Small Intestinal Ulcers Research Articles

Characteristics of chronic enteropathy associated with SLCO2A1 gene (CEAS) in children, a unique type of monogenic very early-onset inflammatory bowel disease

Background Chronic enteropathy associated with SLCO2A1 gene (CEAS) is a unique type of inflammatory bowel disease. CEAS is monogenic disease and is thought to develop from childhood, but studies on pediatric CEAS are scarce. We analyzed characteristics of pediatric CEAS.MethodsEleven patients diagnosed with CEAS at Seoul National University Children’s Hospital were identified and analyzed. Clinical data of patients were collected. Sanger sequencing of SLCO2A1 was performed on all patients.ResultsPatients were diagnosed at a median age of 16.0 years (IQR 11.0 ~ 20.0), and the median age at symptoms onset was only 4.0 years (IQR 2.5 ~ 6.0). Growth delay was observed at the time of diagnosis. Patients showed multiple ulcers or strictures in the small intestine, while the esophagus and colon were unaffected in any patients. Almost half of the patients underwent small intestine resection. The major laboratory features of pediatric CEAS include iron deficiency anemia (IDA), hypoalbuminemia, and near-normal levels of C-reactive protein (CRP). Two novel mutations of SLCO2A1 were identified. The most prevalent symptoms were abdominal pain and pale face. None of the immunomodulatory drugs showed a significant effect on CEAS.ConclusionsPediatric CEAS typically develop from very young age, suggesting it as one type of monogenic very early onset inflammatory bowel disease. CEAS can cause growth delay in children but there is no effective treatment currently. We recommend screening for SLCO2A1 mutations to pediatric patients with chronic IDA from a young age and small intestine ulcers without elevation of CRP levels.

Rapamycin and Starvation Mitigate Indomethacin-Induced Intestinal Damage through Preservation of Lysosomal Vacuolar ATPase Integrity.

Nonsteroidal anti-inflammatory drugs (NSAIDs) possess anti-inflammatory, antipyretic, and analgesic properties and are among the most commonly used drugs. Although the cause of NSAID-induced gastric ulcers is well understood, the mechanism behind small intestinal ulcers remains elusive. In this study, we examined the mechanism through which indomethacin (IM), a prominent NSAID, induces small intestinal ulcers, both in vitro and in vivo. In IEC6 cells, a small intestinal epithelial cell line, IM treatment elevated levels of LC3-II and p62. These expression levels remained unaltered after treatment with chloroquine or bafilomycin, which are vacuolar ATPase (V-ATPase) inhibitors. IM treatment reduced the activity of cathepsin B, a lysosomal protein hydrolytic enzyme, and increased the lysosomal pH. There was a notable increase in subcellular colocalization of LC3 with Lamp2, a lysosome marker, post IM treatment. The increased lysosomal pH and decreased cathepsin B activity were reversed by pretreatment with rapamycin (Rapa) or glucose starvation, both of which stabilize V-ATPase assembly. To validate the in vitro findings in vivo, we established an IM-induced small intestine ulcer mouse model. In this model, we observed multiple ulcerations and heightened inflammation following IM administration. However, pretreatment with Rapa or fasting, which stabilize V-ATPase assembly, mitigated the IM-induced small intestinal ulcers in mice. Coimmunoprecipitation studies demonstrated that IM binds to V-ATPase in vitro and in vivo. These findings suggest that IM induces small intestinal injury through lysosomal dysfunction, likely due to the disassembly of lysosomal V-ATPase caused by direct binding. Moreover, Rapa or starvation can prevent this injury by stabilizing the assembly. SIGNIFICANCE STATEMENT: This study elucidates the largely unknown mechanisms behind small intestinal ulceration induced by indomethacin and reveals the involvement of lysosomal dysfunction via vacuolar ATPase disassembly. The significance lies in identifying potential preventative interventions, such as rapamycin treatment or glucose starvation, offering pivotal insights that extend beyond nonsteroidal anti-inflammatory drugs-induced ulcers to broader gastrointestinal pathologies and treatments, thereby providing a foundation for novel therapeutic strategies aimed at a wide array of gastrointestinal disorders.

