Search

Colon capsule endoscopy (CCE) is a minimally invasive alternative for patients unwilling to undergo conventional colonoscopy, or for whom the latter exam is contraindicated. This is particularly important in the setting of colorectal cancer screening. Nevertheless, these exams produce large numbers of images, and reading them is a monotonous and time-consuming task, with the risk of overlooking important lesions. The development of automated tools based on artificial intelligence (AI) technology may improve some of the drawbacks of this diagnostic instrument. A database of CCE images was used for development of a Convolutional Neural Network (CNN) model. This database included anonymized images of patients with protruding lesions in the colon or patients with normal colonic mucosa or with other pathologic findings. A total of 3,387,259 frames from 24 CCE exams were retrospectively reviewed. For CNN development, 3640 images (860 protruding lesions and 2780 with normal mucosa or other findings) were ultimately extracted. Training and validation datasets were constructed for the development and testing of the CNN. The CNN detected protruding lesions with a sensitivity, specificity, positive and negative predictive values of 90.7, 92.6, 79.2 and 96.9%, respectively. The area under the receiver operating characteristic curve for detection of protruding lesions was 0.97. The deep learning algorithm we developed is capable of accurately detecting protruding lesions. The application of AI technology to CCE may increase its diagnostic accuracy and acceptance for screening of colorectal neoplasia.

Colon capsule endoscopy (CCE) is a minimally invasive alternative to conventional colonoscopy. Most studies on CCE focus on colorectal neoplasia detection. The development of automated tools may address some of the limitations of this diagnostic tool and widen its indications for different clinical settings. We developed an artificial intelligence model based on a convolutional neural network (CNN) for the automatic detection of blood content in CCE images. Training and validation datasets were constructed for the development and testing of the CNN. The CNN detected blood with a sensitivity, specificity, and positive and negative predictive values of 99.8 %, 93.2 %, 93.8 %, and 99.8 %, respectively. The area under the receiver operating characteristic curve for blood detection was 1.00. We developed a deep learning algorithm capable of accurately detecting blood or hematic residues within the lumen of the colon based on colon CCE images.

Introdução: As intervenções fisioterapêuticas podem prevenir e minimizar as disfunções na musculatura do assoalho pélvico durante a gestação. Objetivo: Verificar quais são as intervenções fisioterapêuticas no assoalho pélvico durante a gestação e no preparo para o parto e elaborar um manual com informações mais relevantes encontradas nessa pesquisa. Métodos: Foi realizada uma revisão bibliográfica nas bases de dados: Pubmed, Scielo e PEDro. Foram selecionados 10 artigos relevantes publicados entre o perí­odo de 1997 a 2019. Resultados: Os estudos sobre massagem perineal mostraram que houve redução de episiotomia, dor perineal e laceração. Quanto ao treinamento dos músculos do assoalho pélvico, houve aumento significativo da pressão desses músculos, menor taxa de episiotomia e do tempo da segunda fase do trabalho de parto. O Epi-no® mostrou aumento significativo de perí­neo intacto e taxas mais baixas de episiotomia quando realizados com auxí­lio do fisioterapeuta. Conclusão: Os estudos mostram que o treinamento da musculatura do assoalho pélvico supervisionado e massagem perineal são eficazes para o preparo para o parto. O treinamento com Epi-no® no pré parto apontou ser eficaz na redução de laceração e episiotomia intraparto, porém para determinar sua real eficácia, é necessário aumentar o número amostral.

Whipple’s disease is a rare chronic systemic infection caused by Tropheryma whipplei. The widespread infection by this rod is responsible for the protean clinical manifestations of the disease, although its classical form is notable for the prevalence of abdominal symptoms such as chronic diarrhea and abdominal pain. Whitish-yellow patches, suggestive of lymphangiectasia, are typically observed in the duodenum during upper endoscopy. The diagnosis of this condition is supported by the identification in duodenal biopsies of Periodic acid-Schiff staining within lamina propria macrophages. Nevertheless, a significant portion of patients do not have lesions within the range of conventional upper endoscopy. Therefore, other endoscopic procedures such as video capsule endoscopy and enteroscopy may be useful to detect more distal lesions. The authors describe a case where the combined used of both techniques allowed the unmasking of this disease.

Background and aims The use of capsule endoscopy (CE) is paramount for the detection of small bowel ulcers and erosions. These lesions are responsible for a significant part of obscure gastrointestinal bleeding cases. The interpretation of CE exams is time-consuming and susceptible to errors. This study aims to develop a convolutional neural network (CNN) model for identification and differentiation of ulcers and erosion with distinct hemorrhagic potential in CE images. Methods A CNN based on CE images was developed. This database included images of normal small intestinal mucosa, mucosal erosions, and ulcers with distinct bleeding potential. The hemorrhagic risk was assessed by the Saurin's classification. For CNN development, 23,720 images were ultimately extracted (18,045 normal mucosa, 1765 mucosal erosions, 1300 images of ulcers with uncertain bleeding potential—P1 ulcers; and 2610 ulcers with high bleeding potential—P2 ulcers. Two image datasets were created for CNN training and validation. Results Overall, the network had a sensitivity of 86.6% and a specificity of 95.9% for detection of ulcers and erosions. Mucosal erosions were detected with a sensitivity and specificity of 73.1% and 96.1%, respectively. P1 ulcers were identified with a sensitivity of 71.5%, and a specificity of 97.8%. P2 ulcers were detected with a sensitivity and specificity of 91.4% and 98.8%, respectively. Conclusion Our algorithm is the first deep learning-based model to accurately detect and distinguish enteric mucosal breaks with different hemorrhagic risk. CNN-assisted CE reading may improve the diagnostic of these lesions and overall CE efficiency.

