Occurrence of autoimmune pancreatitis after chronic immune thrombocytopenia in a Caucasian adolescent.

Autoimmune pancreatitis is a rare, distinct and increasingly recognized form of chronic inflammatory pancreatic disease secondary to an underlying autoimmune mechanism. We report on a 14-year-old boy who developed autoimmune pancreatitis, while he was under treatment with eltrombopag for chronic immune thrombocytopenia. Therapy with corticosteroids resulted in complete remission of both. This is the first report on the co-occurrence of autoimmune pancreatitis and chronic immune thrombocytopenia in childhood, and clinicians should be aware of this rare association, because early diagnosis and therapy of autoimmune pancreatitis may prevent severe complications.

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.

Accuracy in Diagnosis of Celiac Disease Without Biopsies in Clinical Practice.

BACKGROUND & AIMS: The guidelines of the European Society of Pediatric Gastroenterology, Hepatology, and Nutrition allow for diagnosis of celiac disease without biopsies in children with symptoms and levels of immunoglobulin A against tissue-transglutaminase (TGA-IgA) 10-fold or more the upper limit of normal (ULN), confirmed by detection of endomysium antibodies (EMA) and positivity for HLA-DQ2/DQ8. We performed a large, international prospective study to validate this approach. METHODS: We collected data from consecutive pediatric patients (18 years or younger) on a gluten-containing diet who tested positive for TGA-IgA from November 2011 through May 2014, seen at 33 pediatric gastroenterology units in 21 countries. Local centers recorded symptoms; measurements of total IgA, TGA, and EMA; and histopathology findings from duodenal biopsies. Children were considered to have malabsorption if they had chronic diarrhea, weight loss (or insufficient gain), growth failure, or anemia. We directly compared central findings from 16 antibody tests (8 for TGA-IgA, 1 for TGA-IgG, 6 for IgG against deamidated gliadin peptides, and 1 for EMA, from 5 different manufacturers), 2 HLA-DQ2/DQ8 tests from 2 manufacturers, and histopathology findings from the reference pathologist. Final diagnoses were based on local and central results. If all local and central results were concordant for celiac disease, cases were classified as proven celiac disease. Patients with only a low level of TGA-IgA (threefold or less the ULN) but no other results indicating celiac disease were classified as no celiac disease. Central histo-morphometry analyses were performed on all other biopsies and cases were carefully reviewed in a blinded manner. Inconclusive cases were regarded as not having celiac disease for calculation of diagnostic accuracy. The primary aim was to determine whether the nonbiopsy approach identifies children with celiac disease with a positive predictive value (PPV) above 99% in clinical practice. Secondary aims included comparing performance of different serological tests and to determine whether the suggested criteria can be simplified. RESULTS: Of 803 children recruited for the study, 96 were excluded due to incomplete data, low level of IgA, or poor-quality biopsies. In the remaining 707 children (65.1% girls; median age, 6.2 years), 645 were diagnosed with celiac disease, 46 were found not to have celiac disease, and 16 had inconclusive results. Findings from local laboratories of TGA-IgA 10-fold or more the ULN, a positive result from the test for EMA, and any symptom identified children with celiac disease (n = 399) with a PPV of 99.75 (95% confidence interval [CI], 98.61-99.99); the PPV was 100.00 (95% CI, 98.68-100.00) when only malabsorption symptoms were used instead of any symptom (n = 278). Inclusion of HLA analyses did not increase accuracy. Findings from central laboratories differed greatly for patients with lower levels of antibodies, but when levels of TGA-IgA were 10-fold or more the ULN, PPVs ranged from 99.63 (95% CI, 98.67-99.96) to 100.00 (95% CI, 99.23-100.00). CONCLUSIONS: Children can be accurately diagnosed with celiac disease without biopsy analysis. Diagnosis based on level of TGA-IgA 10-fold or more the ULN, a positive result from the EMA tests in a second blood sample, and the presence of at least 1 symptom could avoid risks and costs of endoscopy for more than half the children with celiac disease worldwide. HLA analysis is not required for accurate diagnosis. Clinical Trial Registration no: DRKS00003555.

Paediatric Gastrointestinal Endoscopy: European Society for Paediatric Gastroenterology Hepatology and Nutrition and European Society of Gastrointestinal Endoscopy Guidelines.

