Lack of endoscopic visualization of intestinal villi with the "immersion technique" in overt atrophic celiac disease

Gastrointestinal disorders in children with autism: Could artificial intelligence help?

Autism is one of the pervasive neurodevelopmental disorders usually associated with many medical comorbidities. Gastrointestinal (GI) disorders are pervasive in children, with a 46%-84% prevalence rate. Children with Autism have an increased frequency of diarrhea, nausea and/or vomiting, gastroesophageal reflux and/or disease, abdominal pain, chronic flatulence due to various factors as food allergies, gastrointestinal dysmotility, irritable bowel syndrome (IBS), and inflammatory bowel diseases (IBD). These GI disorders have a significant negative impact on both the child and his/her family. Artificial intelligence (AI) could help diagnose and manage Autism by improving children's communication, social, and emotional skills for a long time. AI is an effective method to enhance early detection of GI disorders, including GI bleeding, gastroesophageal reflux disease, Coeliac disease, food allergies, IBS, IBD, and rectal polyps. AI can also help personalize the diet for children with Autism by microbiome modification. It can help to provide modified gluten without initiating an immune response. However, AI has many obstacles in treating digestive diseases, especially in children with Autism. We need to do more studies and adopt specific algorithms for children with Autism. In this article, we will highlight the role of AI in helping children with gastrointestinal disorders, with particular emphasis on children with Autism.

Current Evidence on Computer-Aided Diagnosis of Celiac Disease: Systematic Review

Celiac disease (CD) is a chronic autoimmune disease that occurs in genetically predisposed individuals in whom the ingestion of gluten leads to damage of the small bowel. It is estimated to affect 1 in 100 people worldwide, but is severely underdiagnosed. Currently available guidelines require CD-specific serology and atrophic histology in duodenal biopsy samples for the diagnosis of adult CD. In pediatric CD, but in recent years in adults also, nonbioptic diagnostic strategies have become increasingly popular. In this setting, in order to increase the diagnostic rate of this pathology, endoscopy itself has been thought of as a case finding strategy by use of digital image processing techniques. Research focused on computer aided decision support used as database video capsule, endoscopy and even biopsy duodenal images. Early automated methods for diagnosis of celiac disease used feature extraction methods like spatial domain features, transform domain features, scale-invariant features and spatio-temporal features. Recent artificial intelligence (AI) techniques using deep learning (DL) methods such as convolutional neural network (CNN), support vector machines (SVM) or Bayesian inference have emerged as a breakthrough computer technology which can be used for computer aided diagnosis of celiac disease. In the current review we summarize methods used in clinical studies for classification of CD from feature extraction methods to AI techniques.

Narrow-band imaging with magnification and the water immersion technique: a case-finding, cost-effective approach to diagnose villous atrophy

INTRODUCTION

Narrow-band imaging with magnification endoscopy (NBI-ME) allows real-time visual assessment of the mucosal surface and vasculature of the gastrointestinal tract. This study aimed to determine the performance of NBI-ME combined with the water immersion technique (NBI-ME-WIT) in detecting villous atrophy.

METHODS

All patients who underwent gastroscopy were included. The duodenum was further examined with NBI-ME-WIT only after examination with white light endoscopy did not reveal a cause of anaemia or dyspepsia. Targeted biopsies were taken of visualised areas. NBI-ME-WIT findings were compared with the final histopathological analysis. We calculated the sensitivity (Sn), specificity (Sp), positive predictive value (PPV) and negative predictive value (NPV) of NBI-ME-WIT in detecting villous atrophy and the hypothetical cost saved by using a biopsy-avoiding approach.

RESULTS

124 patients (83 female) with a mean age of 46 (range 18-82) years were included. The most common indication for gastroscopy was abdominal pain (39%), followed by anaemia (35%), chronic diarrhoea/altered bowel habits (19%) and dyspepsia (6%). NBI-ME-WIT was able to detect all nine patients with villous atrophy - eight patchy and one total villous atrophy. The Sn, Sp, PPV and NPV of NBI-ME-WIT in detecting villous atrophy were 100.0%, 99.1%, 90.0% and 100.0%, respectively. Taking into account the cost of biopsy forceps (AUD 17) and pathology (AUD 140), this biopsy-avoidance strategy could have saved AUD 18,055 in these patients.

CONCLUSION

NBI-ME-WIT is a specific and sensitive tool to recognise and accurately diagnose villous atrophy. Biopsies can be avoided in patients with normal-sized villi, which may decrease the overall cost of the procedure.

Statement on Best Practices in the Use of Pathology as a Diagnostic Tool for Celiac Disease: A Guide for Clinicians and Pathologists

Small intestinal biopsy interpretation has been the cornerstone for the diagnosis of celiac disease for over 50 years. Despite the existence of sensitive and specific serological tests, duodenal mucosal biopsies continue to be obtained in the vast majority of patients in whom a diagnosis of celiac disease is being considered. The accurate evaluation of these biopsies requires coordination and information sharing between the gastroenterologist, laboratory, and pathologist in order to optimize tissue sampling, preparation and interpretation. This document, a collaboration between the Rodger C. Haggitt Gastrointestinal Pathology Society and the North American Association for the Study of Celiac Disease, is intended to provide clinicians and pathologists with a summary of best practices in the use of endoscopy and biopsy for patients with suspected celiac disease. The authors present a comprehensive and critical appraisal of the literature with respect to the topics of endoscopic findings, best methods for the obtaining biopsies, completing the pathology form and pathologic assessment, including evaluating intraepithelial lymphocytes and villous architecture. A discussion of conditions with overlapping pathologic findings in duodenal mucosal biopsies is presented. In order to provide additional guidance for challenging situations, the authors include an appendix containing practical suggestions. This review may be utilized in interdisciplinary discussions to optimize care for patients with possible celiac disease.

Fisher encoding of convolutional neural network features for endoscopic image classification

We propose an approach for the automated diagnosis of celiac disease (CD) and colonic polyps (CP) based on applying Fisher encoding to the activations of convolutional layers. In our experiments, three different convolutional neural network (CNN) architectures (AlexNet, VGG-f, and VGG-16) are applied to three endoscopic image databases (one CD database and two CP databases). For each network architecture, we perform experiments using a version of the net that is pretrained on the ImageNet database, as well as a version of the net that is trained on a specific endoscopic image database. The Fisher representations of convolutional layer activations are classified using support vector machines. Additionally, experiments are performed by concatenating the Fisher representations of several layers to combine the information of these layers. We will show that our proposed CNN-Fisher approach clearly outperforms other CNN- and non-CNN-based approaches and that our approach requires no training on the target dataset, which results in substantial time savings compared with other CNN-based approaches.