Introduction: Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disorder with an inexorably progressive course which leads to a progressive neuromuscular weakness. Weight loss is one of the major bad prognostic factors in ALS. The placement of percutaneous endoscopic gastrostomy (PEG) is of paramount importance in patients with dysphagia to improve the disease outcomes, although some fear exists regarding the possible ventilatory complications during the procedure. The aim of this study was to evaluate the safety and effectiveness of PEG tube insertion under non-invasive ventilation (NIV) in patients with ALS and severe ventilatory impairment. Methods: A retrospective study of all consecutive PEGs placed in our department from May 2011 to January 2018 in patients with ALS was performed. The procedure was performed under non-invasive positive-pressure ventilation for ventilatory support. Results: We included 59 patients with ALS with severe ventilatory impairment, 58% were female, with a mean age of 67.2 ± 10.1 years and a median follow-up of 6 [2–15] months. The main indication for PEG placement was dysphagia (98%). The median time for PEG tube insertion since the established diagnosis of ALS was 12 [6–25] months and 4 [2–18] months since the beginning of bulbar symptoms. The majority of the patients had placed a 20-Fr PEG (63%) and under mild sedation with midazolam (80%), all under NIV. There were no immediate complications during and after the procedure (no episodes of aspiration or orotracheal intubation) and mortality. Conclusion: The placement of PEG is a very important procedure in patients with ALS and severe ventilatory impairment. The interdisciplinary department collaboration permitted the placement of PEG under NIV, in a safe and effective procedure in this special population.

Introduction Complications of cirrhosis are one the major causes of hospital admission associated with high morbimortality rates and social and economic charges. The aims of this study were to evaluate hospital readmission and mortality rates and predictive factors for hospital readmission and mortality. Methods Patients with decompensated cirrhosis admitted to our institution between 2008–2014 were retrospectively analyzed. Results Included 427 admissions from 177 patients with cirrhosis with mean age of 59.0 ± 12.3 years. The major cause was alcoholic-related liver disease and the median duration of admission was 9.0 days (IQR 6.0–14.0). During the follow-up period,there were 250 readmissions from 95 patients, with a median of 58 (IQR27-134) days for readmission, representing 58.5% of the total number of admissions.The 180-day mortality rate was 35.0%. In the multivariate analysis, ascites, smoking and MELD Na were associated with 180-day mortality. Creatinine, albumin, esophageal variceal bleeding, previous variceal banding, lactulose, rifaximin and proton pump inhibitors use were independently associated with need of readmission. Based on regression analysis, two models were calculated to predict 180-day mortality (AUROC 0.74 (0.682−0.794)) and need for readmission(AUROC 0.821 (0.781−0.861)), p Conclusion The readmission rate and mortality of cirrhotic patients are still very high and it is a priority to determine preventable risk factors to improve patient outcome. Two models were created to predict 180-day mortality(AUROC 0.74) and need for readmission(AUROC 0.821), that could guide the management of the patients at the time of admission.

Capsule endoscopy has revolutionized the management of patients with obscure gastrointestinal bleeding. Nevertheless, reading capsule endoscopy images is time-consuming and prone to overlooking significant lesions, thus limiting its diagnostic yield. We aimed to create a deep learning algorithm for automatic detection of blood and hematic residues in the enteric lumen in capsule endoscopy exams.A convolutional neural network was developed based on a total pool of 22,095 capsule endoscopy images (13,510 images containing luminal blood and 8,585 of normal mucosa or other findings). A training dataset comprising 80% of the total pool of images was defined. The performance of the network was compared to a consensus classification provided by 2 specialists in capsule endoscopy. Subsequently, we evaluated the performance of the network using an independent validation dataset (20% of total image pool), calculating its sensitivity, specificity, accuracy, and precision.Our convolutional neural network detected blood and hematic residues in the small bowel lumen with an accuracy and precision of 98.5 and 98.7%, respectively. The sensitivity and specificity were 98.6 and 98.9%, respectively. The analysis of the testing dataset was completed in 24 s (approximately 184 frames/s).We have developed an artificial intelligence tool capable of effectively detecting luminal blood. The development of these tools may enhance the diagnostic accuracy of capsule endoscopy when evaluating patients presenting with obscure small bowel bleeding.A endoscopia por cápsula revolucionou a abordagem a doentes com hemorragia digestiva obscura. No entanto, a leitura de imagens de endoscopia por cápsula é morosa, havendo suscetibilidade para a perda de lesões significativas, limitando desta forma a sua eficácia diagnóstica. Este estudo visou a criação de um algoritmo deFoi desenvolvida uma rede neural convolucional com base num conjunto de 22,095 imagens de endoscopia de cápsula (13,510 imagens contendo sangue e 8,585 mucosa normal ou outros achados). Foi construído um grupo de imagens para treino, compreendendo 80% do total de imagens. O desempenho da rede foi comparado com a classificação consenso de dois especialistas em endoscopia por cápsula. Posteriormente, o desempenho da rede foi avaliado usando os restantes 20% de imagens. Foi calculada a sua sensibilidade, especificidade, exatidão e precisão.O algoritmo detetou sangue e resíduos hemáticos no lúmen do intestino delgado com uma exatidão e precisão de 98.5% e 98.7%, respetivamente. A sensibilidade e especificidade foram 98.6% e 98.9%, respetivamente. A análise do conjunto de usado para teste da rede foi concluída em 24 segundos (aproximadamente 184 frames/s).Foi desenvolvida uma ferramenta de inteligência artificial capaz de detetar efetivamente o sangue luminal. O desenvolvimento dessas ferramentas pode aumentar a precisão do diagnóstico da endoscopia por cápsula ao avaliar pacientes que apresentam sangramento obscuro do intestino delgado.