This guideline refers to infants, children, and adolescents ages 0 to 18 years. The areas covered include indications for diagnostic and therapeutic esophagogastroduodenoscopy and ileocolonoscopy; endoscopy for foreign body ingestion; corrosive ingestion and stricture/stenosis endoscopic management; upper and lower gastrointestinal bleeding; endoscopic retrograde cholangiopancreatography; and endoscopic ultrasonography. Percutaneous endoscopic gastrostomy and endoscopy specific to inflammatory bowel disease has been dealt with in other guidelines and are therefore not mentioned in this guideline. Training and ongoing skill maintenance are to be dealt with in an imminent sister publication to this.

Pediatric gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) and European Society for Paediatric Gastroenterology Hepatology and Nutrition (ESPGHAN) Guideline Executive summary.

This Executive summary of the Guideline on pediatric gastrointestinal endoscopy from the European Society of Gastrointestinal Endoscopy (ESGE) and the European Society for Paediatric Gastroenterology Hepatology and Nutrition (ESPGHAN) refers to infants, children, and adolescents aged 0 - 18 years. The areas covered include: indications for diagnostic and therapeutic esophagogastroduodenoscopy and ileocolonoscopy; endoscopy for foreign body ingestion; endoscopic management of corrosive ingestion and stricture/stenosis; upper and lower gastrointestinal bleeding; endoscopic retrograde cholangiopancreatography, and endoscopic ultrasonography. Percutaneous endoscopic gastrostomy and endoscopy specific to inflammatory bowel disease (IBD) have been dealt with in other Guidelines and are therefore not mentioned in this Guideline. Training and ongoing skill maintenance will be addressed in an imminent sister publication.

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.

Survey on computer aided decision support for diagnosis of celiac disease.

Celiac disease (CD) is a complex autoimmune disorder in genetically predisposed individuals of all age groups triggered by the ingestion of food containing gluten. A reliable diagnosis is of high interest in view of embarking on a strict gluten-free diet, which is the CD treatment modality of first choice. The gold standard for diagnosis of CD is currently based on a histological confirmation of serology, using biopsies performed during upper endoscopy. Computer aided decision support is an emerging option in medicine and endoscopy in particular. Such systems could potentially save costs and manpower while simultaneously increasing the safety of the procedure. Research focused on computer-assisted systems in the context of automated diagnosis of CD has started in 2008. Since then, over 40 publications on the topic have appeared. In this context, data from classical flexible endoscopy as well as wireless capsule endoscopy (WCE) and confocal laser endomicrosopy (CLE) has been used. In this survey paper, we try to give a comprehensive overview of the research focused on computer-assisted diagnosis of CD.

Do we need annotation experts? A case study in celiac disease classification.

Inference of clinically-relevant findings from the visual appearance of images has become an essential part of processing pipelines for many problems in medical imaging. Typically, a sufficient amount labeled training data is assumed to be available, provided by domain experts. However, acquisition of this data is usually a time-consuming and expensive endeavor. In this work, we ask the question if, for certain problems, expert knowledge is actually required. In fact, we investigate the impact of letting non-expert volunteers annotate a database of endoscopy images which are then used to assess the absence/presence of celiac disease. Contrary to previous approaches, we are not interested in algorithms that can handle the label noise. Instead, we present compelling empirical evidence that label noise can be compensated by a sufficiently large corpus of training data, labeled by the non-experts.

On the generalizability of resting-state fMRI machine learning classifiers.

Machine learning classifiers have become increasingly popular tools to generate single-subject inferences from fMRI data. With this transition from the traditional group level difference investigations to single-subject inference, the application of machine learning methods can be seen as a considerable step forward. Existing studies, however, have given scarce or no information on the generalizability to other subject samples, limiting the use of such published classifiers in other research projects. We conducted a simulation study using publicly available resting-state fMRI data from the 1000 Functional Connectomes and COBRE projects to examine the generalizability of classifiers based on regional homogeneity of resting-state time series. While classification accuracies of up to 0.8 (using sex as the target variable) could be achieved on test datasets drawn from the same study as the training dataset, the generalizability of classifiers to different study samples proved to be limited albeit above chance. This shows that on the one hand a certain amount of generalizability can robustly be expected, but on the other hand this generalizability should not be overestimated. Indeed, this study substantiates the need to include data from several sites in a study investigating machine learning classifiers with the aim of generalizability.