A comparison study between Magniview and high definition white light endoscopy in detecting villous atrophy and coeliac disease: A single centre pilot study

BACKGROUND AND AIMS

Coeliac disease may be missed at gastroscopy. We aimed to assess the sensitivity of Pentax optical zoom technology endoscopes in detecting duodenal villous atrophy and the ease of image interpretation by non-coeliac specialists.

METHOD

All patients attending for a gastroscopy were assessed for endoscopic villous atrophy in part one and two of the duodenum with high definition white light endoscopy and magnification endoscopy. Endoscopic findings of the duodenum were compared to histology as the reference standard. A short training video of varying degrees of villous atrophy seen by magnification endoscopy was used to train individuals. They were then assessed for the ability to differentiate between normal duodenum and villous atrophy.

RESULTS

Two hundred and fifty patients were prospectively recruited (145 females, 58%; age range 16-84, median age 50.5). Ninety-six patients had villous atrophy on histology (38.4%) 154 were controls. Magnification endoscopy had a higher sensitivity in detecting villous atrophy compared to high definition white light endoscopy (86.4% versus 78.4%, p = .0005). 9/10 individuals undertaking magnification endoscopy training correctly identified all cases of villous atrophy.

CONCLUSION

Magnification endoscopy has superior diagnostic sensitivity in detecting villous atrophy compared to high definition white light endoscopy and the potential to be easily adopted by all endoscopists.

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.

Cost effectiveness of routine duodenal biopsies in iron deficiency anemia

AIM

To investigate the cost effectiveness of routine small bowel biopsies (SBBs) in patients with iron deficiency anemia (IDA) independent of their celiac disease (CD) serology test results.

METHODS

We used a state transition Markov model. Two strategies were compared: routine SBBs during esophagogastroduodenoscopy (EGD) in all patients with IDA regardless their celiac serology status (strategy A) vs SBBs only in IDA patients with positive serology (strategy B). The main outcomes were quality adjusted life years (QALY), average cost and the incremental cost effectiveness ratio (ICER). One way sensitivity analysis was performed on all variables and two way sensitivity analysis on selected variables were done. In order to validate the results, a Monte Carlo simulation of 100 sample trials with 10, and an acceptability curve were performed.

RESULTS

Strategy A of routine SBBs yielded 19.888 QALYs with a cost of $218.10 compared to 19.887 QALYs and $234.17 in strategy B. In terms of cost-effectiveness, strategy A was the dominant strategy, as long as the cost of SBBs stayed less than $67. In addition, the ICER of strategy A was preferable, providing the cost of biopsy stays under $77. Monte Carlo simulation demonstrated that strategy A yielded the same QALY but with lower costs than strategy B.

CONCLUSION

Our model suggests that EGD with routine SBBs is a cost-effective approach with improved QALYs in patients with IDA when the prevalence of CD is 5% or greater. SBBs should be a routine screening tool for CD among patients with IDA, regardless of their celiac antibody status.

Computer-aided texture analysis combined with experts' knowledge: Improving endoscopic celiac disease diagnosis

AIM: To further improve the endoscopic detection of intestinal mucosa alterations due to celiac disease (CD).

METHODS: We assessed a hybrid approach based on the integration of expert knowledge into the computer-based classification pipeline. A total of 2835 endoscopic images from the duodenum were recorded in 290 children using the modified immersion technique (MIT). These children underwent routine upper endoscopy for suspected CD or non-celiac upper abdominal symptoms between August 2008 and December 2014. Blinded to the clinical data and biopsy results, three medical experts visually classified each image as normal mucosa (Marsh-0) or villous atrophy (Marsh-3). The experts’ decisions were further integrated into state-of-the-art texture recognition systems. Using the biopsy results as the reference standard, the classification accuracies of this hybrid approach were compared to the experts’ diagnoses in 27 different settings.

RESULTS: Compared to the experts’ diagnoses, in 24 of 27 classification settings (consisting of three imaging modalities, three endoscopists and three classification approaches), the best overall classification accuracies were obtained with the new hybrid approach. In 17 of 24 classification settings, the improvements achieved with the hybrid approach were statistically significant (P < 0.05). Using the hybrid approach classification accuracies between 94% and 100% were obtained. Whereas the improvements are only moderate in the case of the most experienced expert, the results of the less experienced expert could be improved significantly in 17 out of 18 classification settings. Furthermore, the lowest classification accuracy, based on the combination of one database and one specific expert, could be improved from 80% to 95% (P < 0.001).

CONCLUSION: The overall classification performance of medical experts, especially less experienced experts, can be boosted significantly by integrating expert knowledge into computer-aided diagnosis systems.

Endoscopic evaluation of celiac disease severity and its correlation with histopathological aspects of the duodenal mucosa

BACKGROUND AND STUDY AIMS

Celiac disease (CD) is a chronic systemic autoimmune disorder affecting genetically predisposed individuals, triggered and maintained by the ingestion of gluten. Triggered and maintained by the ingestion of gluten, celiac disease is a chronic systemic autoimmune disorder affecting genetically predisposed individuals. Persistent related inflammation of the duodenal mucosa causes atrophy architecture detectable on esophagogastroduodenoscopy (EGD) and histopathology. We investigated the association between endoscopic features and histopathological findings (Marsh) for duodenal mucosa in celiac disease patients and propose an endoscopic classification of severity.

PATIENTS AND METHODS

Between January 2000 and March 2010, an electronic database containing 34,540 EDGs of patients aged > 14 years was searched for cases of CD. Out of 109 cases, 85 met the inclusion criteria: conventional EGD combined with chromoendoscopy, zoom and biopsy. EGD types 0, I and II corresponds to Marsh grades 0, 1 and 2, respectively, while EGD type III corresponds to Marsh grade 3 and 4.

