Capsule endoscopy: where are we after 6 years of clinical use?

Attention-Enhanced Multi-Task Deep Learning Model for Classification and Segmentation of Esophageal Lesions

Accurate detection and segmentation of esophageal lesions are crucial for diagnosing and treating gastrointestinal diseases. However, early detection of esophageal cancer remains challenging, contributing to a reduced five-year survival rate among patients. This paper introduces a novel multitask deep learning model for automatic diagnosis that integrates classification and segmentation tasks to assist endoscopists effectively. Our approach leverages the MobileNetV2 deep learning architecture enhanced with a mutual attention module, significantly improving the model's performance in determining the locations of esophageal lesions. Unlike traditional models, the proposed model is designed not to replace endoscopists but to empower them to correct false predictions when provided with additional Supporting Information. We evaluated the proposed model on three well-known data sets: Early Esophageal Cancer (EEC), CVC-ClinicDB, and KVASIR. The experimental results demonstrate promising performance, achieving high classification accuracies of 98.72% (F1-score: 98.08%) on CVC-ClinicDB, 98.95% (F1-score: 98.32%) on KVASIR, and 99.12% (F1-score: 99.00%) on our generated EEC data set. Compared to state-of-the-art models, our classification results show significant improvement. For the segmentation task, the model attained a Dice coefficient of 92.73% and an Intersection over Union (IoU) of 91.54%. These findings suggest that the proposed multitask deep learning model can effectively assist endoscopists in evaluating esophageal lesions, thereby alleviating their workload and enhancing diagnostic precision.

Capsule endoscopy: Do we still need it after 24 years of clinical use?

In this letter, we comment on a recent article published in the World Journal of Gastroenterology by Xiao et al, where the authors aimed to use a deep learning model to automatically detect gastrointestinal lesions during capsule endoscopy (CE). CE was first presented in 2000 and was approved by the Food and Drug Administration in 2001. The indications of CE overlap with those of regular diagnostic endoscopy. However, in clinical practice, CE is usually used to detect lesions in areas inaccessible to standard endoscopies or in cases of bleeding that might be missed during conventional endoscopy. Since the emergence of CE, many physiological and technical challenges have been faced and addressed. In this letter, we summarize the current challenges and briefly mention the proposed methods to overcome these challenges to answer a central question: Do we still need CE?

Could Capsule Endoscopy Be Useful in Detection of Suspected Small Bowel Bleeding and IBD-10 Years of Single Center Experience

A retrospective study in patients who underwent video capsule endoscopy (VCE) between 2006 and 2016 was conducted in the Clinic for gastroenterology and Hepatology, University Clinical Center of Serbia. A total of 245 patients underwent VCE. In 198 patients the indication was obscure gastrointestinal bleeding (OGIB), with 92 patients having overt and the other 106 occult bleeding. The remaining 47 patients underwent VCE due to suspected small bowel (SB) disease (i.e., Von Hippel-Lindau syndrome, familial adenomatous polyposis, Peutz Jeghers syndrome, Crohn's disease, prolonged diarrhea, abdominal pain, congenital lymphangiectasia, protein-losing enteropathy, tumors, refractory celiac disease, etc.). VCE identified a source of bleeding in 38.9% of patients (in the obscure overt group in 48.9% of patients, and in the obscure occult group in 30.2% of patients). The most common findings were angiodysplasias, tumors, Meckel's diverticulum and Crohn's disease. In the smaller group of patients with an indication other than OGIB, 38.3% of patients had positive VCE findings. The most common indication is OGIB, and the best candidates are patients with overt bleeding; patients with IBD should be evaluated in this setting.

Endoscope Capsules: The Present Situation and Future Outlooks

This paper presents new perspectives on photonic technologies for capsule endoscopy. It first presents a review of conventional endoscopy (upper endoscopy and colonoscopy), followed by capsule endoscopy (CE), as well as their techniques, advantages, and drawbacks. The technologies for CEs presented in this paper include integration with the existing endoscopic systems that are commercially available. Such technologies include narrow-band imaging (NBI), photodynamic therapy (PDT), confocal laser endomicroscopy (CLE), optical coherence tomography (OCT), and spectroscopy in order to improve the performance of the gastrointestinal (GI) tract examination. In the context of NBI, two optical filters were designed and fabricated for integration into endoscopic capsules, allowing for the visualization of light centered at the 415 nm and 540 nm wavelengths. These optical filters are based on the principle of Fabry-Perot and were made of thin films of titanium dioxide (TiO2) and silicon dioxide (SiO2). Moreover, strategies and solutions for the adaptation of ECs for PDT are also discussed.

CLELNet: A continual learning network for esophageal lesion analysis on endoscopic images

BACKGROUND AND OBJECTIVE

A deep learning-based intelligent diagnosis system can significantly reduce the burden of endoscopists in the daily analysis of esophageal lesions. Considering the need to add new tasks in the diagnosis system, a deep learning model that can train a series of tasks incrementally using endoscopic images is essential for identifying the types and regions of esophageal lesions.

METHOD

In this paper, we proposed a continual learning-based esophageal lesion network (CLELNet), in which a convolutional autoencoder was designed to extract representation features of endoscopic images among different esophageal lesions. The proposed CLELNet consists of shared layers and task-specific layers. Shared layers are used to extract common features among different lesions while task-specific layers can complete different tasks. The first two tasks trained by the CLELNet are the classification (task 1) and the segmentation (task 2). We collected a dataset of esophageal endoscopic images from Macau Kiang Wu Hospital for training and testing the CLELNet.

RESULTS

The experimental results showed that the classification accuracy of task 1 was 95.96%, and the Intersection Over Union and the Dice Similarity Coefficient of task 2 were 65.66% and 78.08%, respectively.

CONCLUSIONS

The proposed CLELNet can realize task-incremental learning without forgetting the previous tasks and thus become a useful computer-aided diagnosis system in esophageal lesions analysis.

Obscure Gastrointestinal Bleeding and Capsule Endoscopy: A Win-Win Situation or Not?

Obscure gastrointestinal bleeding (OGIB) refers to bleeding of uncertain origin that persists or recurs after negative workup using any of the radiologic evaluation modalities. It can be divided into two types based on whether clinically evident bleeding is present, namely, obscure overt and obscure occult bleeding. As the visualization of the bowel mucosa is challenging, capsule endoscopy (CE) is the ideal go-to procedure as the process is wireless, ingestible, small, disposable, and, most importantly, non-invasive. This review article has compiled various studies to shed light on the guidelines for using CE, its structure and procedure, patient preferences, diagnostic yield, cost-effectiveness, and the future. The goal of this review is to show the influence of CE on OGIB on the aspects mentioned earlier.