Colon capsule endoscopy (CCE) represents a landmark in minimally invasive exploration of the colonic mucosa for patients with contraindications for a conventional colonoscopy, or for whom the latter exam is unwanted or unfeasible. Colorectal neoplasia is the most common lesion found in CCE. The widespread acceptance of CCE as a non-invasive diagnostic method is particularly important in the setting of colorectal cancer screening. However, reviewing these exams is a time-consuming process as they generate a large number of frames, with the risk of overlooking important lesions. We aimed to develop an artificial intelligence (AI) algorithm using a convolutional neural network (CNN) architecture for the automatic detection of colonic protruding lesions. A CNN was constructed using an anonymized database of CCE images collected from a total of 124 patients. This database included images of patients with colonic protruding lesions or patients with normal colonic mucosa or with other pathologic findings. A total of 5715 images (2410 protruding lesions, 3305 normal mucosa or other findings) were extracted for CNN development. Two image datasets were created and used for training and validation of the CNN. The performance of the CNN was measured by calculating the area under the receiving operating characteristic curve (AUROC), sensitivity, specificity, positive and negative predictive values (PPV and NPV, respectively). The AUROC for detection of protruding lesions was 0.99. The sensitivity, specificity, PPV and NPV were 90.0%, 99.1%, 98.6% and 93.2%, respectively. The overall accuracy of the network was 95.3%. The developed deep learning algorithm accurately detected protruding lesions in CCE images. The introduction of AI technology to CCE may increase its diagnostic accuracy and acceptance for the screening of colorectal neoplasia.

Background Capsule endoscopy (CE) is the first line for evaluation of patients with obscure gastrointestinal bleeding. A wide range of small intestinal vascular lesions with different hemorrhagic potential are frequently found in these patients. Nevertheless, reading CE exams is time-consuming and prone to errors. Convolutional neural networks (CNN) are artificial intelligence tools with high performance levels in image analysis. This study aimed to develop a CNN-based model for identification and differentiation of vascular lesions with distinct hemorrhagic potential in CE images. Methods The development of the CNN was based on a database of CE images. This database included images of normal small intestinal mucosa, red spots, and angiectasia/varices. The hemorrhagic risk was assessed by Saurin's classification. For CNN development, 11,588 images (9525 normal mucosa, 1026 red spots, and 1037 angiectasia/varices) were ultimately extracted. Two image datasets were created for CNN training and testing. Results The network was 91.8% sensitive and 95.9% specific for detection of vascular lesions, providing accurate predictions in 94.4% of cases. In particular, the CNN had a sensitivity and specificity of 97.1% and 95.3%, respectively, for detection of red spots. Detection of angiectasia/varices occurred with a sensitivity of 94.1% and a specificity of 95.1%. The CNN had a frame reading rate of 145 frames/sec. Conclusions The developed algorithm is the first CNN-based model to accurately detect and distinguish enteric vascular lesions with different hemorrhagic risk. CNN-assisted CE reading may improve the diagnosis of these lesions and overall CE efficiency.

The applicability of artificial intelligence (AI) in gastroenterology is a hot topic because of its disruptive nature. Capsule endoscopy plays an important role in several areas of digestive pathology, namely in the investigation of obscure hemorrhagic lesions and the management of inflammatory bowel disease. Therefore, there is growing interest in the use of AI in capsule endoscopy. Several studies have demonstrated the enormous potential of using convolutional neural networks in various areas of capsule endoscopy. The exponential development of the usefulness of AI in capsule endoscopy requires consideration of its medium- and long-term impact on clinical practice. Indeed, the advent of deep learning in the field of capsule endoscopy, with its evolutionary character, could lead to a paradigm shift in clinical activity in this setting. In this review, we aim to illustrate the state of the art of AI in the field of capsule endoscopy.

BACKGROUND AND AIMS Capsule endoscopy (CE) revolutionized the study of the small intestine. Nevertheless, reviewing CE images is a time-consuming and prone to error. Artificial intelligence algorithms, particularly convolutional neural networks (CNN) are expected to overcome these drawbacks. Protruding lesions of the small intestine exhibit enormous morphological diversity in CE images. We aimed to develop a CNN-based algorithm for automatic detection small bowel protruding lesions. METHODS A CNN was developed using a pool of CE images containing protruding lesions or normal mucosa from 1,229 patients. A training dataset was used for development of the model. The performance of the network was evaluated using an independent dataset. The performance of the network was evaluated by calculating its sensitivity, specificity, accuracy, positive and negative predictive values. RESULTS A total of 18,625 CE images (2,830 showing protruding lesions and 15,795 normal mucosa) were included. Training and validation datasets were built with an 80%/20% distribution, respectively. After optimizing the architecture of the network, our model automatically detected small bowel protruding lesions with an accuracy of 92.5%. Our CNN had a sensitivity and specificity of 96.8%, 96.5%, respectively. The CNN analyzed the validation dataset in 53 seconds, at a rate of approximately 70 frames per second. CONCLUSIONS We developed an accurate CNN for automatic detection of enteric protruding lesions with a wide range of morphologies. The development of these tools may enhance the diagnostic efficiency of CE.