RESULTS

Five patients (5.8 %) were EGD I but not Marsh grade 1; 25 patients (29.4 %) were EGD II, 4 of whom (16 %) were classified as Marsh grade 2; and 55 patients (64.7 %) were EGD III, 51 (92.7 %) of whom were classified as Marsh grades 3 and 4. The Spearman correlation coefficient (r = 0.33) revealed a significant association between the methods (P = 0.002).

CONCLUSIONS

Changes in the duodenal mucosa detected on EGD were significantly and positively associated with histopathologic findings. The use of chromoendoscopy in addition to conventional EGD enhances changes in the duodenal mucosa and permits diagnosis of CD, even in routine examinations. The proposed endoscopic classification is practical and easily reproducible and provides valuable information regarding disease extension.

Novel diagnostic techniques for celiac disease

The diagnosis of celiac disease has long been based on the demonstration of gluten-induced small-bowel mucosal damage. However, due to the constantly increasing disease prevalence and limitations in the histology-based criteria there is a pressure towards more serology-based diagnostics. The serological tools are being improved and new non-invasive methods are being developed, but the constantly refined endoscopic and histologic techniques may still prove helpful. Moreover, growing understanding of the disease pathogenesis has led researchers to suggest completely novel approaches to celiac disease diagnostics regardless of disease activity. In this review, we will elucidate the most recent development and possible future innovations in the diagnostic techniques for celiac disease.

High definition i-SCAN endoscopy with water immersion technique accurately reflects histological severity of celiac disease

BACKGROUND AND AIMS

Severe villous atrophy can be revealed with conventional white light endoscopy (WLE), however, milder grades or patchy villous atrophy are more difficult to detect. Novel endoscopic techniques such as high definition i-SCAN endoscopy with the water immersion technique (i-SCAN-HDWI) may provide the ability to visualize duodenal villi more accurately. We aimed to determine the performance of i-SCAN-HDWI in evaluating the severity of histological damage in the duodenum of patients with celiac disease.

PATIENTS AND METHODS

A retrospective cohort study was performed in a single tertiary academic endoscopic center. We studied 58 patients (46 women; median age 36.5 years, range 18 - 72 years) with positive anti-TTG IgA antibody. The villous pattern of the second part of the duodenum was assessed by WLE and i-SCAN-HDWI. The endoscopic grades in both techniques were correlated using Marsh histologic grades by Spearman correlation coefficient. The diagnostic accuracy of i-SCAN-HDWI for detection of patchy or complete atrophy of the villi was evaluated.

RESULTS

A significant correlation was demonstrated between endoscopic grade using i-SCAN-HDWI and Marsh histologic grade (r = 0.732; P < 0.00001). The correlation between WLE grade and Marsh histologic grade was inferior to i-SCAN-HDWI (r = 0.31; P = 0.01). The sensitivity of i-SCAN-HDWI was 96 % (95 %CI: 85 - 99 %) and the specificity was 63 % (95 %CI: 26 - 90 %) in diagnosing abnormal biopsy consistent with celiac disease.

CONCLUSION

i-SCAN-HDWI endoscopy can reflect the histological severity of celiac disease more accurately than conventional WLE alone. This novel endoscopic imaging can improve the diagnostic yield of duodenal biopsies in celiac patients, especially for those with a patchy distribution of villous damage.

Celiac Disease: Ten Things That Every Gastroenterologist Should Know

There are 10 things that all gastroenterologists should know about celiac disease (CD). (1) The immunoglobulin A tissue transglutaminase is the single best serologic test to use for the detection of CD. (2) CD can be recognized endoscopically, and water immersion enhances villi detection, although a normal endoscopic appearance does not preclude the diagnosis. (3) It is recommended that 4 biopsies be taken from the second part of the duodenum and 2 bulb biopsies be taken at the 9 o'clock and 12 o'clock positions to maximize the sensitivity for histologic confirmation of CD. (4) Consider serologic testing of first-degree relatives, patients with type 1 diabetes mellitus, Down's, Turner's, and Williams' syndromes, as well as those with premature osteoporosis, iron deficiency, abnormal liver biochemistries, and other manifestations of CD. (5) Patients already on a prolonged gluten-free diet (GFD) should be tested for the presence of HLA DQ2 or DQ8, thereby avoiding the need for further evaluation of CD in non-allelic carriers. (6) The basic treatment of CD is a strict, lifelong GFD, enabled by an expert dietitian. (7) Newly diagnosed adults with CD should be assessed for micronutrient deficiencies (iron, B12, folate, zinc, copper), fat soluble vitamin deficiencies (vitamin D), and bone densitometry. (8) All patients diagnosed with CD should have clinical follow-up to ensure response and adherence to a GFD. (9) In those with persistent or relapsing symptoms, the robustness of the original diagnosis should be reviewed, gluten exposure sought, and a systematic evaluation for alternative and associated diseases performed. (10) Evaluate those with refractory disease for malignant transformation.

Narrow band imaging combined with water immersion technique in the diagnosis of celiac disease

BACKGROUND

The "multiple-biopsy" approach both in duodenum and bulb is the best strategy to confirm the diagnosis of celiac disease; however, this increases the invasiveness of the procedure itself and is time-consuming.

AIM

To evaluate the diagnostic yield of a single biopsy guided by narrow-band imaging combined with water immersion technique in paediatric patients.

METHODS

Prospective assessment of the diagnostic accuracy of narrow-band imaging/water immersion technique-driven biopsy approach versus standard protocol in suspected celiac disease.

RESULTS

The experimental approach correctly diagnosed 35/40 children with celiac disease, with an overall diagnostic sensitivity of 87.5% (95% CI: 77.3-97.7). An altered pattern of narrow-band imaging/water immersion technique endoscopic visualization was significantly associated with villous atrophy at guided biopsy (Spearman Rho 0.637, p<0.001). Concordance of narrow-band imaging/water immersion technique endoscopic assessments was high between two operators (K: 0.884). The experimental protocol was highly timesaving compared to the standard protocol.

CONCLUSIONS

An altered narrow-band imaging/water immersion technique pattern coupled with high anti-transglutaminase antibodies could allow a single guided biopsy to diagnose celiac disease. When no altered mucosal pattern is visible even by narrow-band imaging/water immersion technique, multiple bulbar and duodenal biopsies should be obtained.