LEUCINE-RICH ALPHA 2 GLYCOPROTEIN: A USEFUL BIOMARKER TO DISCRIMINATE SMALL INTESTINAL MUCOSAL HEALING IN C-REACTIVE PROTEIN-NEGATIVE CROHN’S DISEASE

Abstract BACKGROUND The treatment goals for inflammatory bowel disease, including Crohn's disease (CD), have shifted from clinical remission to mucosal healing. However, frequent endoscopies burden patients. Leucine-rich alpha 2 glycoprotein (LRG), produced by hepatocytes, neutrophils, and the intestinal epithelium, is more gut-specific than C-reactive protein (CRP). We examined whether LRG, as a biomarker, can detect small intestinal mucosal healing in CD patients, especially in those who are CRP-negative. METHOD 1) This study examined CD patients who visited our department from May 2021 to April 2023, had LRG measured, and underwent image evaluation using capsule endoscopy or balloon-assisted endoscopy. We analyzed their clinical background, looked for a correlation between LRG and CRP, assessed the ROC-AUC of LRG and CRP for mucosal healing, and measured the LRG and CRP cutoff values to determine mucosal healing. 2) Next, in CRP-negative CD patients, we analyzed the ROC-AUC of LRG for mucosal healing and LRG cutoff value to determine mucosal healing. Endoscopic evaluation was done within 3 months before and after LRG measurement. Absent open ulcers indicated mucosal healing. The upper limit of normal CRP value was <3 mg/L. We used the Spearman correlation coefficient to determine the correlation. RESULTS 1) Here, 67 CD patients were analyzed; 43 (64%) were men. The median age (range) of onset was 25.6 (3-57) years. The median disease duration (range) was 7.6 (0-27) years. B1, B2, and B3 of Montreal Classification were established in 31 (46.2%), 21 (31.3%), and 15 (22.3%) patients, respectively. The median (range) of LRG was 21.7 (7.6-67.4) μg/mL. The median (range) of CRP was 10.8 (0.0-86.9) mg/L. LRG and CRP were strongly correlated (r=0.878, p<0.001). The ROC-AUC of LRG for mucosal healing was 0.839 (95% confidence interval [CI] 0.760-0.918). LRG cutoff value for discriminating mucosal healing was 15.5 μg/mL (sensitivity 77%, specificity 75%). The ROC-AUC of CRP for mucosal healing was 0.811 (95% CI 0.721-0.900). The CRP cutoff value to differentiate mucosal healing was 0.9 mg/L (sensitivity 55%, specificity 90%). 2) Forty CRP-negative CD patients were analyzed; 23 (57%) were men. The median age (range) of onset was 21.9 (3-57) years. The median disease duration (range) was 7.0 (0-27) years. B1, B2, and B3 of Montreal Classification were established in 17 (42.5%), 12 (30.0%), and 11 (27.5%) patients, respectively. The median (range) of LRG was 12.3 (7.6-23.5) μg/mL. The ROC-AUC of LRG for mucosal healing was 0.817 (95% CI 0.696-0.938). The LRG cutoff value to differentiate mucosal healing was 14.1 μg/mL (sensitivity 61%, specificity 76%). CONCLUSION LRG may be a better biomarker than CRP for assessing endoscopic remission of the small intestinal mucosa in CD. In CRP-negative CD patients, LRG level of ≥14.1 μg/mL could indicate small intestinal ulcers.

S3910 Case Report of Paroxysmal Nocturnal Hemoglobinuria and Small Intestinal Ulcers: A Rare Finding With Common GI Symptoms

S3910 Case Report of Paroxysmal Nocturnal Hemoglobinuria and Small Intestinal Ulcers: A Rare Finding With Common GI Symptoms

Tocilizumab-induced mucosal injury in the terminal ileum mimicking intestinal Behçet's disease: A case report.