Multi-Task Model for Esophageal Lesion Analysis Using Endoscopic Images: Classification with Image Retrieval and Segmentation with Attention

The automatic analysis of endoscopic images to assist endoscopists in accurately identifying the types and locations of esophageal lesions remains a challenge. In this paper, we propose a novel multi-task deep learning model for automatic diagnosis, which does not simply replace the role of endoscopists in decision making, because endoscopists are expected to correct the false results predicted by the diagnosis system if more supporting information is provided. In order to help endoscopists improve the diagnosis accuracy in identifying the types of lesions, an image retrieval module is added in the classification task to provide an additional confidence level of the predicted types of esophageal lesions. In addition, a mutual attention module is added in the segmentation task to improve its performance in determining the locations of esophageal lesions. The proposed model is evaluated and compared with other deep learning models using a dataset of 1003 endoscopic images, including 290 esophageal cancer, 473 esophagitis, and 240 normal. The experimental results show the promising performance of our model with a high accuracy of 96.76% for the classification and a Dice coefficient of 82.47% for the segmentation. Consequently, the proposed multi-task deep learning model can be an effective tool to help endoscopists in judging esophageal lesions.

Capsule Retention in Crohn's Disease: A Meta-analysis

BACKGROUND

The main factor that limits wider utilization of capsule endoscopy (CE) in Crohn's disease (CD) is the potential risk of retention. The aim of this systematic review was to evaluate capsule retention rates in adult and pediatric CD and determine if retention risk is reduced in established CD (ECD) with patency capsule (PC) or magnetic resonance/computed tomography (MR/CT) enterography.

METHODS

Studies of CD patients undergoing CE that reported retention were identified. Pooled estimates for retention rates and relative risk in ECD to suspected CD (SCD) were calculated. All hypothesis tests were 2-sided; statistical significance was set at a P value of <0.05.

RESULTS

In the overall CD cohort, retention rates were 3.32% (95% confidence interval [CI], 2.62%-4.2%): 4.63% (95% CI, 3.42%-6.25%) and 2.35% (95% CI, 1.31%-4.19%) in ECD and SCD, respectively. Retention rates were 3.49% (95% CI, 2.73%-4.46%) and 1.64% (95% CI, 0.68%-3.89%) in adult and pediatric CD, respectively. Retention risk in adult ECD was 3.4 times higher than SCD, but there was no difference in retention risk in pediatric ECD compared with SCD. Retention rates in ECD were decreased after patency capsule (2.88%; 95% CI, 1.74%-4.74%) and MR/CT enterography (2.32%; 95% CI, 0.87%-6.03%).

CONCLUSIONS

In comparison with older literature, this meta-analysis demonstrates lower CE retention rates in SCD and ECD. Retention rates in pediatric CD were lower than in adult CD. Retention rates in adult ECD were higher than SCD, but there were no differences between pediatric ECD and SCD. Retention rates in ECD were lower after negative PC or MR/CT enterography.

The etiology of potential small-bowel bleeding depending on patient's age and gender

Background

Whether the etiology of potential small-bowel bleeding depends on the age and gender of the patient is not yet fully understood.

Methods

A total of 1953 patients who underwent video capsule endoscopy (VCE) to evaluate potential small-bowel bleeding and were registered in the Capsule Endoscopy Nationwide Database Registry from 2003 to 2014 were eligible for this study. VCE findings and the etiology of small-bowel bleeding were analyzed by age and gender.

Results

The diagnostic yield of VCE was 48.4% (95% CI: 46.2%-50.6%) and the diagnosis rate of etiology of potential small-bowel bleeding was 61.4% (95% CI: 59.2%-63.6%). The etiology of potential small-bowel bleeding depends on the age and gender of the patient. Crohn's disease and small-bowel diverticular diseases were more prevalent etiology of potential small-bowel bleeding in the young adults group (< 40 years) whereas angiodysplasia was revealed to be a most common etiology in elderly group (≥ 60 years), reaching statistical significance (p<0.00152) by Bonferroni correction.

Conclusions

The etiology of potential small-bowel bleeding depends on the age of the patient. Thus, an individualized lesion-specific diagnostic approach based on age might be needed for patients with potential small-bowel bleeding.

What defines quality in small bowel capsule endoscopy

Small bowel capsule endoscopy is considered a first-line diagnostic tool for the investigation of small bowel diseases. Gastroenterological and endoscopic societies have proposed and established measures known as quality indicators, quality measures or performance measures for the majority of endoscopic procedures, in order to ensure competence, healthcare quality and define areas requiring improvement. However, there is a paucity of publications describing small bowel capsule endoscopy quality indicators. Hereby, we attempt to identify and describe a number of pre-procedure, intra-procedure and post-procedure quality indicators, regarding process measures in small bowel capsule endoscopy, after a comprehensive review of the literature.

Bleeding Detection in Wireless Capsule Endoscopy Image Video Using Superpixel-Color Histogram and a Subspace KNN Classifier

Wireless Capsule Endoscopy (WCE) has become increasingly popular in clinical gastrointestinal (GI) disease diagnosis, benefiting from its painless and noninvasive examination. However, reviewing a large number of images is time-consuming for doctors, thus a computer-aided diagnosis (CAD) system is in high demand. In this paper, we present an automatic bleeding detection algorithm that consists of three stages. The first stage is the preprocessing, including key frame extraction and edge removal. In the second stage, we discriminate the bleeding frames using a novel superpixelcolor histogram (SPCH) feature based on the principle color spectrum, and then the decision is made by a subspace KNN classifier. Thirdly, we further segment the bleeding regions by extracting a 9-D color feature vector from the multiple color spaces at the superpixel level. Experimental results with an accuracy of 0.9922 illustrate that our proposed method outperforms the state-of-the-art methods in GI bleeding detection with low computational costs.