Narrow band imaging combined with water immersion technique in the diagnosis of celiac disease

BACKGROUND

The "multiple-biopsy" approach both in duodenum and bulb is the best strategy to confirm the diagnosis of celiac disease; however, this increases the invasiveness of the procedure itself and is time-consuming.

AIM

To evaluate the diagnostic yield of a single biopsy guided by narrow-band imaging combined with water immersion technique in paediatric patients.

METHODS

Prospective assessment of the diagnostic accuracy of narrow-band imaging/water immersion technique-driven biopsy approach versus standard protocol in suspected celiac disease.

RESULTS

The experimental approach correctly diagnosed 35/40 children with celiac disease, with an overall diagnostic sensitivity of 87.5% (95% CI: 77.3-97.7). An altered pattern of narrow-band imaging/water immersion technique endoscopic visualization was significantly associated with villous atrophy at guided biopsy (Spearman Rho 0.637, p<0.001). Concordance of narrow-band imaging/water immersion technique endoscopic assessments was high between two operators (K: 0.884). The experimental protocol was highly timesaving compared to the standard protocol.

CONCLUSIONS

An altered narrow-band imaging/water immersion technique pattern coupled with high anti-transglutaminase antibodies could allow a single guided biopsy to diagnose celiac disease. When no altered mucosal pattern is visible even by narrow-band imaging/water immersion technique, multiple bulbar and duodenal biopsies should be obtained.

Endoscopic tools for the diagnosis and evaluation of celiac disease

Celiac disease (CD) is an autoimmune disease of the small bowel induced by ingestion of wheat, rye and barley. Current guidelines indicate histological analysis on at least four duodenal biopsies as the only way to diagnose CD. These indications are based on the conception of the inability of standard endoscopy to make diagnosis of CD and/or to drive biopsy sampling. Over the last years, technology development of endoscopic devices has greatly ameliorated the accuracy of macroscopic evaluation of duodenal villous pattern, increasing the diagnostic power of endoscopy of CD. The aim of this paper is to review the new endoscopic tools and procedures proved to be useful in the diagnosis of CD, such as chromoendoscopy, Fujinon Intelligent Chromo Endoscopy, Narrow Band Imaging, Optical Coherence Tomography, Water-Immersion Technique, confocal laser endomicroscopy, high-resolution magnification endoscopy, capsule endoscopy and I-Scan technology.

Evaluation of different distortion correction methods and interpolation techniques for an automated classification of celiac disease

Due to the optics used in endoscopes, a typical degradation observed in endoscopic images are barrel-type distortions. In this work we investigate the impact of methods used to correct such distortions in images on the classification accuracy in the context of automated celiac disease classification. For this purpose we compare various different distortion correction methods and apply them to endoscopic images, which are subsequently classified. Since the interpolation used in such methods is also assumed to have an influence on the resulting classification accuracies, we also investigate different interpolation methods and their impact on the classification performance. In order to be able to make solid statements about the benefit of distortion correction we use various different feature extraction methods used to obtain features for the classification. Our experiments show that it is not possible to make a clear statement about the usefulness of distortion correction methods in the context of an automated diagnosis of celiac disease. This is mainly due to the fact that an eventual benefit of distortion correction highly depends on the feature extraction method used for the classification.

Enteroscopy: Advances in diagnostic imaging

Routine endoscopic imaging of the small bowel is performed with videoendoscopic white light technology. However, currently there are many new methods that improve our visual acuity when evaluating the small bowel mucosa. These methods are collectively called "advanced endoscopic imaging". These imaging methods include high-definition white light endoscopy, standard and dye-less or "virtual" chromoendoscopy, magnification endoscopy and confocal laser endomicroscopy. Regardless of the method used to image the small bowel the endosocopist needs to pay attention to detail and focus on three essential aspects: a) the shape of the lesion, b) the superficial mucosal detail (i.e. "pit pattern") and c) the submucosal vascular pattern. This review describes advances in the endoscopic imaging methods to study the small bowel.

The role of video capsule endoscopy in the diagnosis of celiac disease: a meta-analysis

BACKGROUND

Video capsule endoscopy (VCE) is an attractive and patient friendly tool that provides high quality images of the small bowel. The reported yield of VCE in diagnosing celiac disease (CD) has shown variable results.

OBJECTIVE

The aim of this study was to assess the accuracy of VCE by pooling data of existing trials.

DESIGN

Meta-analysis. The fixed-effects or random-effects model was used as appropriate, based on whether homogeneity or heterogeneity, respectively, was indicated by the Cochran Q-test.

PATIENTS

Studies that estimated the accuracy of VCE were identified. The two investigators independently conducted the search and data extraction. A total of 166 individuals were included in this meta-analysis.

METHODS

An extensive literature search was performed and studies that estimated the accuracy of VCE in CD were identified. The two investigators independently conducted the search and data extraction. Data from the eligible studies were collected and pooled; sensitivity, specificity, likelihood ratios, and diagnostic odds ratios were computed. In addition, the results of the individual studies were displayed in a receiver operating characteristic (ROC) space to illustrate the distribution of sensitivities and specificities. A weighted symmetric summary ROC curve was computed and the area under the curve (AUC) was calculated, with perfect tests having an AUC of 1 and poor tests having an AUC close to 0.5.

RESULTS

Out of 461 titles initially generated by the literature searches, six studies met the inclusion criteria and were eligible for meta-analysis. The overall pooled VCE sensitivity was 89% [95% confidence interval (82-94%)] and specificity was 95% [95% confidence interval (89-98%)]. The AUC under the weighted symmetric summary ROC was 0.9584.

CONCLUSION

The results of this meta-analysis mean that VCE, although it is not as accurate as pathology, could be a reasonable alternative method of diagnosing CD. Hopefully, this method will expand the portfolio of diagnostic methods available, especially in patients unwilling to undergo gastroscopy because of its perceived inconvenience and discomfort. However, larger, multicenter, and well-designed trials are needed to further establish the role of VCE in the diagnosis of CD.