BACKGROUND Capsule enteroscopy (CE) and 99mTc Red blood cell (RBC) scintigraphy are frequently used tests in the investigation of obscure gastrointestinal bleeding (OGIB). There is a scarcity of data comparing both diagnostic modalities. This study aims to assess the performance of CE and scintigraphy for the diagnosis of OGIB. METHODS Patients who underwent CE and scintigraphy for OGIB were selected and analyzed retrospectively. The hemorrhagic potential of CE findings was rated using Saurin's classification. The concordance between both diagnostic techniques for bleeding detection and localization was analyzed. RESULTS Eighty-five patients (62% female), with a median age of 63 years, were included. Capsule enteroscopy identified 37 patients (43%) with high hemorrhagic potential (P2) lesions. Most scintigraphy exams were positive for gastrointestinal bleeding (82%). No concordance was found between the detection of lesions with hemorrhagic potential in CE and scintigraphy (kappa

A dramatic SARS-Cov-2 outbreak is hitting Italy hard. To face the new scenario all the hospitals have been re-organised in order to reduce all the outpatient services and to devote almost all their personnel and resources to the management of Covid-19 patients. As a matter of fact, all the services have undergone a deep re-organization guided by: the necessity to reduce exams, to create an environment that helps reduce the virus spread, and to preserve the medical personnel from infection. In these days a re-organization of the endoscopic unit, sited in a high-incidence area, has been adopted, with changes to logistics, work organization and patients selection. With the present manuscript, we want to support gastroenterologists and endoscopists in the organization of a "new" endoscopy unit that responds to the "new" scenario, while remaining fully aware that resources, availability and local circumstances may extremely vary from unit to unit.

The present evidence-based guidelines are focused on the use of device-assisted enteroscopy in the management of small-bowel diseases. A panel of experts selected by the Spanish and Portuguese small bowel study groups reviewed the available evidence focusing on the main indications of this technique, its role in the management algorithm of each indication and on its diagnostic and therapeutic yields. A set of recommendations were issued accordingly.Estas recomendações baseadas na evidência detalham o uso da enteroscopia assistida por dispositivo no manejo clínico das doenças do intestino delgado. Um conjunto de Gastrenterologistas diferenciados em patologia do intestino delgado foi selecionado pelos grupos de estudos Espanhol e Portugués de intestino delgado para rever a evidência disponível sobre as principais indicações desta técnica, o seu papel nos algoritmos de manejo de cada indicação e sobre o seu rendimento diagnóstico e terapêutico. Foi gerado um conjunto de recomendações pelos autores.

Introdução: A amaurose transitória é uma complicação rarapós-cirurgia da coluna vertebral. Tem maior incidência emcirurgias que exigem decúbito ventral. A etiopatogenia é incerta, mas tem sido relacionada com isquemia do nervo óptico, oclusão da artéria central da retina (OACR) e lesão ocular externa. Objetivos: Relatar um caso de amaurose bilateral transitória em uma paciente submetida a tratamento cirúrgico de hérnia discal cervical em decúbito ventral. Relato do caso: JMS, 68 anos, feminina. Dor cervical unilateral e monoradicular no trajeto de C6 há três meses. Exame de RM da coluna cervical demonstrou hérnia discal extrusa no espaço C6-C7 à direita. Foi submetida à cirurgia sob anestesia geral, em decúbito ventral para exérese da hérnia discal cervical. Houve perda sanguínea no ato cirúrgico de 600 ml, sendo reposto durante o procedimento cerca de 300 ml. Duração do ato cirúrgico foi de 185 minutos. No pós-operatóro imediato apresentou perda da acuidade visual bilateral. Ao exame físico não havia sinais de compressão externa dos globos oculares. Exame Fundoscopia: não revelou alterações significantes. No 3º dia de pós-operatório começou apresentar recuperação parcial da acuidade visual e teve melhora total da sua acuidade visual no 16º dia de pós-operatório. Conclusões: Em nosso caso a etiologia provável foi a presença de decúbito ventral prolongado, bem como a perda transitória sanguínea. A profilaxia baseia-se no correto posicionamento do paciente na mesa operatória, hidratação normovolêmica, evitar perda sanguínea abundante no procedimento cirúrgico e redução do tempo anestésico.

Introduction: Spinal compression from unknown primary neoplasms occurs in 5 to 14% in cancer patients. The most common metastasis is secondary to lung, breast and prostate neoplasms. The objective of this study is to describe the clinical characteristics and to evaluate outcomes in patients with spinal compression from unknown primary neoplasms. Methods: We developed a retrospective, observational and descriptive study. Six patients were analyzed according to gender, age, location of injury, treatment and prognosis. These patients were analyzed from January 2008 and July 2011 at Emergency Hospital of Sergipe. Results: Six patients were identified. The median age was 52 years. Male gender was the most affected. The main complaint was pain, followed by motor deficit and sphincter disturbances. The thoracic region was involved in four cases, one cervical and one lumbar. The primary source was lung in three patients, thyroid in one, prostate in one and unknown in one. The CT and MRI were gold standard exams to the diagnosis. Four patients were undergoing decompressive laminectomy, a radiotherapy combined with chemotherapy was performed in three patients and only chemotherapy in two cases. There was death in four cases. Conclusions: Spinal compression can be a late manifestation of primary cancer metastasis. The prognosis of these patients is reserved in several cases due to advanced stage of the primary lesion when the diagnosis is made.