Two center experience of capsule endoscopy in Iran: Report on 101 cases

Background: Capsule endoscopy (CE) is a minimally invasive method for the visual examination of the small intestine, which may be for the evaluation and follow-up of patients with Crohn's disease. It can also be used to look at mucosal inflammation. Methods: This cross sectional study was used to determine the diagnostic efficacy of the CE system by performing a cross-sectional study of cases from 2011-2014. This study involved a total of 101 Iranian patients who were referred to the gastrointestinal and liver diseases outpatient clinics in Guilan (northern Iran) and in Isfahan (central Iran) for complaints of gastrointestinal problems. For all patients, definitive diagnosis had failed with the use of other diagnostic tools and CE was performed. Descriptive analysis was used. The patient population was represented by men and women equally, and the mean age of the patients was 42.3 ± 17.2 years (range: 16-89 years). Results: The final diagnoses were: non-specific enteritis (30.6%), Crohn's disease (20.7%), ulcers caused by aspirin or non-steroidal anti-inflammatory drugs (8.9%), mucosal erosion (5.9%) and angioectasia (4.9%); nearly 10% of the patients had normal findings. Analysis of the distribution of chief presenting complaints with patients stratified by the final diagnosis of Crohn's disease showed that the most frequently presented chief complaint was abdominal pain 42.9% and the least frequently presented chief complaint was diarrhea (4.8%). Conclusions: Small bowel evaluation by CE was well tolerated and capable of diagnosing Crohn's disease and gastrointestinal bleeding in patients who failed other diagnostic tests.

Two center experience of capsule endoscopy in Iran: Report on 101 cases

Background: Capsule endoscopy (CE) is a minimally invasive method for the visual examination of the small intestine, which may be for the evaluation and follow-up of patients with Crohn's disease. It can also be used to look at mucosal inflammation. Methods: This cross sectional study was used to determine the diagnostic efficacy of the CE system by performing a cross-sectional study of cases from 2011-2014. This study involved a total of 101 Iranian patients who were referred to the gastrointestinal and liver diseases outpatient clinics in Guilan (northern Iran) and in Isfahan (central Iran) for complaints of gastrointestinal problems. For all patients, definitive diagnosis had failed with the use of other diagnostic tools and CE was performed. Descriptive analysis was used. The patient population was represented by men and women equally, and the mean age of the patients was 42.3 ± 17.2 years (range: 16-89 years). Results: The final diagnoses were: non-specific enteritis (30.6%), Crohn's disease (20.7%), ulcers caused by aspirin or non-steroidal anti-inflammatory drugs (8.9%), mucosal erosion (5.9%) and angioectasia (4.9%); nearly 10% of the patients had normal findings. Analysis of the distribution of chief presenting complaints with patients stratified by the final diagnosis of Crohn's disease showed that the most frequently presented chief complaint was abdominal pain 42.9% and the least frequently presented chief complaint was diarrhea (4.8%). Conclusions: Small bowel evaluation by CE was well tolerated and capable of diagnosing Crohn's disease and gastrointestinal bleeding in patients who failed other diagnostic tests.

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.

ACG Clinical Guideline: Diagnosis and Management of Small Bowel Bleeding

Bleeding from the small intestine remains a relatively uncommon event, accounting for ~5-10% of all patients presenting with gastrointestinal (GI) bleeding. Given advances in small bowel imaging with video capsule endoscopy (VCE), deep enteroscopy, and radiographic imaging, the cause of bleeding in the small bowel can now be identified in most patients. The term small bowel bleeding is therefore proposed as a replacement for the previous classification of obscure GI bleeding (OGIB). We recommend that the term OGIB should be reserved for patients in whom a source of bleeding cannot be identified anywhere in the GI tract. A source of small bowel bleeding should be considered in patients with GI bleeding after performance of a normal upper and lower endoscopic examination. Second-look examinations using upper endoscopy, push enteroscopy, and/or colonoscopy can be performed if indicated before small bowel evaluation. VCE should be considered a first-line procedure for small bowel investigation. Any method of deep enteroscopy can be used when endoscopic evaluation and therapy are required. VCE should be performed before deep enteroscopy if there is no contraindication. Computed tomographic enterography should be performed in patients with suspected obstruction before VCE or after negative VCE examinations. When there is acute overt hemorrhage in the unstable patient, angiography should be performed emergently. In patients with occult hemorrhage or stable patients with active overt bleeding, multiphasic computed tomography should be performed after VCE or CTE to identify the source of bleeding and to guide further management. If a source of bleeding is identified in the small bowel that is associated with significant ongoing anemia and/or active bleeding, the patient should be managed with endoscopic therapy. Conservative management is recommended for patients without a source found after small bowel investigation, whereas repeat diagnostic investigations are recommended for patients with initial negative small bowel evaluations and ongoing overt or occult bleeding.

Automatic detection of small bowel tumors in endoscopic capsule images by ROI selection based on discarded lightness information

This paper addresses the problem of automatic detection of tumoral frames in endoscopic capsule videos by using features directly extracted from the color space. We show that tumor can be appropriately discriminated from normal tissue by using only color information histogram measures from the Lab color space and that light saturated regions are usually classified as tumoral regions when color based discriminative procedures are used. These regions are correctly classified if lightening is discarded becoming the tissue classifier based only on the color differences a and b of the Lab color space. While current state of the art systems for small bowel tumor detection usually rely on the processing of the whole frame regarding features extraction this paper proposes the use of fully automatic segmentation in order to select regions likely to contain tumoral tissue. Classification is performed by using Support Vector Machine (SVM) and Multilayer Perceptron (MLP) by using features from color channels a and b of the Lab color space. The proposed algorithm outperforms in more than 5% a series of other algorithms based on features obtained from the higher frequency components selected from Wavelets and Curvelets transforms while saving important computational resources. In a matter of fact the proposed algorithm is more than 25 times faster than algorithms requiring wavelet/curvelet and co-occurrence computations.

Bleeding Frame and Region Detection in the Wireless Capsule Endoscopy Video

Wireless capsule endoscopy (WCE) enables noninvasive and painless direct visual inspection of a patient's whole digestive tract, but at the price of long time reviewing large amount of images by clinicians. Thus, an automatic computer-aided technique to reduce the burden of physicians is highly demanded. In this paper, we propose a novel color feature extraction method to discriminate the bleeding frames from the normal ones, with further localization of the bleeding regions. Our proposal is based on a twofold system. First, we make full use of the color information of WCE images and utilize K-means clustering method on the pixel represented images to obtain the cluster centers, with which we characterize WCE images as words-based color histograms. Then, we judge the status of a WCE frame by applying the support vector machine (SVM) and K-nearest neighbor methods. Comprehensive experimental results reveal that the best classification performance is obtained with YCbCr color space, cluster number 80 and the SVM. The achieved classification performance reaches 95.75% in accuracy, 0.9771 for AUC, validating that the proposed scheme provides an exciting performance for bleeding classification. Second, we propose a two-stage saliency map extraction method to highlight bleeding regions, where the first-stage saliency map is created by means of different color channels mixer and the second-stage saliency map is obtained from the visual contrast. Followed by an appropriate fusion strategy and threshold, we localize the bleeding areas. Quantitative as well as qualitative results show that our methods could differentiate the bleeding areas from neighborhoods correctly.