Tocilizumab, a humanized anti-interleukin-6 (IL-6) receptor monoclonal antibody, is used for the treatment of adult-onset Still disease (AOSD). Despite its efficacy in many clinical situations, concerns have been raised regarding intestinal mucosal injury in patients receiving tocilizumab. A 64-year-old woman with a history of AOSD was admitted to our hospital with hematochezia. She had AOSD for 15 years and underwent treatment with biweekly tocilizumab 9 months prior to admission. Colonoscopy revealed a large punched-out ulcer in the terminal ileum. On pathological evaluation, nonspecific enteritis with lymphocytes and eosinophils were seen. Based on the location and shape of the lesion, we suspected intestinal Behçet's disease. However, the ulcer reduced in size over time by discontinuation of tocilizumab without additional drug treatment, indicating that it was a drug-induced ulcer. The patient was diagnosed with tocilizumab-induced small intestinal ulcer. The patient treated with the discontinuation of tocilizumab. The discontinuation of tocilizumab resulted in ulcer scarring. There was no recurrence of hematochezia. Tocilizumab can cause deep ulcerative lesions in the terminal ileum, which may resemble intestinal Behçet's disease. It is important to continuously monitor abdominal symptoms during tocilizumab therapy and aggressively perform colonoscopy when hematochezia or abdominal pain is observed.

P644 Leucine-rich alpha 2 glycoprotein- A useful biomarker to discriminate small intestinal mucosal healing in asymptomatic CRP-negative Crohn’s disease

Abstract Background The long-term treatment goals for inflammatory bowel disease including Crohn’s disease (CD) have shifted from clinical remission to mucosal healing. However, frequent endoscopies are a great burden on the patients. Leucine-rich alpha 2 glycoprotein (LRG) is produced by hepatocytes, neutrophils, and the intestinal epithelium. Therefore, it is speculated to be more gut-specific than C-reactive protein (CRP) level. This study examined whether LRG could be used as a biomarker to determine the presence or absence of small intestinal mucosal healing in asymptomatic patients with CRP-negative CD. Methods The subjects of this study were asymptomatic CRP-negative CD patients who visited our department from May 2021 to October 2022, had their LRG measured, and underwent imaging evaluation by capsule endoscopy or balloon-assisted endoscopy. We analysed the patients’ clinical background, the ROC-AUC of LRG for mucosal healing, the cut-off value of LRG to discriminate mucosal healing. Endoscopic evaluation was performed within 3 months before and after the LRG measurement. Mucosal healing was defined as the absence of open ulcers. Clinical remission (no subjective symptoms) was defined as a Harvey-Bradshaw index (HBI) ≤4 points. The upper limit of the normal CRP value was set to <3 mg/L. Results A total of 28 cases were analysed; 13 (46%) were men. The median age (range) of onset was 21.2 years (7-52 years). The median disease duration (range) was 6.4 years (0-27). B1 was established in 13 (45%) cases, B2 in 7 (25%) cases and B3 of Montreal Classification in 8 (29%) cases. The median (range) of the HBI score was 2 (0-4). The median (range) of LRG was 12.3 g/ml (7.6-20.5 μg/ml). The ROC-AUC of LRG for mucosal healing was 0.743 (95% confidence interval 0.559-0.927). The cut-off value of LRG for discriminating mucosal healing was 12.2 μg/ml (sensitivity 0.769, specificity 0.682). Conclusion In asymptomatic CRP-negative CD patients, when LRG was 12.2 μg/ml or more, it was suggested that they might have small intestinal ulcers.

Multiple small intestinal ulcers with SLCO2A1 mutation in a Chinese patient.

A 31-year-old man was admitted to our hospital due to recurrent abdominal pain and intermittent melena for 9 years. He also suffered from skin thickening and digital clubbing since adolescence (Fig. 1A and B). He denied intake of non-steroidal, anti-inflammatory drugs. Blood tests revealed normocytic normochromic anemia (hemoglobin, 110 g/dL). Other examinations such as T-SPOT.TB, autoantibody biomarkers, cytomegalovirus, Epstein-Barr virus, and growth hormone level were normal. X-ray showed irregular cortical thickening of the tibiofibular and hand (Fig. 1C).