Systematic assessment of performance prediction techniques in medical image classification: a case study on celiac disease

In the context of automated classification of medical images, many authors report a lack of available test data. Therefore techniques such as the leave-one-out cross validation or k-fold validation are used to assess how well methods will perform in practice. In case of methods based on feature subset selection, cross validation might provide bad estimations of how well the optimized technique generalizes on an independent data set. In this work, we assess how well cross validation techniques are suited to predict the outcome of a preferred setup of distinct test- and training data sets. This is accomplished by creating two distinct sets of images, used separately as training- and test-data. The experiments are conducted using a set of Local Binary Pattern based operators for feature extraction which are using histogram subset selection to improve the feature discrimination. Common problems such as the effects of over fitting data during cross validation as well as using biased image sets due to multiple images from a single patient are considered.

Automated Marsh-like classification of celiac disease in children using local texture operators

Automated classification of duodenal texture patches with histological ground truth in case of pediatric celiac disease is proposed. The classical focus of classification in this context is a two-class problem: mucosa affected by celiac disease and unaffected duodenal tissue. We extend this focus and apply classification according to a modified Marsh scheme into four classes. In addition to other techniques used previously for classification of endoscopic imagery, we apply local binary pattern (LBP) operators and propose two new operator types, one of which adapts to the different properties of wavelet transform subbands. The achieved results are promising in that operators based on LBP turn out to achieve better results compared to many other texture classification techniques as used in earlier work. Specifically, the proposed wavelet-based LBP scheme achieved the best overall accuracy of all feature extraction techniques considered in the two-class case and was among the best in the four-class scheme. Results also show that a classification into four classes is feasible in principle however when compared to the two-class case we note that there is still room for improvement due to various reasons discussed.

Quantitative assessment of endoscopic images for degree of villous atrophy in celiac disease

BACKGROUND

The degree of villous atrophy in celiac disease is difficult to assess at endoscopy. We sought to develop a quantitative technique for the evaluation of villous atrophy in endoscopic images.

METHOD

In ten celiac patients as identified by standard endoscopy with biopsy, and ten control patients, standard and videocapsule endoscopic images of the duodenum were digitized. Subimages 7.5 × 7.5 mm(2) in area from random locations within each image were assessed by measuring the length of mucosal fissures per unit area (L), and correlating L with the histologic grade of villous atrophy as determined by modified Marsh criteria.

RESULTS

Mean L values for standard endoscopic images were 37.8, 43.3, 64.1, and 83.5 mm for Marsh grades II, IIIa, IIIb, and IIIc, respectively. Mean L values for videocapsule images were 49.1, 50.0, 64.7, and 72.4 mm for Marsh grades II, IIIa, IIIb, and IIIc, respectively. Significant differences in the means existed between celiac images (Marsh scores II-IIIc) versus controls (p < 0.001) for both endoscopic and videocapsule images. There were no significant differences between measurements obtained from endoscopic versus videocapsule images.

CONCLUSIONS

Quantified image analysis correlates with the histologic grade of villous atrophy, is automated, and lacks observer bias, thus lending itself to standardization.

Quantitative assessment of endoscopic images for degree of villous atrophy in celiac disease

BACKGROUND

The degree of villous atrophy in celiac disease is difficult to assess at endoscopy. We sought to develop a quantitative technique for the evaluation of villous atrophy in endoscopic images.

METHOD

In ten celiac patients as identified by standard endoscopy with biopsy, and ten control patients, standard and videocapsule endoscopic images of the duodenum were digitized. Subimages 7.5 × 7.5 mm(2) in area from random locations within each image were assessed by measuring the length of mucosal fissures per unit area (L), and correlating L with the histologic grade of villous atrophy as determined by modified Marsh criteria.

RESULTS

Mean L values for standard endoscopic images were 37.8, 43.3, 64.1, and 83.5 mm for Marsh grades II, IIIa, IIIb, and IIIc, respectively. Mean L values for videocapsule images were 49.1, 50.0, 64.7, and 72.4 mm for Marsh grades II, IIIa, IIIb, and IIIc, respectively. Significant differences in the means existed between celiac images (Marsh scores II-IIIc) versus controls (p < 0.001) for both endoscopic and videocapsule images. There were no significant differences between measurements obtained from endoscopic versus videocapsule images.

CONCLUSIONS

Quantified image analysis correlates with the histologic grade of villous atrophy, is automated, and lacks observer bias, thus lending itself to standardization.

Endocytoscopy for the detection of microstructural features in adult patients with celiac sprue: a prospective, blinded endocytoscopy-conventional histology correlation study

BACKGROUND

Endocytoscopy (EC) is a novel technique that allows magnified live inspection of the intestinal mucosa.

OBJECTIVE

To evaluate EC for the detection of key pathological findings in patients with celiac sprue.

DESIGN

A total of 166 EC recordings were prospectively acquired. Matched videos, images, and biopsy specimens were obtained by duodenal argon beamer labeling of the respective sites.

SETTING

Academic tertiary referral center.

PATIENTS

Forty patients (mean age 51.5 years, 70% women) with established (n = 32) or suspected (n = 8) celiac disease (CD).

INTERVENTIONS

A validated scoring system (Marsh classification) was used to assess disease activity. EC criteria were independently evaluated by 2 gastroenterologists and 1 pathologist.

MAIN OUTCOME MEASUREMENTS

The primary endpoint was to examine EC correlation with conventional CD histology.

RESULTS

Of 166 duodenal biopsy sites, 23% were classified as Marsh III (moderate to severe), 10% as Marsh I (mild), and 67% as Marsh 0 (normal). Using the 450x magnification, we found that identification of crypts was diagnostic for celiac pathology. Four criteria were significant predictors of Marsh III pathology when adjusted by multivariate analysis: low number of villi per visual field (<3; odds ratio [OR] 9.1; 95% CI, 1.3-62.0), confluence of villi (OR 37.1; 95% CI, 1.3-1021.2), irregular epithelial lining (OR 10.9; 95% CI, 2.5-46.7), and inability to delineate loop capillaries (OR 14.9; 95% CI, 3.3-67.0). None was a good predictor of Marsh I pathology.

LIMITATIONS

Single-center experience. No prospective validation of the criteria in an independent patient population.

CONCLUSIONS

EC at 450x magnification accurately identifies mucosal histopathology of advanced CD, but not early morphological changes.

The water immersion technique is easy to learn for routine use during EGD for duodenal villous evaluation: a single-center 2-year experience

GOALS

We investigated the learning parameters of the immersion technique for the assessment of marked villous atrophy (MVA), during routine esophagogastroduodenoscopy (EGD).