Leukocytoclastic vasculitis is a single-organ, skin-isolated small vessel vasculitis. It can be a side effect of many common drugs, including biological agents. Unlike with other drugs, leukocytoclastic vasculitis induced by biological agents may have a prolonged latency period. We report the first case of ustekinumab-induced leukocytoclastic vasculitis in a patient with inflammatory bowel disease.

Background Conventional colonoscopy is the standard criterion for the diagnosis and staging of colonic disease, including inflammatory bowel disease (IBD). However, it has the risk of complications, including bleeding and perforation. Colon capsule endoscopy (CCE) is a minimally invasive alternative for patients refusing conventional colonoscopy or for whom the latter is contraindicated. However, reading CCE images is a time-consuming task and prone to diagnostic error. Detection of colonic blood is relevant for the diagnosis and assessment of the activity of IBD, particularly ulcerative colitis. An accurate and early diagnosis is essential as it directs subsequent treatment. Our aim was to develop an Artificial Intelligence (AI) algorithm, based on a multilayer Convolutional Neural Network (CNN), for automatic detection of blood and other significant lesions in the colonic lumen in CCE exams: Methods A total of 24 CCE exams (PillCam COLON 2®) from a single centre, performed between 2010–2020, were analysed. From these exams 7640 images (2915 normal mucosa, 3065 blood and 1660 mucosal lesions) were ultimately extracted. Two image datasets were created for CNN training and testing. These images were inserted in a CNN model with transfer of learning. The output provided by the CNN was compared to the classification provided by a consensus of specialists (Figure 1). Performance marks included sensitivity, specificity, positive and negative predictive values (PPV and NPV, respectively), accuracy and area under the receiving operator characteristics curve (AUROC). Results Blood was detected with a sensitivity and specificity of 97.2% and 99.9%, respectively. The AUROC for detection of blood was 1.00 (Figure 2). Detection of other findings had a sensitivity and specificity of 83.7% and 96.7%, respectively. The overall accuracy of the CNN was of 95.4%. Figure 1 - Output obtained from the application of the convolutional neural network. N: normal mucosa; B - blood or hematic residues; ML – mucosal lesions. Figure 2 – Receiver operating characteristic analyses of the network’s performance in the detection of normal mucosa, blood and colon mucosal lesions. AUROC – are under the receiver operating characteristic curve; N – normal colonic mucosa; B – blood; ML – mucosal lesions. Conclusion We developed a pioneer CNN for CCE which demonstrated high levels of efficiency for the automatic detection of blood and lesions with high clinical significance. The development of tools for automatic detection of these lesions may allow for minimization of diagnostic error and the time spent evaluating these exams.

Background Conventional colonoscopy is gold standard for the diagnosis and monitoring of patients with suspected or known inflammatory bowel disease (IBD). Nevertheless, it is a potentially painful procedure with risk of complications, including bleeding and perforation. Colon capsule endoscopy (CCE) is a minimally invasive alternative for patients unwilling to undergo colonoscopy or when it is contraindicated or unfeasible. However, CCE produces thousands of frames and their revision is a time-consuming and monotonous task. The detection of ulcers and erosions is paramount for the diagnosis and assessment of the activity of IBD. However, these lesions may appear in a very small number of frames, thus increasing the risk of overlooking significant lesions. Our aim was to develop an Artificial Intelligence (AI) algorithm, based on a multilayer Convolutional Neural Network (CNN) for automatic detection of ulcers and erosions in CCE exams. Methods A total of 24 CCE exams (PillCam COLON 2®) performed at a single centre between 2010–2020 were analysed. From these exams, 3 635 frames of the colonic mucosa were extracted, 770 containing colonic ulcers or erosions and 2 865 showing normal colonic mucosa. These images were used for construction of training (80% of the frames) and validation (20% of the frames) datasets. For automatic identification of these lesions, these images were inputted in a CNN model with transfer learning. The output provided by the CNN (Figure 1) was compared to the classification provided by a consensus of specialists. Performance marks included sensitivity, specificity, positive and negative predictive values, accuracy and area under the receiving operator characteristics curve (AUROC). Results After the optimization of the neural architecture of the CNN, our model automatically detected colonic ulcers and erosions with a sensitivity of 90.3%, specificity of 98.8% and an accuracy of 97.0% (Figure 2). The AUROC was 0.99 (Figure 3). The mean processing time for the validation dataset was 11s (approximately 66 frames/s). Conclusion We developed a CNN model which demonstrated high levels of efficiency for the automatic detection of ulcers and erosions in CCE images. Our study lays the foundations for the development of effective AI tools for application to CCE exams. These systems may enhance the diagnostic accuracy and reading efficiency of CCE, thus expanding the role of minimally-invasive colonic exploration in the management of IBD patients.