Application of capsule endoscopy in patients with chronic and recurrent abdominal pain: Abbreviated running title: capsule endoscopy in abdominal pain.

The incidence of chronic and recurrent abdominal pain increases every year, while the diagnosis is still unsatisfactory even after a number of check-ups. This study aimed to evaluate the diagnosis value of capsule endoscopy in patients suffering from chronic and recurrent abdominal pain. A retrospective case study was performed in 80 chronic and recurrent abdominal pain patients at Xiangyang Central Hospital from January 2013 to November 2017. Meanwhile, diagnoses by capsule endoscopy were collected for analysis. Abnormal findings were found in 54 of 80 (67.5%) patients. The findings in chronic and recurrent abdominal pain patients include small intestinal erosion and congestion, small intestinal ulcers, small intestinal parasites, small intestinal vascular malformations, small intestinal polyps, small intestinal diverticulum, and small intestinal lymphangiectasia. There were no immediate significant side effects without being reported up to 1 month after ingestion of the capsule. The capsule was evacuated by all patients. Capsule endoscopy has a great value in the diagnosis of chronic and recurrent abdominal pain with satisfactory safety and less pain for patients. Inflammatory lesions and ulcers in the small intestine account for the majority of positive findings in these patients.

Lactobacillus complex capsules ameliorate aspirin-related small intestinal mucosal injury: a prospective, randomized, controlled clinical trial

Objectives Aspirin can reduce cardiovascular disease risk; however, it can increase the risk of gastrointestinal injury. Lactobacilli have some protective effects; however, there are few studies on their effects on humans. This study investigates the effects of Lactobacillus complex capsule treatment on the aspirin-related small intestinal mucosal injury. Methods This single-center, prospective, randomized controlled clinical trial included 69 patients using enteric-coated aspirin for >1 month between May and December 2019. After baseline magnetically controlled capsule endoscopy (MCCE), patients with aspirin-related small intestinal mucosal injury were randomly assigned (1:1) to receive enteric-coated aspirin and Lactobacillus complex capsules containing a combination of Lactobacillus rhamnosus I, Lactobacillus rhamnosus II, and Enterococcus faecium (probiotics group) or enteric-coated aspirin only (control group) for 2 months. After treatment, the patient underwent MCCE again. The primary outcome was the change in small intestinal mucosal injury scores from baseline to post-intervention. Results Twenty-five patients in the probiotics group and 28 in the control group completed the trial. The decrease in small intestinal mucosal injury scores from baseline to post-intervention was significantly greater in the probiotics group than that in the control group (p < .001). The improvement rates of red spots and erosions in the probiotics group were higher compared with the control group (p = .027 and .022, respectively), and the improvement rate of small intestinal ulcers in the probiotics group was 75.0%; however, there was no improvement in the control group. Conclusion Lactobacillus complex capsules can ameliorate aspirin-related small intestinal mucosal injury.

P156 A multicentric study on the development and application of a deep learning algorithm for automatic detection of ulcers and erosions in the novel PillCam™ Crohn’s capsule