BACKGROUND

The immersion technique offers a proven possibility of enhancing the sensitivity of endoscopy in detecting duodenal villous atrophy patterns.

STUDY

Nine endoscopists with at least 2 years of experience, who had previously been trained to perform the immersion technique, searched for duodenal villi during routine EGD. In a 2-year study, duodenal villi were evaluated underwater duodenoscopy in 432 patients from whom duodenal biopsies had been, for various reasons, obtained. The endoscopic findings were compared with the histology. The learning parameters of the water immersion technique and the accuracy in detecting subjects with MVA were observed.

RESULTS

A total of 28 (6.5%) patients with MVA were identified during endoscopy by the trained endoscopists. All these patients were diagnosed as being celiac patients. The sensitivity, specificity, and accuracy (positive and negative predictive values) of the immersion technique in detecting MVA patterns, irrespective of the endoscopist who performed the examination, were always 100%.

CONCLUSIONS

The underwater evaluation of the duodenum can be efficiently and regularly performed during routine EGD by endoscopists with 2 years of experience, after a specific, brief training period. This procedure is simple, feasible, and can accurately detect MVA patterns.

Celiac disease in the 21st century: issues of under- and over-diagnosis

Until the 1960s celiac disease (CD) or sprue was considered a pediatric disease that was rarely diagnosed in adulthood. Thanks to greater awareness of the disease and the availability of improved diagnostic tools (above all, sophisticated endoscopic techniques and the development of reliable serological markers), the prevalence of CD in Western countries has been increasing steadily, and it is now recognized as a common disorder, even in adults. However, many cases of this disease still go undiagnosed, especially among the elderly and in patients with atypical clinical presentations (which are by no means uncommon). On the other hand, the frequency of unfounded diagnoses of CD is also on the rise. This reflects a tendency toward exclusively symptomatic diagnosis as well as the growing use of invalidated tests for CD (e.g., the cytotoxic test, the sublingual or subcutaneous provocation/neutralization test, etc.). As a result, public healthcare spending is being increased in several countries (Italy included) by the growing number of prescriptions for gluten-free diets. This editorial discusses the problems of under- and over-diagnosis of CD and provides an algorithm for management of suspected cases designed to minimize both problems with particular importance to morphologic aspects of small bowel (also in electron microscopy), in basal conditions or in gluten-free diets.

Emerging technologies in upper gastrointestinal endoscopy and celiac disease

Despite advances in our knowledge of celiac disease, the most current and authoritative recommendations conclude that diagnosis requires at least four biopsy specimens to be taken from the duodenal area. These recommendations are based on the perception that classic endoscopic markers are not adequate to target biopsy sampling to sites of villous damage in the duodenum. In the past few years, newly developed procedures and technologies have improved endoscopic recognition of the duodenum. These advances make possible the real-time recognition of the duodenal villous pattern during an upper endoscopy procedure, and thereby have the potential to optimize diagnostic accuracy. It is, therefore, reasonable to hypothesize that upper endoscopy might have a more incisive role in the diagnosis of celiac disease than merely providing a means of obtaining biopsy specimens for histological analysis. This Review highlights the new technologies in the field of upper endoscopy that could be helpful for the diagnosis of celiac disease, including the water-immersion technique, chromoendoscopy, high-resolution magnification endoscopy, optimal band imaging, optical coherence tomography and confocal endomicroscopy.

Capsule endoscopy in celiac disease

Video capsule endoscopy is an attractive and patient-friendly tool that provides high quality images of the small bowel. Obscure gastrointestinal bleeding is the primary and most evaluated indication to capsule endoscopy; however, indications are expanding and a small number of preliminary reports have been presented concerning the role of video capsule endoscopy in the diagnosis of celiac disease. The purpose of this review is to update the current knowledge and to hypothesize on future perspectives of the use of video capsule endoscopy in patients with celiac disease.

Cystic lymphangioma of the mesentery and hyposplenism in celiac disease

Celiac disease is characterized by intestinal inflammation and mucosal atrophy that improves on a gluten-free diet. Delayed diagnosis can result in diet-refractory disease known as refractory sprue, which is linked to other disorders (intestinal lymphoma, ulcerative jejunoileitis, mesenteric lymph-node cavitation, collagenous sprue, malignancy) and carries a poor prognosis. Here we report the case of a young woman diagnosed with Marsh stage 3C celiac disease with intestinal occlusion due to intra-abdominal cystic lymphangioma mimicking mesenteric lymph-node cavitation, and hyposplenism. Despite a number of prognostically negative features, the disease has been managed successfully for the past 2 years with a gluten-free diet. The pathogenesis, prognosis and therapeutic implications are discussed.

Role of the "immersion technique" in diagnosing celiac disease with villous atrophy limited to the duodenal bulb

GOALS

To investigate if the so-called immersion technique during upper endoscopy may be helpful to predict patterns of villous atrophy restricted to the duodenal bulb.

BACKGROUND

Patients with celiac disease may have a patchy distribution of duodenal villous atrophy. In some cases, mucosa of duodenal bulb may be the only intestinal area involved. The immersion technique is a novel procedure that allows visualizing duodenal villi directly during endoscopy.

STUDY

With this prospective study, the immersion duodenoscopy was performed in 67 celiac subjects to investigate their duodenal villous pattern. Villi were evaluated both in the first and in the second duodenal segment and judged as present or absent (flat mucosa). Results were compared with histology as reference.

RESULTS

Among celiac subjects, 49 were newly diagnosed and 18 previously diagnosed celiac patients. Four (8%) newly diagnosed and 7 (39%) previously diagnosed celiac subjects had an extension of the villous atrophy (flat mucosa) limited to the duodenal bulb. The sensitivity, specificity, and positive and negative predictive values of the immersion-based duodenal investigation in predicting areas of duodenal villous atrophy was always 100%.

CONCLUSIONS

Immersion technique may be useful for directing duodenal biopsies in celiac subjects with a patchy distribution of villous atrophy. This procedure can avoid blinded sampling of the duodenal mucosa and enhance the diagnostic yield.