High sensitivity of quick view capsule endoscopy for detection of small bowel Crohn's disease

BACKGROUND AND AIM

Capsule endoscopy (CE) has a high sensitivity for diagnosing small bowel Crohn's disease, but video analysis is time-consuming. The quick view (qv) function is an effective tool to reduce time consumption. The aim of this study was to determine the rate of missed small bowel ulcerations with qv-CE compared with standard view and the diagnostic accuracy of qv-CE in suspected Crohn's disease.

METHODS

This study consisted of two parts: (i) 12 small bowel segments with Crohn's disease of varying severity were selected for a detailed analysis of the number and type of lesions visualized with CE and qv-CE, and (ii) a blinded study of the diagnostic accuracy of qv-CE including 40 patients with suspected Crohn's disease. Ileocolonoscopy and CE served as gold standard.

RESULTS

Part 1: CE visualized 171 ulcerations compared with 102 detected with qv-CE (miss rate 40%, P = 0.02). Part 2: qv-CE identified 15 of 16 patients with small bowel Crohn's disease corresponding to a 94% sensitivity, and overall, 39 out of 40 patients were classified correct (diagnostic accuracy 98%). Qv-CE was false negative in one patient because of a leap of 3 min and 20 s in the terminal ileum. Reading times varied from 5 to 18 min (median 10).

CONCLUSION

Despite a significant number of missed lesions, qv-CE is a safe and time-reducing method for diagnosing small bowel Crohn's disease. To avoid false negative cases, we recommend viewing the terminal ileum in standard view.

CT enterography in obscure gastrointestinal bleeding: a systematic review and meta-analysis

The objective of this article is to provide a comprehensive and update overview of clinical application of CT enterography (CTE) in the evaluation of obscure gastrointestinal bleeding (OGIB). We performed a systematic review of relevant literatures in PubMed, EMBASE and The Cochrane Library and pooled the yield of CTE and the incremental yield (IY) of CTE over an alternate modality. A total of 18 studies (n = 660) reported the yield of CTE in evaluating OGIB and the pooled yield was 40% (95% confidence interval (CI): 33-49%). Seven studies (n = 279) compared the yield of CTE with capsule endoscopy (CE). The yield for CTE and CE for all findings was 34% and 53%, respectively (IY = -19%, 95% CI = -34% to -4%). When considering the types of identified lesions, the yield was significantly different for vascular and inflammatory lesions but not significantly different for neoplastic or other lesions. Two studies (n = 63) compared the yield of CTE with double-balloon enteroscopy (DBE). The yield for CTE and DBE was 38% and 78%, respectively (IY = -40%, 95% CI = -55% to -25%). Three studies (n = 49) compared the yield of CTE with digital subtraction angiography. The yield for CTE and digital subtraction angiography was 64% and 60%, respectively (IY = 4%, 95% CI = -40% to 47%). CTE is an excellent diagnostic tool in patients with OGIB. It may play a complementary role to CE and can be used as a triage tool prior to DBE in evaluating OGIB.

Bleeding detection in wireless capsule endoscopy images based on color invariants and spatial pyramids using support vector machines

Wireless capsule endoscopy (WCE) is a revolutionary imaging technique that enables detailed inspection of the interior of the whole gastrointestinal tract in a non-invasive way. However, viewing WCE videos is a very time-consuming, and labor intensive task for physicians. In this paper, we propose an automatic method for bleeding detection in WCE images. A novel series of descriptors which combine color and spatial information is designed in a way that local and global features are also incorporated together. And a kernel based classification method using histogram intersection or chi-square is deployed to verify the performance of the proposed descriptors. Experiments demonstrate that the proposed kernel based scheme is very effective in detecting bleeding patterns of WCE images.

Capsule endoscopy: comparison of two different reading modes

PURPOSE

Capsule endoscopy (CE) is a very useful tool for the evaluation of the small intestine, but it is time consuming. The aim of this study was to compare evaluation times and detection rates in two different reading modes (single view at a speed of 10 frames per second (fps) and four images simultaneously, i.e., quadview mode at a speed of 20 fps) to find the optimum setting mode for evaluation of CE videos.

METHODS

CE videos of 70 patients performed for different indications (obscure bleeding, n = 50; suspected Crohn's disease, n = 10; and suspected or complicated celiac disease, n = 10) were reviewed by investigators A and B in the two different reading modes.

RESULTS

The mean evaluation time using single view at 10 fps was 22 min (SD ± 9.1 min) and 11.9 min (SD ± 4.8 min) using quadview mode at 20 fps. The detection rates of angiodysplasias, erosions, small ulcers, and small polyps were only discreetly lower using the quadview mode at 20 fps. In Crohn's disease and celiac disease, the essential aspects of inflamed or atrophic mucosa segments were equally detected in both reading modes. In one case of complicated celiac disease with severe erosive jejunitis, a lymphoma-suspect lesion was overlooked in the quadview mode at 20 fps.

CONCLUSIONS

It is often possible to read CE videos in quadview mode at a higher speed with even so a high diagnostic yield in a shortened evaluation time.

Advance in diagnosis and treatment of small bowel tumors: a single-center report

BACKGROUND

The past decade has seen significant advances in the evaluation of the small bowel, long considered as the "black box" in gastroenterology. The development of several endoscopic techniques, including capsule endoscopy (CE) and double (DBE)- and single (SBE)-balloon enteroscopy, has improved the evaluation of this part of the gut and led to reach a more precise preoperative diagnosis of small-bowel tumors. These rare tumors were previously diagnosed only after laparotomy, although laparoscopic advanced surgery can be used for minimally invasive therapeutic approach in these patients. This study was designed to evaluate the diagnostic and therapeutic impact of endoscopic procedures on small-bowel tumors.