Abstract Background Crohn’s disease has the potential to involve all segments of the gastrointestinal tract, requiring frequent and judicious clinical and endoscopic surveillance. Capsule endoscopy (CE) has revolutionized the management of these patients, playing a role in diagnosis, classification, and assessment of response to treatment. In 2017, PillCam™ Crohn’s Capsule (PCC) was introduced to provide a panenteric assessment to this panenteric disease. However, reviewing each PCC exam is time-consuming and prone to errors as it implies examining thousands of images while significant lesions may only be represented in a small number of frames. Recently, the development of artificial intelligence (AI) algorithms for automatic interpretation of endoscopic images has generated a large interest. The performance of these tools, particularly convolutional neural networks have shown potential to overcome some of the main drawbacks of CE. This multicentric study aims to assess the performance of a deep learning algorithm for the automatic detection of small intestinal and colonic ulcers and erosions in PCC images. Methods We included a total of 59 PCC exams from two centres (ManopH Gastroenterology Clinic and Centro Hospitalar Universitário de São João) performed between 2017 and 2021. A total of 78415 frames were extracted. This pool of images was constituted by 14124 images depicting ulcers and erosions and 64291 with normal enteric and colonic mucosa. For the automatic identification of these findings, this image pool was split into training and validation datasets in a patient-based manner. Therefore, images from the same patient were restricted to a single dataset. A CNN model with transfer learning was developed using tensorflow and keras tools. Results The neural architecture of our CNN was optimized for the detection of enteric and colonic ulcers and erosions. An example of the output provided by the CNN is shown in Figure 1. The deep learning model had a sensitivity of 86.7%, a specificity of 98.6%, a positive predictive value of 92.3% and a negative predictive value of 97.4%. The overall accuracy of our network was 96.6% (Figure 2). At a threshold value of 50%, our CNN had an area under the curve of 0.98 for the detection of ulcers and erosions (Figure 3). Conclusion In this multicentric study, our group has developed a CNN and assessed its performance in a patient-based design, which provides significant robustness to our results. Patient-split analyses are the first step towards real-life application of AI solutions which, allied to the high-performance results of our model, may significantly improve the diagnostic yield of this panendoscopic tool.

NSAID-Induced Enteropathy Affects Regulation of Hepatic Glucose Production by Decreasing GLP-1 Secretion.

Background/Aim: Given their widespread use and their notorious effects on the lining of gut cells, including the enteroendocrine cells, we explored if chronic exposure to non-steroidal anti-inflammatory drugs (NSAIDs) affects metabolic balance in a mouse model of NSAID-induced enteropathy. Method: We administered variable NSAIDs to C57Blk/6J mice through intragastric gavage and measured their energy balance, glucose hemostasis, and GLP-1 levels. We treated them with Exendin-9 and Exendin-4 and ran a euglycemic-hyperinsulinemic clamp. Results: Chronic administration of multiple NSAIDs to C57Blk/6J mice induces ileal ulcerations and weight loss in animals consuming a high-fat diet. Despite losing weight, NSAID-treated mice exhibit no improvement in their glucose tolerance. Furthermore, glucose-stimulated (glucagon-like peptide -1) GLP-1 is significantly attenuated in the NSAID-treated groups. In addition, Exendin-9—a GLP-1 receptor antagonist—worsens glucose tolerance in the control group but not in the NSAID-treated group. Finally, the hyper-insulinemic euglycemic clamp study shows that endogenous glucose production, total glucose disposal, and their associated insulin levels were similar among an ibuprofen-treated group and its control. Exendin-4, a GLP-1 receptor agonist, reduces insulin levels in the ibuprofen group compared to their controls for the same glucose exchange rates. Conclusions: Chronic NSAID use can induce small intestinal ulcerations, which can affect intestinal GLP-1 production, hepatic insulin sensitivity, and consequently, hepatic glucose production.

Meckel\u2019s diverticulum with intraperitoneal hemorrhage in a child detected with screening laparoscopy: a case report

BackgroundThe most common presentation of symptomatic Meckel’s diverticulum (MD) are intestinal obstruction, gastrointestinal hemorrhage, and inflammation of the MD with or without perforation. Intraperitoneal hemorrhage because of MD is extremely rare. We report a case of MD with intraperitoneal hemorrhage in a child detected with screening laparoscopy.Case presentationAn 11-year-old girl presented to another hospital with lower abdominal pain and vomiting that lasted for 2 days. Acute appendicitis was suspected, and she was referred to our department. Abdominal enhanced computed tomography showed an abscess in the lower abdomen with ascites in the pelvis. She was diagnosed with a localized intra-abdominal abscess and the decision was made to treat with antibiotics. However, her abdominal pain worsened, with abdominal distension, tenderness and guarding. She was diagnosed with panperitonitis and the decision was made for surgery 5 h after admission. During surgery, laparoscopic observation from the umbilical region revealed 200 ml of fresh blood throughout the peritoneal cavity, originating from the mesentery of the ileum. MD was observed with bleeding from the surrounding mesentery. Small bowel resection was performed, and the patient was discharged on the 5th postoperative day. Pathological findings revealed an MD containing ectopic gastric mucosa and small intestinal ulcer perforation at the base of the MD.ConclusionsWe report an extremely rare case of an MD with intraperitoneal hemorrhage in a child. In pediatric cases, it is possible that perforation with ectopic gastric mucosa may cause massive bleeding because of rupture of the surrounding mesenteric blood vessels.