The value of double-balloon enteroscopy in patients with refractory celiac disease

OBJECTIVE

Patients with refractory celiac disease can develop enteropathy-associated T-cell lymphoma (EATL) or ulcerative jejunitis. Double-balloon enteroscopy allows examination of the small bowel. We prospectively assessed the value of this technique in patients with refractory celiac disease in a tertiary referral center.

METHODS

Small bowel enteroscopy was performed in a total of 21 consecutive patients for lesions like ulcerations (high risk). Biopsy specimens were taken from such lesions and from examined small bowel at three different levels of scope insertion depth. Tissue specimens were evaluated for the modified Marsh classification and for the presence of EATL.

RESULTS

Twenty-four procedures were successfully performed without complications. EATL was found in five patients (24%, 95% CI 10-45%) as circumferential, discrete, or confluent ulcerations. In three of them, Marsh III was found while in the other two patients with EATL Marsh I was found. Another two patients (9%, 95% CI 2-28%) had ulcerative jejunitis in the absence of EATL and histology was compatible with Marsh III. In the remaining 14 patients (54%, 95% CI 35-73%), no high-risk lesions were found. Double-balloon enteroscopy could exclude the presence of EATL in four patients that was suggested by abdominal computerized tomography.

CONCLUSIONS

Complications of refractory celiac disease like ulcerative jejunitis or EATL could efficiently be detected or excluded by double-balloon enteroscopy. This technique should be reserved for patients with refractory celiac disease or patients with a past history of EATL.

Diagnostic and therapeutic impact of double-balloon enteroscopy (DBE) in a series of 100 patients with suspected small bowel diseases

BACKGROUND

Double-balloon enteroscopy is a newly developed endoscopic method allowing non-surgical full-length exploration of the small bowel, biopsies sample and endoscopic treatment of previously inaccessible lesions.

AIM

To prospectively assess the diagnostic and therapeutical impact of double-balloon enteroscopy in patients with suspected or documented small bowel disease.

PATIENTS AND METHODS

One hundred consecutive patients referring to our centre for suspected small bowel disease underwent double-balloon enteroscopy. Starting insertion route (anal or oral) of double-balloon enteroscopy was chosen according to the estimated location of the suspected lesions basing on the clinical presentation and on the findings, when available, of previous endoscopic or radiological investigations. Major indications for the procedures were acute recurrent or chronic mid-gastrointestinal bleeding (n=71), suspected gastrointestinal tumours (n=10), suspected Crohn's disease (n=6), chronic abdominal pain and/or chronic diarrhoea (n=8), refractory celiac disease (n=5).

RESULTS

One hundred and eighteen double-balloon enteroscopy procedures were carried out. Oral and anal route double-balloon enteroscopies were performed in 54 and 28 patients, respectively, while 18 patients underwent a combination of both approaches. Overall diagnostic yield of double-balloon enteroscopy resulted 69%. Most common pathological findings included angiodysplasias (n=39), ulcerations and erosions of various aetiologies (n=21), tumours (n=7) and ileal stenosis in patients with Crohn's disease suspicion (n=2). In the 65% of the patients examined, double-balloon enteroscopy findings influenced the subsequent clinical management (endoscopic, medical or surgical treatment). No major complications related to the procedure occurred.

CONCLUSIONS

Our prospective analysis shows that double-balloon enteroscopy is a useful, safe and well-tolerated new method with a high diagnostic and therapeutic impact for the management of suspected or documented small bowel diseases.

Capsule endoscopy: an alternative to duodenal biopsy for the recognition of villous atrophy in coeliac disease?

BACKGROUND

Villous atrophy present on a duodenal biopsy remains the 'gold standard' diagnostic test for coeliac disease. However, endoscopic biopsy may cause morbidity and discomfort. Our aim was to evaluate wireless capsule endoscopy as an alternative test for the recognition of villous atrophy.

METHOD

Twenty-one patients with a positive endomysial antibody referred for endoscopy and duodenal biopsy were also offered a wireless capsule endoscopy to evaluate their small bowel. Concurrently, other patients (n=23) referred for a wireless capsule endoscopy acted as controls. Wireless capsule endoscopy reports were assessed for the presence of villous atrophy by one blinded investigator.

RESULTS

Twenty endomysial antibody positive patients subsequently had villous atrophy on duodenal biopsy. The controls all had normal duodenal biopsies (with a negative endomysial antibody) and no evidence of villous atrophy noted on their wireless capsule endoscopy. Of the 20 endomysial antibody positive patients with confirmed villous atrophy on biopsy, 17 had villous atrophy also detected by wireless capsule endoscopy. The sensitivity, specificity, positive and negative predictive values for wireless capsule endoscopy recognising villous atrophy were 85%, 100%, 100%, 88.9%, respectively.

CONCLUSION

Wireless capsule endoscopy may be an option to recognise villous atrophy in patients with a positive endomysial antibody who are unwilling, or unable to have a gastroscopy. However, a negative test should be followed by a biopsy if coeliac disease is to be excluded.

High accuracy and cost-effectiveness of a biopsy-avoiding endoscopic approach in diagnosing coeliac disease

BACKGROUND

The 'immersion' technique during upper endoscopy allows the visualization of duodenal villi and the detection of total villous atrophy.

AIM

To evaluate the accuracy of the immersion technique in detecting total villous atrophy in suspected coeliac patients. The accuracy in diagnosing coeliac disease and the potential cost-sparing of a biopsy-avoiding approach, based on selection of individuals with coeliac disease-related antibodies and on endoscopic detection of absence of villi, were also analysed.

METHODS

The immersion technique was performed in 79 patients with positive antibodies and in 105 controls. Duodenal villi were evaluated as present or absent. As reference, results were compared with histology. Diagnostic approaches, including endoscopy with or without biopsy, were designed to investigate patients with coeliac disease-related antibodies and total villous atrophy. A cost-minimization analysis was performed.

RESULTS

All patients with positive antibodies had coeliac disease. The sensitivity, specificity, positive and negative predictive values of endoscopy to detect total villous atrophy was always 100%. The sensitivity, specificity, positive and negative predictive values of biopsy-avoiding or biopsy-including strategies in diagnosing coeliac disease when villi were absent was always 100%. The biopsy-avoiding strategy was cost-sparing.