METHODS

During October 2010, 148 SBE procedures were performed; in 14 patients (7 males and 7 females, mean age 58.8 years; range 37-82 years) who suffered from obscure gastrointestinal bleeding, with previous negative upper and lower GI endoscopy, a diagnosis of small-bowel tumor was suspected according to CT scan (7 cases) and/or CE (11 patients). Then, an enteroscopy was performed.

RESULTS

Multiple biopsies were taken in 9 cases; endoscopic tattoos were performed in 11 cases. After endoscopic procedures, histological examination showed melanoma in one case, adenocarcinoma in seven, and adenoma in one case. In 11 of 14 patients, a laparoscopic partial resection of small bowel involved was possible due to endoscopic tattoos. In one patient, the involvement of colic segment precluded a laparoscopic resection. In two patients, the laparoscopic resection was not possible for technical problems. Histological findings on resected specimens were indicative for melanoma in one case, gastrointestinal stromal tumor (GIST) in four cases, gastrointestinal autonomic nerve tumor (GANT) in one case, adenoma in one, and adenocarcinoma in seven cases.

CONCLUSIONS

New development of different endoscopic approaches to the small bowel has led to reach an earlier diagnosis of small-bowel tumors and a preoperative diagnosis with consequent minimally invasive surgical approach.

Automatic small bowel tumor diagnosis by using multi-scale wavelet-based analysis in wireless capsule endoscopy images

Background

Wireless capsule endoscopy has been introduced as an innovative, non-invasive diagnostic technique for evaluation of the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the output of this technique is an 8 hours video, whose analysis by the expert physician is very time consuming. Thus, a computer assisted diagnosis tool to help the physicians to evaluate CE exams faster and more accurately is an important technical challenge and an excellent economical opportunity.

Method

The set of features proposed in this paper to code textural information is based on statistical modeling of second order textural measures extracted from co-occurrence matrices. To cope with both joint and marginal non-Gaussianity of second order textural measures, higher order moments are used. These statistical moments are taken from the two-dimensional color-scale feature space, where two different scales are considered. Second and higher order moments of textural measures are computed from the co-occurrence matrices computed from images synthesized by the inverse wavelet transform of the wavelet transform containing only the selected scales for the three color channels. The dimensionality of the data is reduced by using Principal Component Analysis.

Results

The proposed textural features are then used as the input of a classifier based on artificial neural networks. Classification performances of 93.1% specificity and 93.9% sensitivity are achieved on real data. These promising results open the path towards a deeper study regarding the applicability of this algorithm in computer aided diagnosis systems to assist physicians in their clinical practice.

Single-balloon push-and-pull enteroscopy system: does it work? A single-center, 3-year experience

BACKGROUND

The last decade has seen significant advances in the evaluation of the small bowel. Several endoscopic techniques have been developed in recent years: capsule endoscopy (CE), double-balloon enteroscopy (DBE), and, more recently, the single-balloon enteroscopy (SBE). The aim of this study was to evaluate diagnostic and therapeutic impact, safety, and feasibility of the SBE procedure after a 3-year experience.

METHODS

A total of 73 SBE procedures were performed from July 2006 to July 2009. The starting insertion route (oral or anal) of SBE was chosen according to the estimated location of the suspected lesions based on the clinical presentation and, in 48 patients, on the findings of CE. A total of 70 patients with obscure gastrointestinal bleeding (31), suspected malabsorption syndrome (12), polyposis syndromes (11), suspected Crohn's disease (9), and suspected gastrointestinal tumors (7) were recruited.

RESULTS

The SBE was not carried out in four patients because of technical problems. Multiple angiodysplasias were found and treated in 9 patients; Peutz-Jeghers syndrome, familial adenomatous polyposis (FAP), and multiple polypectomies were carried out in 8 patients; endoscopic tattoos were performed in 2 patients due to the large diameter of the polyps; and multiple biopsies was performed in only one patient. SBE diagnosed Crohn's disease in four patients, malabsorption syndromes in two, lymphangiectasia in two, eosinophilic enteritis in one, melanoma in one, and nonspecific inflammation in eight. A total of seven small-bowel tumors were diagnosed (all were tattooed). In 23/70 patients the exam was negative. No major complications occurred.

CONCLUSION

Single-balloon enteroscopy seems to be safe, useful, and highly effective in the diagnosis and therapy of several small-bowel diseases.

Small bowel tumors detection in capsule endoscopy by Gaussian modeling of color curvelet covariance coefficients

This paper is concerned with the classification of tumoral tissue in the small bowel by using capsule endoscopic images. The followed approach is based on texture classification. Texture descriptors are derived from selected scales of the Discrete Curvelet Transform (DCT). The goal is to take advantage of the high directional sensitivity of the DCT (16 directions) when compared with the Discrete Wavelet Transform (DWT) (3 directions). Second order statistics are then computed in the HSV color space and named Color Curvelet Covariance (3C) coefficients. Finally, these coefficients are modeled by a Gaussian Mixture Model (GMM). Sensitivity of 99% and specificity of 95.19% are obtained in the testing set.

10 years of capsule endoscopy: an update

Capsule endoscopy (CE) has evolved in a few short years to become a first-line, noninvasive diagnostic technique for the small bowel. CE is now being utilized worldwide to assess patients for obscure gastrointestinal bleeding, possible Crohn's disease, celiac disease and small bowel tumors. The device is now used in tandem with balloon enteroscopy to direct therapeutic interventions. Alterations and improvements in CE have also led to the evaluation of both the esophagus and colon. It can be anticipated that in the near future pan CE of the entire GI tract will be performed, as well as possible tissue acquisition, drug delivery and therapeutic interventions.

Capsule retention: a feared complication of wireless capsule endoscopy

Wireless capsule endoscopy is a simple, non-invasive technique for the visualization of the entire small bowel. It was introduced in clinical praxis in 2001 and has already become the method of choice for the investigation of small-bowel pathology. Capsule retention is a major complication, with an overall incidence of 1-2%, although reported rates vary widely from 0% to 21%, depending on the indication for the examination. This complication can occur at any level of the gastrointestinal tract and in most cases runs asymptomatically. However, symptomatic bowel obstruction requiring surgical or endoscopic removal of the impacted capsule can occur. Rarely, capsule retention can lead to intestinal perforation. Despite several years of experience with wireless capsule endoscopy, there is up to the present no safe means of predicting capsule retention. Radiological studies have a low diagnostic yield and tend to underestimate or overestimate small-bowel strictures. The role of the new generation patency capsule (Agile patency capsule) needs to be further documented. The experts agree that obtaining a careful history is perhaps the best single method to detect the possibility of retention.