Follow-up of pediatric celiac disease: value of antibodies in predicting mucosal healing, a prospective cohort study.

BACKGROUND: In diagnosing celiac disease (CD), serological tests are highly valuable. However, their role in following up children with CD after prescription of a gluten-free diet is unclear. This study aimed to compare the performance of antibody tests in predicting small-intestinal mucosal status in diagnosis vs. follow-up of pediatric CD. METHODS: We conducted a prospective cohort study at a tertiary-care center. 148 children underwent esophohagogastroduodenoscopy with biopsies either for symptoms ± positive CD antibodies (group A; n = 95) or following up CD diagnosed ≥ 1 year before study enrollment (group B; n = 53). Using biopsy (Marsh ≥ 2) as the criterion standard, areas under ROC curves (AUCs) and likelihood-ratios were calculated to estimate the performance of antibody tests against tissue transglutaminase (TG2), deamidated gliadin peptide (DGP) and endomysium (EMA). RESULTS: AUCs were higher when tests were used for CD diagnosis vs. follow-up: 1 vs. 0.86 (P = 0.100) for TG2-IgA, 0.85 vs. 0.74 (P = 0.421) for TG2-IgG, 0.97 vs. 0.61 (P = 0.004) for DPG-IgA, and 0.99 vs. 0.88 (P = 0.053) for DPG-IgG, respectively. Empirical power was 85% for the DPG-IgA comparison, and on average 33% (range 13-43) for the non-significant comparisons. Among group B children, 88.7% showed mucosal healing (median 2.2 years after primary diagnosis). Only the negative likelihood-ratio of EMA was low enough (0.097) to effectively rule out persistent mucosal injury. However, out of 12 EMA-positive children with mucosal healing, 9 subsequently turned EMA-negative. CONCLUSIONS: Among the CD antibodies examined, negative EMA most reliably predict mucosal healing. In general, however, antibody tests, especially DPG-IgA, are of limited value in predicting the mucosal status in the early years post-diagnosis but may be sufficient after a longer period of time.

Characteristics of invasive pneumococcal disease in hospitalized children in Austria.

UNLABELLED: In a prospective surveillance study covering all pediatric wards in Austria, 308 cases of invasive pneumococcal disease (IPD) were reported in hospitalized children <5 years of age between 2002 and 2012. Incidence was 7.1 per 100,000 per year for IPD with a case fatality rate of 3 %, and 1.9 per 100,000 per year for pneumococcal meningitis with a case fatality rate of 9 %. At hospital discharge, 17 % of the children were not fully recovered and suffered from problems such as hearing or motor deficits. Persistent sequelae 6 months after hospital discharge were present in 13 % of the children, a finding that emphasizes the seriousness of IPD. From 2007 onwards, we observed a shift of pneumococcal serotypes from those covered by the heptavalent vaccine to serotypes consequently added to 10- and 13-valent vaccines, particularly regarding serotype 19A. Among antimicrobial resistances detected, macrolide resistance was predominant; however, between 2002 and 2012, we saw an overall decrease of resistance rates. CONCLUSION: Considering this change of serotypes and the high rate of permanent sequelae after IPD, our data show the importance of pediatric pneumococcal vaccination and the relevance of continuous monitoring of circulating serotypes. By the end of 2012, which was the first year of universal mass vaccination against pneumococcal disease in Austria, no change in the incidence of invasive pneumococcal disease was observed yet.

Non-Celiac Gluten sensitivity: the new frontier of gluten related disorders.