Background Capsule endoscopy (CE) is recommended for the diagnosis and assessment of disease extension in patients with suspected or known inflammatory bowel disease, particularly Crohn’s disease. Ulcers and erosions of the enteric mucosa are prevalent findings in these patients. They frequently occur together, and their identification in CE is crucial for an accurate evaluation of disease severity. Nevertheless, reviewing CE images is a time-consuming task, and the risk of overlooking lesions is significant. Over the last decade, artificial intelligence (AI) has emerged as a mean for overcoming these pitfalls. Of all AI methods, convolutional neural networks (CNN), due to their complex multilayer architecture present the best results in image analysis. We aimed to develop a CNN for the automatic identification of ulcers and erosions in the small bowel mucosa. Methods A total of 1483 CE exams (PillCam SB3®) performed at a single centre between 2015–2020 were analyzed. From these exams, a sum of 11588 frames of the enteric mucosa were obtained, 3163 containing enteric ulcers and erosions, and the remaining containing normal mucosa or other findings. Ulcers and erosions were stratified according to the Saurin’s classification for bleeding potential: P1E – erosions with intermediate bleeding risk; P1U – ulcers with intermediate bleeding risk; P2U – ulcers with high bleeding risk. For automatic identification of these lesions, these images were inserted into an CNN model with transfer learning. Subsequently, the performance of the network assessed using an independent set of images. The output provided by the CNN was compared to the classification provided by a consensus of specialists (Figure 1). Results After optimizing the neural architecture of the algorithm, our model was able to automatically detect and distinguish ulcers and erosions (any bleeding potential) in the small intestine mucosa with an accuracy of 96.7%, precision of 95.9%, sensitivity of 91.7% and a specificity of 97.8% (Figure 1). The mean processing time for the validation dataset was 23 seconds (approximately 101 frames/second). Conclusion We developed and tested a deep learning model based on a CNN for the automatic detection of enteric ulcers and erosions in CE images. Our system revealed extraordinary performance marks. We believe that our study lays the foundation for the development and application of effective AI tools to clinical practice. These techniques should improve diagnostic accuracy and reading efficiency.

Background Capsule endoscopy (CE) plays a central role in the management of patients with suspected or known Crohn’s disease (CD). It is indicated for the diagnosis, classification, monitoring of the response to treatment, and prognostic prediction. In 2017, PillCam™ Crohn’s Capsule (PCC) was introduced. It has demonstrated greater accuracy in detecting and evaluating the extent of lesions in these patients. However, this new tool produces thousands of images, whose revision is time-consuming and prone to errors, since lesions can be restricted to a small number of images. In the last decade, several Artificial Intelligence (AI) algorithms were developed, and demonstrated potential to mitigate some of the drawbacks of CE. Among AI tools, Convolutional Neural Networks (CNN) display the best performance for imagery analysis. This study aims to develop an AI algorithm based on an CNN for the automatic detection of ulcers and erosions of the small intestine and colon in PCC images. Methods A total of 8 085 PCC images were extracted from a single tertiary centre between 2017–2020. This pool of images was constituted by 2 855 images depicting ulcers, 1 975 erosions; the remaining with normal enteric and colonic mucosa. For the automatic identification of these findings, this pool of images was split into training and validation datasets. A CNN model with transfer learning using tensorflow and keras tools was constructed. The performance of the network was subsequently assessed in an independent test set. Results After optimizing the different layers of the CNN, our model was able to detect and distinguish small intestinal or colonic erosions or ulcers with a sensitivity and specificity of 90.0% and 96.0%, respectively. The precision and accuracy of this model were 97.1% and 92.4%, respectively (Figure 1). Particularly, the CNN detected ulcers with a sensitivity of 83% and specificity of 98%, and erosions with sensitivity and specificity of 91% and 93%, respectively. Conclusion Our group developed, for the first time, a CNN capable of automatically detecting ulcers and erosions of the small intestine and colon in PCC images with high sensitivity and specificity. These findings are extremely important since they pave the way for the development of systems for the automatic detection of clinically significant lesions, optimizing diagnostic performance and efficiency of monitoring CD activity.

The broader use of anti-tumor necrosis factor (TNF) agents in inflammatory bowel disease (IBD) has been associated with a high rate of adverse reactions. Dermatological complications are among the most common adverse events. We assessed the incidence, risk factors, management, and outcome of anti-TNF-induced dermatological complications in a large cohort of IBD patients. This was an observational retrospective study at a single tertiary referral center. All consecutive adult IBD patients treated with anti-TNF agents between 2005 and 2015 were identified. Patients who developed at least one dermatological complication while on anti-TNF therapy were included. From the 732 patients treated with anti-TNF agents, 211 (29%) developed at least one dermatological complication: 52% women (mean age of 42 ± 13 years), 85% with Crohn’s disease, 67% were under infliximab. Median follow-up time under anti-TNF therapy was 53 (27–77) months. Dermatological complications recorded were: infections (13.5%), psoriasiform lesions (5.3%), injection/infusion reactions (3.8%), skin cancer (0.5%), and miscellaneous (5.6%). Overall, female gender (OR = 1.658, p = 0.029), smoking (OR = 2.021, p = 0.003), and treatment with an infliximab dose of 10 mg/kg (OR = 2.012, p = 0.007) were independent risk factors for dermatological complications in multivariable analysis. Female gender (OR = 3.63, p = 0.017), smoking (OR = 2.846, p = 0.041), and treatment with adalimumab (OR = 8.894, p