The effect of metoclopramide in capsule enteroscopy

Clinical utility of prokinetics in capsule endoscopy (CE) is not clearly established. The objective of this prospective, randomized, single-blind, controlled trial was to determine if metoclopramide is useful in CE by increasing the rate of complete enteroscopy. Ninety-five patients referred for CE were randomized to no metoclopramide (group B, n = 48) or 10 mg metoclopramide (group A, n = 47). Complete enteroscopy was possible in 38 patients of group A (80.9%) and 37 of group B (77.1%) (P = 0.422) with two cases of gastric retention in group B (4.2%; P = 0.253). Median gastric transit time was 26 min (1-211) in group A and 28 min (4-200) in group B (P = 0.511). Mean small bowel transit time, calculated after excluding 20 patients with incomplete enteroscopy, was similar in both groups (221.2 +/- 89 min vs. 256 +/- 82.2 min; P = 0.083). There were also no differences in the total number of findings (group A 4.5 +/- 4.7; group B 4.7 +/- 3.7, P = 0.815). Administration of 10 mg metoclopramide orally 15 min before capsule ingestion did not significantly increase the rate of total enteroscopies and had no effect on transit times. It also did not modify CE diagnostic yield.

PillCam ESO versus esophagogastroduodenoscopy in esophageal variceal screening: A decision analysis

OBJECTIVES

PillCam ESO has been evaluated as a possible strategy to screen patients with cirrhosis for esophageal varices, but current guidelines recommend patients undergo screening with esophagogastroduodenoscopy (EGD), as it is currently the gold standard. Although recent data have suggested that PillCam ESO may be an acceptable alternative for screening, there is limited data on its cost-effectiveness compared with other screening modalities. This study was performed to compare the cost-effectiveness of PillCam ESO versus EGD for esophageal variceal screening.

METHODS

Markov models were constructed to compare 2 screening strategies: PillCam ESO versus EGD. In each arm, patients were followed for a time horizon of 15 years in 1-year transition intervals. All variables, transition probabilities, and costs were derived from the medical literature, and sensitivity analyses were performed on the different variables in the model.

RESULTS

Base-case analysis shows that PillCam ESO is associated with an average expected cost of $22,589 and an average expected effectiveness measure of 12.81 life-years. EGD is associated with an average expected cost of $23,083 and an average expected effectiveness measure of 12.67 life-years. PillCam ESO was found to dominate EGD as a screening strategy for patients with cirrhosis. Sensitivity analyses found several variables within the model to have influential effects on the results.

CONCLUSIONS

PillCam ESO is the dominant strategy for screening patients with cirrhosis for esophageal varices. However, based on a small difference in costs and effectiveness between each strategy, the results would suggest that PillCam ESO and EGD are essentially equivalent strategies.

Multi-phase CT enterography in obscure GI bleeding

Multiphase CT enterography is a modification of conventional abdominal CT designed to optimize detection of abnormalities responsible for obscure GI bleeding. This imaging test appears to be complimentary to wireless capsule endoscopy in the evaluation of this difficult group of patients. A description of exam technique, findings, and discussion of results will be presented in this article.

[Future prospects in digestive endoscopy: wireless capsule endoscopy]

Since the beginning of the millennium, the development of wireless capsule endoscopy has represented a major technological advance. The capsule is ingested by the patient and images are transmitted via several sensors positioned on the skin of the patient and downloaded in a computer system. The first applications were focused on the exploration of the small bowel which was previously considered as an obscure area for conventional endoscopy. Wireless capsule endoscopy of the small bowel is now an established technique with many acknowledged indications for the diagnosis of obscure bleeding, anemia of presumed digestive origin, Crohn's disease and small bowel tumors. Recently, thanks to technological progresses, novel capsules have been developed for specific segments of the gut namely the oesophagus and the colon. Recent data suggest that these new capsules could have potential applications for the diagnosis of oesophageal varices, Barrett's oesophagus and for the screening and/or surveillance of polyps of the colon. However, further studies are required before such strategies could be approved for clinical use or even replace conventional endoscopic modalities. In the long-term, progresses in signal processing as well as in the miniaturisation of sensors or markers may lead to a new generation of endoscopic robots. This technological breakthrough may ultimately result in new concepts and change current practice of digestive endoscopy.

Double-balloon enteroscopy and small bowel tumors: a South-European single-center experience

Small bowel tumors are rare, accounting for 1-2% of all gastrointestinal neoplasms. We sought to determine the diagnostic and therapeutic impact of double-balloon enteroscopy (DBE) in patients with small bowel tumors. Between January 2005 and March 2008, 78 patients underwent 96 DBE. All nine patients (seven males; mean age 68 +/- 11.3 years) with small bowel tumors were retrospectively reviewed. Clinical presentation was: mid-gastrointestinal bleeding or iron-deficient anemia (55.6%); abdominal pain (22.2%); nausea/vomiting and abdominal distension (22.2%). Five patients had abnormal findings in previous capsule endoscopy and four in previous radiologic examinations. Route of insertion was exclusively oral and abnormal lesions were detected in all patients (jejunum 8; ileum 1). Biopsies were taken in seven patients and provided definitive histological diagnosis in all except one. There were no complications of DBE. Surgical resection took place in eight patients. Final histologic diagnosis were: primary carcinoma (33.3%), gastrointestinal stromal tumor (GIST) (33.3%), malignant lymphoma (22.2%), and carcinoid tumor (11.1%). Mean follow-up time was 15.4 +/- 12.7 months (range 2-34 months). Six patients were submitted to chemotherapy. Two patients died. Small bowel tumors are common in patients submitted to DBE. Given its safety and diagnostic capabilities, DBE should be considered the gold-standard method in the study of these neoplasms.

Enteroscopy in the diagnosis and management of obscure gastrointestinal bleeding

Capsule endoscopy and balloon-assisted enteroscopy, have revolutionized our approach to the diagnosis and management of patients with obscure gastrointestinal bleeding, largely replacing intraoperative enteroscopy and conventional barium studies. Despite its limitations, capsule endoscopy may well be the most reasonable initial diagnostic strategy to evaluate most patients with obscure gastrointestinal bleeding, leaving balloon-assisted enteroscopy in reserve as a complementary tool. This article reviews the data on enteroscopy, with particular emphasis on the use of capsule endoscopy and balloon-assisted enteroscopy for the diagnosis and management of patients with obscure gastrointestinal bleeding.