Non Celiac Gluten sensitivity (NCGS) was originally described in the 1980s and recently a "re-discovered" disorder characterized by intestinal and extra-intestinal symptoms related to the ingestion of gluten-containing food, in subjects that are not affected with either celiac disease (CD) or wheat allergy (WA). Although NCGS frequency is still unclear, epidemiological data have been generated that can help establishing the magnitude of the problem. Clinical studies further defined the identity of NCGS and its implications in human disease. An overlap between the irritable bowel syndrome (IBS) and NCGS has been detected, requiring even more stringent diagnostic criteria. Several studies suggested a relationship between NCGS and neuropsychiatric disorders, particularly autism and schizophrenia. The first case reports of NCGS in children have been described. Lack of biomarkers is still a major limitation of clinical studies, making it difficult to differentiate NCGS from other gluten related disorders. Recent studies raised the possibility that, beside gluten, wheat amylase-trypsin inhibitors and low-fermentable, poorly-absorbed, short-chain carbohydrates can contribute to symptoms (at least those related to IBS) experienced by NCGS patients. In this paper we report the major advances and current trends on NCGS.

Sustained low hospitalization rates after four years of rotavirus mass vaccination in Austria.

This hospital based surveillance study evaluates the effects of the rotavirus mass vaccination program, which was initiated in Austria in August 2007. Since then, incidence rates of rotavirus hospitalizations in children <15 years of age have decreased by 70% and 64% in 2010 and 2011 compared to the pre-vaccination era (2001-2005). Incidence rates were highest in children <90 days of age, highlighting the importance of the early start of active rotavirus immunization. In children between 2 and 3.5 years in 2011, who were in the second and third year after vaccination in the universal mass vaccination program, incidence rates remained low suggesting sustained protection after vaccination up to three years. In the years 2010 and 2011, field effectiveness of the vaccines was between 79% and 96%, depending on the assumptions made for children without information on vaccination history. From genotyping an increase of the prevalence of G2P[4] in children with breakthrough infection (disease despite vaccination) can be suspected. The rate of severe adverse events was 1.3-1.5 per 10(-5) administered doses of rotavirus vaccines and no death, intussusception or Kawasaki disease was reported in 2010 and 2011 following rotavirus vaccination.

Scale invariant texture descriptors for classifying celiac disease.

Scale invariant texture recognition methods are applied for the computer assisted diagnosis of celiac disease. In particular, emphasis is given to techniques enhancing the scale invariance of multi-scale and multi-orientation wavelet transforms and methods based on fractal analysis. After fine-tuning to specific properties of our celiac disease imagery database, which consists of endoscopic images of the duodenum, some scale invariant (and often even viewpoint invariant) methods provide classification results improving the current state of the art. However, not each of the investigated scale invariant methods is applicable successfully to our dataset. Therefore, the scale invariance of the employed approaches is explicitly assessed and it is found that many of the analyzed methods are not as scale invariant as they theoretically should be. Results imply that scale invariance is not a key-feature required for successful classification of our celiac disease dataset.

Prevalence and clinical course of viral upper respiratory tract infections in immunocompromised pediatric patients with malignancies or after hematopoietic stem cell transplantation.

BACKGROUND: Respiratory tract infections (RTI) in immunosuppressed pediatric patients with malignancies or after hematopoietic stem cell transplantation (HSCT) are associated with significant morbidity and mortality. Prospective data on the incidence and clinical role of infections by respiratory viruses in this population have been lacking. METHODS: In this prospective study, 191 children between 0 and 18 years of age were investigated by real-time polymerase chain reaction for the presence of 8 common respiratory virus types in transnasal aspirations. The study included 110 children with leukemia, lymphoma, or solid tumors (subgroup 1); 31 children after HSCT (subgroup 2); and 50 immunocompetent control patients. RESULTS: In comparison with the control group, immunocompromised children showed a significantly higher incidence of positive virus tests (subgroup 1: 53%; subgroup 2: 81%; controls: 24%; P<0.0001), and more frequently experienced ensuing viral infections in the lower respiratory tract (subgroup 1: 74%; subgroup 2: 88%; controls: 25%; P<0.0001). Sixteen percent of these children had coinfections by 2 or more viruses and revealed more severe respiratory illness. CONCLUSIONS: The present epidemiologic study on viral upper RTI in immunocompromised children revealed a high virus-associated morbidity which was particularly prominent in HSCT recipients. In these children, detection of viral coinfections was identified as a risk factor for a severe course of lower RTI.

Endoscope distortion correction does not (easily) improve mucosa-based classification of celiac disease.

Distortion correction is applied to endoscopic duodenal imagery to improve automated classification of celiac disease affected mucosa patches. In a set of six edge- and shape-related feature extraction techniques, only a single one is able to consistently benefit from distortion correction, while for others, even a decrease of classification accuracy is observed. Different types of distortion correction do not lead to significantly different behaviour in the observed application scenario.