AIM To evaluate the accuracy and best cut-off value of fecal calprotectin (FC) and fecal lactoferrin (FL) to predict disease recurrence in asymptomatic patients presenting with anastomotic strictures. METHODS This was a longitudinal single tertiary center study based on prospectively collected data (recorded in a clinical database created for this purpose) performed between March 2010 and November 2014. Crohn’s disease (CD) patients with anastomotic stricture who submitted to postoperative endoscopic evaluation were included. Stools were collected on the day before bowel cleaning for FC and FL. Endoscopic balloon dilation (EBD) was performed if the patient presented an anastomotic stricture not traversed by the colonoscope, regardless of patients’ symptoms. Successful dilation was defined as passage of the colonoscope through the dilated stricture into the neotermimal ileum. Postoperative recurrence was defined as a modified Rutgeerts score of ≥ i2b. RESULTS In a total of 178 patients who underwent colonoscopy, 58 presented an anastomotic stricture, 86% were asymptomatic, and 48 (54% male; median age of 46.5 years) were successfully dilated. Immediate success rate was 92% and no complications were recorded. FC and FL levels correlated significantly with endoscopic recurrence (P < 0.001) with an optimal cut-off value of 90.85 µg/g (sensitivity of 95.5%, specificity of 69.2%, positive predictive value (PPV) of 72.4%, negative predictive value (NPV) of 94.7% and accuracy of 81%] for FC and of 5.6 µg/g (sensitivity of 77.3%, specificity of 69.2%, PPV of 68%, NPV of 78.4% and accuracy of 72.9%) for FL. CONCLUSION Fecal markers are good predictors of CD endoscopic recurrence in patients with asymptomatic anastomotic stricture. FC and FL may guide the need for EBD in this context.

Smaller endoscopes and catheters have been developed that permit direct visualization of the bile and pancreatic ducts (cholangioscopy and pancreatoscopy, respectively). These endoscopes and catheters are passed through the working channel of a standard therapeutic duodenoscope during endoscopic retrograde cholangiopancreatography (ERCP). The SpyGlass Direct Visualization System (Boston Scientific Corp, Natick, MA, USA) is currently the most widely used and studied device. Cholangioscopy with intraductal lithotripsy has become an established modality in the treatment of difficult biliary lithiasis. When used in the evaluation of indeterminate biliary strictures by experienced endoscopists in recognizing intraductal pathology, it increases the diagnostic yield of tissue sampling. Pancreatoscopy is complementary to other imaging modalities in the evaluation of intraductal papillary mucinous neoplasms of the pancreas and is emerging as a sole or adjunctive therapy to extracorporeal shock wave lithotripsy for the treatment of main pancreatic duct stones. It remains investigational in the diagnosis of pancreatic adenocarcinoma. Complications specific to the performance of cholangiopancreatoscopy include cholangitis, which is related to intraductal fluid irrigation.Abbreviations: EHL: Electrohydraulic lithotripsy; ERCP: Endoscopic retrograde cholangiopancreatography; ESWL: Extracorporeal lithotripsy by shock waves; ET: Endoscopic therapy; EUS: Endoscopic ultrasound; IPMN: intraductal papillary mucinous neoplasm; LL: Laser lithotripsy; MDCT: Multi-detector computed conventional tomography; MPD: Main pancreatic duct; MRCP: Magnetic resonance cholangiopancreatography; MRI: Magnetic resonance imaging; POCPS: Peroral cholangiopancreatoscopy; PSC: Primary sclerosing cholangitis

Background and Aims The histological status of ulcerative colitis [UC] patients in clinical and endoscopic remission has gained space as an important prognostic marker and a key component of disease monitoring. Our main aims were to compare two histological indexes—the continuous Geboes score [GS] and the Robarts Histopathology index [RHI]—regarding their definitions of histological remission and response, and the ability of faecal calprotectin [FC] levels to discriminate between these statuses. Methods This was an analysis of three prospective cohorts including 422 patients previously enrolled in other studies. Results The two continuous scores [GS and RHI] were shown to be significantly correlated [correlation coefficient of 0.806, p < 0.001] and particularly close regarding their definition of histological response: 95% and 88% of all patients classified as having/not having [respectively] histological response according to RHI also did so according to GS. Moreover, median FC levels in patients with histological response were lower than those in patients without histological response [GS: 73.00 vs 525.00, p < 0.001; RHI: 73.50 vs 510.00, p < 0.001]; a similar trend was observed when FC levels of patients in histological remission were compared to those of patients with histological activity [GS: 76.00 vs 228.00, p < 0.001; RHI: 73.50 vs 467.00, p < 0.001]. FC levels allowed us to exclude the absence of histological remission [according to RHI] and absence of histological response [according to RHI and GS], with negative predictive values varying from 82% to 96%. However, optimization of the FC cut-off to exclude the absence of histological remission, as for the continuous GS, falls within values that resemble those of the healthy population. Conclusion The continuous GS and RHI histological scores are strongly correlated in their definitions of histological response. An absence of histological remission could only be excluded at physiological levels of FC.

ObjectiveHistological remission is being increasingly acknowledged as a therapeutic endpoint in patients with UC. The work hereafter described aimed to evaluate the concordance between three histological classification systems—Geboes Score (GS), Nancy Index (NI) and RobartsHistopathologyIndex (RHI), as well as to evaluate their association with the endoscopic outcomes and the faecal calprotectin (FC) levels.DesignBiopsy samples from 377 patients with UC were blindly evaluated using GS, NI and RHI. The results were compared with the patients’ Mayo Endoscopic Score and FC levels.ResultGS, NI and RHI have a good concordance concerning the distinction between patients in histological remission or activity. RHI was particularly close to NI, with 100% of all patients classified as being in remission with NI being identified as such with RHI and 100% of all patients classified as having activity with RHI being identified as such with NI. These scores could also predict the Mayo Endoscopic Score and the FC levels, with their sensitivity and specificity levels depending on the chosen cut-offs. Moreover, higher FC levels were statistically associated with the presence of neutrophils in the epithelium, as well as with ulceration or erosion of the intestinal mucosa.ConclusionsGS, NI and RHI histopathological scoring systems are comparable in what concerns patients’ stratification into histological remission/activity. Additionally, FC levels are increased when neutrophils are present in the epithelium and the intestinal mucosa has erosions or ulcers. The presence of neutrophils in the epithelium is, indeed, the main marker of histological activity.