Improvements in small bowel carcinoid diagnosis and staging: 18F-DOPA PET, capsule endoscopy and double balloon enteroscopy

Carcinoid tumours are rare, slow growing tumours, originating from cells of the neuroendocrine system. Staging of the disease is of paramount importance to determine the optimal treatment strategy but is notoriously difficult. A case of a 45-year-old male who presented with abdominal pain and flushes is presented. An abdominal computerised tomography-scan was performed which showed a solitary liver lesion, consisting of neuroendocrine tumour cells. Further staging with (18)F-DOPA PET, capsule endoscopy and double balloon enteroscopy revealed the localisation of the primary tumours in the small bowel, and the patient subsequently underwent surgery. The recent introduction of (18)F-DOPA PET, capsule endoscopy and double balloon enteroscopy in the diagnosis and staging of carcinoid tumours has made significant contributions to the management of this disease.

A blinded pilot comparison of capsule endoscopy and small bowel histology in unresponsive celiac disease

This study compares video capsule endoscopy (VCE) with histological specimens of proximal small bowel in patients with celiac disease who have failed to respond to a gluten-free diet. Patients with nonresponsive celiac disease underwent capsule endoscopy, and concordance between endoscopy and histology was then calculated using the kappa statistic. In 19 patients, endoscopy videos were reported as normal in ten (53%) case, as having mild changes in three (16%) cases, and as having moderate-severe changes in six (31%) cases. Two (11%) had acute ulcers. No small bowel tumors were seen. Endoscopy demonstrated concordance with histological changes in 14 of the 18 patients with histology available (78% concordance). The kappa statistic suggested a substantial degree of concordance between histology and endoscopic findings. Endoscopy with distal duodenal biopsies is superior to VCE in detecting proximal, nonresponsive celiac disease, but more distal lesions may be missed such that the strength of VCE lies in its ability to visualize the entire small bowel.

Detection of small bowel tumors in capsule endoscopy frames using texture analysis based on the discrete wavelet transform

Capsule endoscopy is an important tool to diagnose tumor lesions in the small bowel. The capsule endoscopic images possess vital information expressed by color and texture. This paper presents an approach based in the textural analysis of the different color channels, using the wavelet transform to select the bands with the most significant texture information. A new image is then synthesized from the selected wavelet bands, trough the inverse wavelet transform. The features of each image are based on second-order textural information, and they are used in a classification scheme using a multilayer perceptron neural network. The proposed methodology has been applied in real data taken from capsule endoscopic exams and reached 98.7% sensibility and 96.6% specificity. These results support the feasibility of the proposed algorithm.

Capsule endoscopy

Capsule endoscopy (CE) is a simple, safe, non-invasive, reliable technique, well accepted and tolerated by the patients, which allows complete exploration of the small intestine. The advent of CE in 2000 has dramatically changed the diagnosis and management of many diseases of the small intestine, such as obscure gastrointestinal bleeding, Crohn's disease, small bowel tumors, polyposis syndromes, etc. CE has become the gold standard for the diagnosis of most diseases of the small bowel. Lately this technique has also been used for esophageal and colonic diseases.

Urgent capsule endoscopy is useful in severe obscure-overt gastrointestinal bleeding

AIM

With capsule endoscopy (CE) it is possible to examine the entire small bowel. The present study assessed the diagnostic yield of CE in severe obscure-overt gastrointestinal bleeding (OOGIB).

METHODS

During a 3-year period, 15 capsule examinations (4.5% of all CE in a single institution) were carried out in 15 patients (11 men; mean age 69.9 +/- 20.1 years) with severe ongoing bleeding, defined as persistent melena and/or hematochezia, with hemodynamic instability and the need for significant red blood cell transfusion. CE was carried out after non-diagnostic standard upper and lower endoscopy. The mean time from admission until CE was 4.1 +/- 4.4 days (0-15 days).

RESULTS

CE revealed active bleeding in seven patients and signs of recent bleeding in four. Etiology of bleeding was correctly diagnosed in 11 patients (73.3%) (portal hypertension enteropathy, three patients; subepithelial ulcerated lesion, two patients; angiodysplasia, two patients; jejunal ulcer with visible vessel, one patient; multiple small bowel ulcers, one patient; jejunal tumor, one patient; jejunal mucosa irregularity with adherent clot, one patient). One patient (6.7%) had active bleeding but no visible lesion. As a consequence of the capsule findings, specific therapeutic measures were undertaken in 11 patients (73.3%) with five managed conservatively, four endoscopically and two surgically. Two patients experienced bleeding recurrence. One of them, with a probable small bowel tumor, refused any other interventions.

CONCLUSIONS

CE is useful in patients with severe OOGIB by providing positive findings in the majority of patients, with subsequent impact on therapeutic procedures.

Automatic detection of small bowel tumors in capsule endoscopy based on color curvelet covariance statistical texture descriptors

Traditional endoscopic methods do not allow the visualization of the entire Gastrointestinal (GI) tract. Wireless Capsule Endoscopy (CE) is a diagnostic procedure that overcomes this limitation of the traditional endoscopic methods. The CE video frames possess rich information about the condition of the stomach and intestine mucosa, encoded as color and texture patterns. It is known for a long time that human perception of texture is based in a multi-scale analysis of patterns, which can be modeled by multi-resolution approaches. Furthermore, modeling the covariance of textural descriptors has been successfully used in classification of colonoscopy videos. Therefore, in the present paper it is proposed a frame classification scheme based on statistical textural descriptors taken from the Discrete Curvelet Transform (DCT) domain, a recent multi-resolution mathematical tool. The DCT is based on an anisotropic notion of scale and high directional sensitivity in multiple directions, being therefore suited to characterization of complex patterns as texture. The covariance of texture descriptors taken at a given detail level, in different angles, is used as classification feature, in a scheme designated as Color Curvelet Covariance. The classification step is performed by a multilayer perceptron neural network. The proposed method has been applied in real data taken from several capsule endoscopic exams and reaches 97.2% of sensitivity and 97.4% specificity. These promising results support the feasibility of the proposed method.

Recent progress in clinical applications of capsule endoscopy

Capsule endoscopy has been widely used since it was approved by the Food & Drug Administration in the USA in 2001. It plays an important role in the investigation of obscure gastrointestinal bleeding, Crohn's disease and complications of coeliac disease, and surveillance of polyposis syndromes in adults. Despite a lag in its use in paediatrics, capsule endoscopy offers an accurate and effective means of investigating the small bowel in children. It has opened up new horizons and provided a noninvasive approach to identify occult lesions in the small bowel. This article reviews the recent advance in clinical applications of capsule endoscopy.