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.

Helicobacter pylori eradication rates in children upon susceptibility testing based on noninvasive stool polymerase chain reaction versus gastric tissue culture.

BACKGROUND AND OBJECTIVES: In children with clarithromycin-resistant Helicobacter pylori, clarithromycin-containing therapies often fail. The present study aimed to assess the outcome of tailored therapy upon noninvasive versus invasive H pylori susceptibility testing. PATIENTS AND METHODS: A retrospective cohort study was conducted in a pediatric outpatient clinic located in a region where H pylori clarithromycin resistance is highly prevalent. Between June 2007 and September 2009, 96 infected children (mean age 10.8 years), naïve to H pylori eradication treatment, were prescribed triple eradication therapies. These therapies were individually tailored upon susceptibility testing performed either noninvasively using stool polymerase chain reaction (stool PCR group) or invasively using endoscopy, biopsy, and culturing of gastric biopsies (gastric biopsy group). Eradication was defined by negative results upon noninvasive testing including stool PCR at least 5 weeks after the end of treatment. RESULTS: H pylori was eradicated in 43 of 55 stool PCR group versus 30 of 41 gastric biopsy group children (78.2% vs 73.2%, P = 0.63). Of those H pylori strains with pretherapeutic clarithromycin susceptibility, 78.8% were eradicated in the stool PCR group and 69.2% in the gastric biopsy group (P = 0.41) following clarithromycin-containing therapy; clarithromycin resistance was acquired by 4.1% of strains in the former group versus 12% in the latter (P = 0.33). CONCLUSIONS: Stool PCR is as effective as the invasive approach of H pylori susceptibility testing for targeting resistance-guided eradication treatments in children. Furthermore, stool PCR is a useful tool for tracking the emergence of clarithromycin resistance following eradication treatment.

Herd immunity after two years of the universal mass vaccination program against rotavirus gastroenteritis in Austria.

Austria was the first country in Europe implementing a universal mass vaccination program against rotavirus gastroenteritis (RV-GE) for all infants nationwide. Epidemiological data from a hospital based surveillance system show that incidence rates of children hospitalized with RV-GE decreased in 2009 compared to 2008 and compared to the prevaccination period 2001-2005. Decreasing hospitalization-rates from RV-GE were observed in children of all age groups, even in those not eligible for vaccination according to their age, suggesting herd immunity induced by universal mass vaccination against RV-GE. In 2009 the disease burden was highest in children below three months of age stressing the importance of the early start of the immunization course.

Time trends of Helicobacter pylori resistance to antibiotics in children living in Vienna, Austria.

BACKGROUND: Increase of antibiotic resistance is a worldwide problem. Within the 4 years before the turn of the millennium Helicobacter pylori strains isolated in children living in Vienna, Austria, showed a primary clarithromycin and metronidazole resistance of 20% and 16%, respectively. The aim of this retrospective follow-up survey was to assess the further development and current antimicrobial resistance status. METHODS: Children having undergone upper endoscopy between March 2002 and March 2008 at the same two co-operating pediatric gastroenterology units which had also been collaborating on the prior assessment were included. H. pylori infection was diagnosed by rapid urease test, histology, and culture. If the latter was positive, susceptibility testing to amoxicillin, clarithromycin and metronidazole by E-test followed. From March 2004 onwards, susceptibility to levofloxacin, tetracycline and rifampin was additionally assessed. RESULTS: Out of 897 children, 153 had a proven infection with H. pylori and no history of prior eradication treatment. Their median age was 11.5 years (range 0.5-20.9 years). Primary resistance to clarithromycin and metronidazole were 34% and 22.9%, respectively; dual resistance was found in 9.8% of the strains; 0.9% was resistant to tetracycline and rifampin, respectively. No case of amoxicillin resistance was detected. The only independent risk factor for clarithromycin resistance turned out to be the origin of a child from Austrian parents. CONCLUSIONS: In the last decade, the rate of primary resistance of H. pylori to clarithromycin continued to rise. No significant change was found regarding primary resistance to metronidazole or dual resistance to metronidazole and clarithromycin, respectively.