 'per se' bears a number of ambiguities. Here we will discuss the pros and cons of ileo-colonoscopy and other imaging studies including wireless capsule endoscopy to diagnose and manage post-operative recurrence of Crohn's disease. A number of studies provide evidence that wireless capsule endoscopy is a potentially more accurate as well as less invasive and less costly alternative to conventional techniques including ileo-colonoscopy.

A new panenteric capsule endoscopy-based strategy in patients with melena and a negative upper gastrointestinal endoscopy: a prospective feasibility study

OBJECTIVE

patients presenting with melena and nondiagnostic esophagogastroduodenoscopy are usually investigated with colonoscopy and if negative, with small bowel capsule endoscopy. In this pilot study, we tested feasibility and performance of panenteric capsule endoscopy (PCE) in patients presenting with melena and negative esophagogastroduodenoscopy.

METHODS

Between January and December 2018, consecutive patients presenting with melena, clinically significant bleeding and negative esophagogastroduodenoscopy were invited to undergo PCE by swallowing PillCam Colon 2 (Medtronic Inc., Dublin, Ireland). PCE results, further diagnostic or therapeutic examinations, rebleeding rates at 30 days and 12 months were recorded.

RESULTS

Out of 128 patients with melena, 23 had negative esophagogastroduodenoscopy. Of them, 12 (8 female, mean age 76 years) underwent PCE, which allowed complete small bowel and colonic evaluation in 12 (100%) and 11 (91.7%) patients, respectively. The small bowel and colon cleansing were adequate in 100 and 83.3%, respectively. No PCE-related complications were observed. The PCE diagnostic yield was 83.3%: significant findings were located in the small bowel, colon or both in 5 (41.7%), 4 (33.3%) and 1 (8.3%) patients, respectively. Device-assisted enteroscopy was performed in 6 (50%) patients. Thirty days and 1 year rebleeding rates were 0 and 18.1%, respectively.

CONCLUSIONS

In this proof-of-concept study, PCE was feasible and safe in patients with melena and negative esophagogastroduodenoscopy, identifying the bleeding site in 83% of patients. PCE lead to small bowel therapeutic interventions in 50% of patients, thus avoiding unnecessary standard colonoscopy. Further large prospective randomized studies investigating this strategy are warranted.

CECDAIic - a new useful tool in pan-intestinal evaluation of Crohn's disease patients in the era of mucosal healing

Background: Pan-intestinal capsule endoscopy (Pan-CE) has been used to assess both the small and large bowel inflammation in Crohn's disease (CD) patients in a single examination. The capsule endoscopy Crohn's disease activity index (CECDAI) was initially developed to measure mucosal disease activity in the small bowel, although in 2018, it was extended to the colon for standardization of inflammatory activity (CECDAIic). The aim of this study was to apply the CECDAIic in a cohort of CD patients that underwent Pan-CE to evaluate the inter-observer agreement and the correlation between this score and inflammatory parameters.Methods: The videos were read and scored using the CECDAIic by three independent experienced operators, blinded to the results of the standard workup. Statistical analysis was performed with SPSS®, using Kendall's coefficient to evaluate the inter-observer agreement. Spearman correlation (rs) was used to access the correlation between the score and inflammatory biomarkers.Results: Included 22 patients, 59.1% males with mean age of 30.7 ± 11.1 years. The median CECDAIic score was 9.17 (0-37). The overall CECDAIic score Kendall coefficient was 0.94, demonstrating a statistically significant (p < .001) and excellent agreement between the three observers. In addition, we found a very good correlation between CECDAIic and calprotectin (rs = 0.82; p = .012) and a moderate correlation with C-reactive protein (CRP, rs = 0.50; p = .019).Conclusions: CECDAIic is a new score with excellent inter-observer agreement and strong correlation with calprotectin levels.

Utility of video capsule endoscopy for longitudinal monitoring of Crohn's disease activity in the small bowel: a prospective study

BACKGROUND AND AIMS

This prospective, multicenter study evaluated small-bowel capsule endoscopy (CE) for the longitudinal assessment of mucosal inflammation in subjects with Crohn's disease (CD).

METHODS

Subjects with known CD underwent clinical evaluation with ileocolonoscopy and CE at baseline and 6-month follow-up. Small-bowel patency was confirmed before CE at both time points. The Simple Endoscopic Score for CD (SES-CD) was used for ileocolonoscopy, and the Lewis score and the CE CD Endoscopic Index of Severity (CECDEIS) were used for CE. Clinical scoring indices included the Physician Global Assessment (PGA), CD Activity Index (CDAI), and Harvey-Bradshaw Index (HBI). Laboratory markers including C-reactive protein, fecal calprotectin, and erythrocyte sedimentation rate were collected at baseline and follow-up. Correlation between endoscopic scores and clinical parameters were measured using Spearman tests.

RESULTS

A total of 74 subjects were enrolled, of whom 53 (72%) completed endoscopic procedures at baseline and 6-month follow-up. The SES-CD ileocolonoscopy score correlated with the Lewis score (P < .001, ρ = .59) and CECDEIS capsule score (P = .002, ρ = .48). None of the 3 endoscopic scores correlated with PGA, CDAI, HBI, C-reactive protein, erythrocyte sedimentation rate, or fecal calprotectin. Approximately 85% of subjects had proximal small-bowel inflammation identified on CE. There were no CE-related adverse events.

CONCLUSIONS

There was high correlation between CE and ileocolonoscopy scores for the assessment of mucosal disease activity over time; however, there were no correlations between endoscopic scores and clinical parameters. The use of serial CE for the assessment of small-bowel CD is feasible and valid. (Clinical trial registration number: NCT01942720.).

Video capsule endoscopy in pediatric patients with Crohn's disease: a single-center experience of 180 procedures

BACKGROUND

Video capsule endoscopy (VCE) is a noninvasive method enabling excellent visualization of the small bowel (SB) mucosa. The aim of this study was to examine the impact and safety of VCE performed in children and adolescents with suspected or established Crohn's disease (CD).

METHODS

A total of 180 VCE examinations in 169 consecutive patients conducted in 2003-14 in a single center were retrospectively analyzed. The median age was 13 years (range 3-17 years) and indications for VCE were suspected (125 cases, 69%) and established (55 cases, 31%) CD. VCE was performed with a PillCam SB (Given Imaging, Yokneam, Israel) VCE system with 8-12 h of registration without bowel preparation.

RESULTS

A total of 154 of 180 (86%) patients swallowed the capsule and 26 (14%) had the capsule endoscopically placed in the duodenum. Patency capsule examination was performed in 71 cases prior to VCE to exclude SB obstruction. VCE detected findings consistent with SB CD in 71 (40%) examinations and 17 (9%) procedures showed minor changes not diagnostic for CD. A total of 92 (51%) examinations displayed normal SB mucosa. The capsule did not reach the colon within the recording time in 30 (17%) procedures and were defined as incomplete examinations. A change in diagnosis or therapy was recommended in 56 (31%) patients based on VCE results. Capsule retention occurred in one patient.

CONCLUSIONS

VCE is a safe method in children with suspected or established CD. VCE often leads to a definitive diagnosis and has a significant impact on the clinical management of pediatric patients with CD.