Impact of capsule endoscopy on outcome in mid-intestinal bleeding: a multicentre cohort study in 285 patients

BACKGROUND

Capsule endoscopy (CE) sensitively detects the bleeding source in the small bowel. However, the influence of CE on long-term outcome is not well established.

METHODS

In five tertiary hospitals, all CE investigations were retrospectively identified dating back to 3 years. Patients with intestinal bleeding and negative bidirectional endoscopy were included, and relapse of bleeding was recorded.

RESULTS

A bleeding source was detected in 219 of 285 patients (76.8%); CE provided the diagnosis in 175 of 219 (79.9%) and other, repeated investigations in 44 cases (20.1%). Follow-up (mean+/-SD=20.7+/-9.4 months) in 240 patients identified rebleeding in 65 (27.1%), and readmission to a hospital in 42 (17.5%). Hospital readmission was most frequent in patients with angiectasias (31.3%, relative risk (RR)=5.0; 95% confidence interval (CI)=2.4-10.4). Other risk factors included patients being older than 60 years of age (RR=3.8; 95% CI=1.5-9.5), and anticoagulant medication (RR=3.0; 95% CI=1.5-6.0). Therapeutic measures had a mean recurrence rate of 3.7% in surgical candidates (Meckel's diverticulum, tumor), 40% in endoscopically treated and 16% in medically treated patients. In case all the detected angiectasias had been cauterized, the relapse rate was low (11.8%), but in incompletely treated patients, it was high (85.7%). Bleeding relapse was never lethal.

CONCLUSION

CE guides therapeutic measures and predicts the risk of recurrent bleeding in small intestinal bleeding. High risk of rebleeding in angiectasias is significantly reduced by the cauterization of all demonstrable lesions.

Capsule endoscopy in neoplastic diseases

Until recently, diagnosis and management of small-bowel tumors were delayed by the difficulty of access to the small bowel and the poor diagnostic capabilities of the available diagnostic techniques. An array of new methods has recently been developed, increasing the possibility of detecting these tumors at an earlier stage. Capsule endoscopy (CE) appears to be an ideal tool to recognize the presence of neoplastic lesions along this organ, since it is non-invasive and enables the entire small bowel to be visualized. High-quality images of the small-bowel mucosa may be captured and small and flat lesions recognized, without exposure to radiation. Recent studies on a large population of patients undergoing CE have reported small-bowel tumor frequency only slightly above that reported in previous surgical series (range, 1.6%-2.4%) and have also confirmed that the main clinical indication to CE in patients with small-bowel tumors is obscure gastrointestinal (GI) bleeding. The majority of tumors identified by CE are malignant; many were unsuspected and not found by other methods. However, it remains difficult to identify pathology and tumor type based on the lesion’s endoscopic appearance. Despite its limitations, CE provides crucial information leading in most cases to changes in subsequent patient management. Whether the use of CE in combination with other new diagnostic (MRI or multidetector CT enterography) and therapeutic (Push-and-pull enteroscopy) techniques will lead to earlier diagnosis and treatment of these neoplasms, ultimately resulting in a survival advantage and in cost savings, remains to be determined through carefully-designed studies.

Correlation between predicted and actual consequences of capsule endoscopy on patient management

BACKGROUND

Capsule endoscopy (CE) is a relatively new diagnostic modality in the evaluation of patients with suspected small bowel pathology. It is unclear to what extent physicians are able to predict the clinical consequences of CE on patient management.

METHODS

In this prospective study, 180 consecutive CE examinations were analysed. Prior to CE, referring physicians were asked to indicate the consequences of CE according to potential different CE outcomes. The influence of CE on patient management was determined with at least 1 year follow-up. Management consequences were defined as major (surgical or endoscopic intervention, or medical therapy) or minor (nonspecific therapy, including iron supplementation, or no further diagnostic tests).

RESULTS

CE led to major management consequences in 32% of cases. Of patients with obscure gastrointestinal bleeding and normal CE findings, 91% were independent of blood transfusions and experienced no further bleeding episodes during a mean follow-up of 33 months. In 78% of 118 cases that were evaluated, the actual consequences of CE matched the consequences predicted by the referring physicians.

CONCLUSION

CE had a major impact on patient management in about one third of investigations. In the majority of cases, physicians adequately predicted the clinical consequences of CE.

How good is capsule endoscopy for detection of periampullary lesions? Results of a tertiary-referral center

BACKGROUND

Ampullary adenomas are increasingly being recognized, particularly in patients with familial adenomatous polyposis. A capsule endoscopy (CE) is routinely recommended for surveillance of small-intestinal polyposis. Performance characteristics of CE for the detection of periampullary lesions are unclear.

OBJECTIVE

To evaluate the ability of CE to detect the major duodenal papilla.

DESIGN AND PATIENTS

A total of 146 consecutive CE studies were reviewed by 2 CE gastroenterologists at 5 frames per second. Primary outcome was visualization of the major duodenal papilla. Discrepancies were reviewed by 5 CE gastroenterologists.

SETTING

A tertiary-referral center.

MAIN OUTCOME MEASUREMENTS

The ability of CE to detect the duodenal papilla.

RESULTS

Among 146 consecutive CE studies, 21 were excluded: capsule retention (3), patient age <18 years (6), duplicate study (8), and prior surgery disrupting duodenal anatomy (4). Of the remaining 125 studies, indications were the following: obscure GI bleeding (45.6%), iron deficiency anemia (19.2%), abdominal pain (17.6%), diarrhea (10.4%), and Crohn's disease (4.8%). In total, 13 major duodenal papillae were visualized. The median time of detection was 31 seconds after the first duodenal image. This translates to a CE sensitivity of 10.4% for detection of the major papilla.

LIMITATION

Papilla position was not verified by an EGD.

CONCLUSIONS

CE has limited sensitivity to visualize the major papilla and lesions in the periampullary small intestine. Nondiagnostic CE studies must not be relied upon as proof that small-bowel lesions do not exist. Consideration should be given for an enteroscopy or side-viewing duodenoscopy in cases where significant clinical concern exists for unrecognized periampullary lesions. The current recommendations about surveillance for small-bowel polyposis should be revised.