CONCLUSIONS

Upper endoscopy is highly accurate in detecting total villous atrophy coeliac patients. A biopsy-avoiding approach is both accurate and cost-sparing to diagnose coeliac disease in subjects with marked duodenal villous atrophy.

The European experience with double-balloon enteroscopy: indications, methodology, safety, and clinical impact

BACKGROUND

Double-balloon enteroscopy (DBE) is a new technique that allows high-resolution visualization, biopsies, and therapeutic interventions in all segments of the GI tract. The objective of the study was to evaluate the indications, the safety, and the clinical impact of DBE.

METHODS

This is a retrospective analysis conducted at 4 European medical centers. A total of 62 patients with suspected or documented small-bowel diseases were investigated by DBE. A total of 89 procedures were performed (26 and 9 patients from the oral or the anal route, respectively; 27 patients from both). The main outcome measurements were complications, depth and time of insertion, diagnostics, and therapeutics rates.

RESULTS

No complications occurred. Mean time was 70 +/- 30 minutes and 90 +/- 35 minutes from the oral and the anal route, respectively. Length of insertion was 254 +/- 174 cm beyond the pylorus, 180 +/- 150 cm beyond the ileocecal valve, whereas the entire small bowel was completely explored in 10 patients. DBE was diagnostic in 80% of the patients: in 29 of 33 of patients with GI bleeding, in one of 5 patients with iron deficiency anemia and positive fecal occult blood testing, in 3 of 5 patients with chronic diarrhea, in two of 3 patients with abdominal pain, in two of 3 patients with GI cancer (follow-up), in all patients with suspected or refractory celiac disease, and in two of 3 patients with Crohn's disease. Treatment was performed in 41.9% of patients (22 polyps and 29 angioectesias).

CONCLUSIONS

DBE is a safe and feasible diagnostic and therapeutic tool for suspected or documented small-bowel diseases. At present, the best candidates for the procedure appear to be those with obscure GI bleeding.

Acute cryptogenic liver failure in an untreated coeliac patient: a case report

Coeliac disease is an autoimmune enteropathy triggered by the ingestion of gluten in susceptible individuals. The clinical presentation of coeliac disease is variable and several extra-intestinal manifestations, as well as an association with autoimmune diseases, have been described. In particular, there are many links between liver disease and coeliac disease. Here we report the case of a young Caucasian woman with acute liver failure, selected as a possible candidate for liver transplantation. Investigation of the patient led to the diagnosis of coeliac disease. A gluten-free diet led to the reversal of the severe liver failure, without the necessity for any surgical or medical treatment.

Endoscopy in celiac disease

PURPOSE OF REVIEW

The primary objective of this review is to highlight the evidence for the role of endoscopy in celiac disease.

RECENT FINDINGS

Evidence is presented that the endoscopic markers of celiac disease are specific although not sensitive for the disease. Villous atrophy, the hallmark of celiac disease, is patchy in the duodenum, and various techniques may identify areas of villous atrophy. These methods include magnification endoscopy and chromoendoscopy. The most recent innovation, video capsule endoscopy, may be of value in the diagnosis of celiac disease and in the assessment of patients with complicated celiac disease.

SUMMARY

Endoscopy and duodenal biopsies are the mainstay for diagnosing celiac disease. Although characteristic endoscopic features may be useful, their absence does not exclude celiac disease. Random biopsy, even of normal-appearing mucosa is necessary for the diagnosis of celiac disease.

Direct visualization of intestinal villi by high-resolution magnifying upper endoscopy: a validation study

BACKGROUND

New generation videoendoscopes potentially may visualize duodenal villi. This study compared endoscopic findings with this type of instrument to the histopathologic evaluation of duodenal villi.

METHODS

A total of 191 patients underwent upper endoscopy for the purpose of obtaining duodenal biopsy specimens. The findings were assessed independently by 3 experienced observers by using a commercially available, high-resolution, high-magnifying (x2) videoendoscope. The duodenal villous profile was determined by endoscopic magnification and by endoscopic magnification after filling the duodenum with water. With both endoscopic magnification and endoscopic magnification after filling the duodenum with water, villous patterns were scored as the following: definitely present, partially present, or definitely absent. Villous patterns also were histopathologically scored as the following: normal, partial villous pattern, or total villous atrophy.

RESULTS

Interobserver variability was excellent (kappa = 0.93). The concordance between either endoscopic magnification or endoscopic magnification after filling the duodenum with water and histology was 100% for presence/absence of villi. The sensitivity, the specificity, and the positive and negative predictive values of endoscopic magnification for detection of any villous abnormality were 95%, 99%, 95%, and 99%, respectively; the respective values of endoscopic magnification after filling the duodenum with water were 95%, 98%, 92%, and 99%.

CONCLUSIONS

High-resolution magnifying upper endoscopy can reliably predict the presence or the absence of duodenal villi.

Reliability of the "immersion technique" during routine upper endoscopy for detection of abnormalities of duodenal villi in patients with dyspepsia

BACKGROUND

Upper endoscopy is not routinely performed to directly detect abnormalities of the duodenal villi. The reliability of the immersion technique for assessment of duodenal villi was evaluated in a series of patients with dyspepsia.

METHODS

A total of 396 patients who were to undergo standard EGD for dyspeptic symptoms were enrolled. Patients with suspected malabsorption were excluded. By performing a "modified immersion technique," duodenal villi were scored as the following: definitely present, partially present, or definitely absent. Three duodenal biopsy specimens were obtained from each patient, and villi also were scored histologically as the following: normal, partial villous pattern, or total villous atrophy.

RESULTS

Sensitivity, specificity, and positive and negative predictive values of the modified immersion technique for detection of total villous atrophy were 100%, 99.7%, 85.7%, and 100%, respectively. Sensitivity, specificity, and positive and negative predictive values of modified immersion technique for detection of partial villous patterns were 75%, 99.5%, 60%, and 99.7%, respectively. Sensitivity, specificity, and positive and negative predictive values for modified immersion technique detection of any villous abnormality (partial or total villous atrophy) were 90.9%, 99.5%, 83.3%, and 99.7%, respectively.

CONCLUSIONS

During standard EGD, duodenal evaluation by modified immersion technique can reliably detect abnormalities of duodenal villi. This simple diagnostic technique may be performed routinely during endoscopic exploration of duodenum.