BACKGROUND Endoscopic recurrence after surgery for Crohn's disease (CD) is high, and it has important prognostic value. Crohn's disease will recur in the majority of patients after surgery. Fecal calprotectin (FC) and lactoferrin (FL) have attracted interest in the postoperative setting for predicting relapse. We have evaluated the accuracy of FC and FL in diagnosing endoscopic recurrence (ER) using the modified Rutgeerts score (MRS) compared with the Rutgeerts score (RS). METHODS A series of consecutive patients who underwent ileocolonic resection for Crohn's disease were evaluated. Biomarkers, clinical indexes, and fecal markers were recorded on the day of ileocolonoscopy. ER was defined as a MRS ≥ i2b or a RS ≥ i2. RESULTS Ninety-nine patients were included in this prospective cohort. The median time between surgery and colonoscopy was 87.5 months (IQR, 31-137). FC and FL levels were higher in patients with ER than in those in remission (Median FC, 196.5 μg/g [IQR, 96-634 μg/g] versus 42.1 μg/g [IQR 19-91.60 μg/g; P < 0.001]; Median FL, 23.27 μg/g [IQR 8.9-47.8 μg/g] versus 2 μg/g [IQR 0.9-7.26 μg/g; P < 0.001]). Using the MRS, 34% of patients presented with ER compared with 76% if the RS was used. The RS performed worse than the MRS with a decrease in sensitivity (74% versus 48% for FC and 85% versus 55% for FL) and in NPV (91% versus 33% for FC, and 90% versus 37% for FL). Furthermore, the accuracy of the MRS was higher than that of the RS (75% versus 55%). CONCLUSIONS Both FC and FL proved to correlate well with endoscopic findings in the evaluation of Crohn's disease after surgery. Both markers predicted recurrence with greater accuracy when the MRS was used. Fecal markers can be used to monitor disease recurrence after intestinal resection, with patients being selected to undergo further endoscopic evaluation.

Background and Aim Immunization against hepatitis B virus (HBV) infection is recommended in patients with inflammatory bowel disease (IBD), particularly in those under immunosuppressive therapy. Limited data are available about IBD patient's response to HBV vaccination. We assessed the response rate to HBV vaccination in IBD patients and evaluated the impact of different factors on the efficacy of HBV vaccination. Methods Anti-HBs titers were measured in a cohort of IBD patients under treatment with infliximab and/or azathioprine. Vaccination was considered efficient when anti-HBs titers were higher than 10 IU/L. Results We have identified 217 patients with IBD under infliximab who were vaccinated for hepatitis B, 172 (79%) with Crohn's Disease and the remaining with ulcerative colitis; 114 patients (53%) were male and mean age was 33 ± 11 years. Overall, HBV vaccine was successful in 164 (76%) patients. Only 14 patients were vaccinated after infliximab was initiated, and only two of them had antibody levels above 10 IU/L. Among the patients that received vaccination before the beginning of infliximab, 88% of those who were vaccinated before starting azathioprine developed antibodies in contrast to 55% who already were under azathioprine. In multivariable analysis, treatment with infliximab (adjusted OR [95% CI]: 17.642 [8.514–33.937]) and with azathioprine (adjusted OR [95% CI]: 3.344 [1.653–9.145]) were the only factors associated with weaker response to HBV vaccination. Conclusion The response rate to the standard HBV vaccination in IBD patients is low mainly in those treated with infliximab and/or azathioprine.

Aims Hepatic granulomas have an estimated prevalence of 5% in liver biopsies, with a wide range of aetiologies globally. Our aim was to assess the clinical relevance, presenting features and underlying aetiology in a non-transplant, tertiary referral centre from a western country. Methods and results This was a retrospective, single-centre review of clinical, laboratory and histological data including all adult patients for whom a liver biopsy was performed from January 1998 to December 2014. A total of 297 cases with hepatic granulomas were found in 9374 biopsies, but 57 were excluded from analysis either because they were lipogranulomas or the biopsy/aetiological work-up had not been performed at our institution. Overall, the most common aetiology was tuberculosis (35.8%), followed by primary biliary cholangitis (PBC) - 15.0%. In 30 patients (12.5%) granulomas were classified as idiopathic. From 1998 to June 2006 there were 147 granulomas in 5304 biopsies (2.8%), a frequency that did not change significantly compared to the period from July 2006 to December 2014 (93 granulomas in 4070 biopsies, 2.3%, P > 0.05). However, for the majority of cases (61.9%) there was a shift in granuloma aetiology during the former time-period that infectious diseases were responsible, whereas in the latter, autoimmune liver diseases (43%) were the main aetiology. In addition, while three cases of drug-induced granulomas were found from 1998 to June 2006, we report two cases in the second time-period. Conclusions Hepatic granulomas can result from various infectious and non-infectious diseases. During recent years, an epidemiological shift regarding granuloma aetiology was observed, from systemic infectious diseases to non-infectious, mainly immune-mediated primary liver disorders. With an appropriate work-up the aetiology can be identified in the vast majority of cases (~90%), rendering its histological identification and characterisation essential, as disease-specific therapies are becoming available.