Video capsule endoscopy: Initial experience from a tertiary care center in Sri Lanka

Background: Since its global introduction in 2000, capsule endoscopy (CE) has revolutionized the evaluation of small bowel disease. Aims and Objective: The aim of this study was to share our experience with CE including the findings and its diagnostic yield. Materials and Methods: A retrospective study was carried out at Colombo South Teaching Hospital of Sri Lanka. Data of patients who underwent CE from its initiation in 2017 until June 2020 were obtained from the hospital computer database. These included the patient demographics, indications for the study, quality of bowel preparation, and its findings. Results: The study included 54 patients with a mean age of 55 years. Mean gastric time and small bowel transit time were 52 and 272 min, respectively. Forty-five CE studies were done for the evaluation of small bowel bleeding and an abnormal study was found in 26 (57.78%) patients. Small intestinal ulcers and erosions were the most frequently found abnormality (n=16, 35.56%) followed by tumors (n=5, 11.11%). Active bleeding was evident in 14 (31.11%) patients. Overall diagnostic yield was higher in those with a history of overt bleeding (n=15, 71.43%) compared to occult bleeding (n=11, 45.83%). Most patients who were evaluated for abdominal pain and diarrhea had normal CE except for two who had small intestinal ulcers and subepithelial lesions. Only one case was complicated with capsule retention. Conclusion: CE is a useful investigation for the evaluation of small bowel disease, particularly in suspected small bowel bleeding. In contrast to western population, ulcers and erosions were the more frequently found abnormalities seen in local setting.

A treat-to-target approach is needed for Behçet's syndrome.

Treat-to-target (T2T) approach has improved outcomes in chronic diseases. The aim of this review is to discuss the long-term goals and review the evidence for possible targets that would predict the achievement of these goals for developing a T2T strategy for Behçet's syndrome. There are no trials comparing a tight control strategy to standard care in Behçet's syndrome but recent studies suggest better outcomes with earlier use of biologic agents compared with sustained conventional treatment. Fluorescein angiography may be a reliable tool for assessing remission in uveitis as fluorescein angiography findings were shown to predict relapses and long-term visual outcome. Good recanalization on Doppler ultrasonography can be a target for venous involvement as this was the only predictor of relapse. Fecal calprotectin levels were associated with small intestinal and colonic ulcers and may be used as a surrogate for remission of gastrointestinal involvement. There are several new treatment modalities that are tried for Behçet's syndrome and ongoing work on outcome measures for reliable disease assessment. In order to ensure the wise and efficient use of treatment modalities, development and implementation of T2T strategies are needed through multidisciplinary and multinational efforts that include patient research partners.

Efficacy and safety of canakinumab for colchicine-resistant or colchicine-intolerant familial Mediterranean fever: A single-centre observational study.

To evaluate the efficacy and safety of canakinumab in Japanese patients with colchicine-resistant or colchicine-intolerant familial Mediterranean fever (FMF) in a real-world clinical setting. We reviewed 13 Japanese FMF patients to whom canakinumab was introduced during the period of October 2017 to December 2020. All patients were diagnosed as FMF according to Tel-Hashomer criteria. We performed genetic analyses for Mediterranean fever or MEFV by targeted next-generation sequencing. Efficacy was assessed by attack frequency and the percentage of patients who achieved attack improvement at 24 weeks. Safety was assessed by adverse events observed during canakinumab treatment. The median duration and follow-up of canakinumab treatment were 13 and 16 months, respectively. The median attack frequency was 0.50 [0.30-1.00] at 24 weeks, which was a significant decrease from 2.00 [0.85-2.88] at the time of induction (p = .019). There were three patients (23%) with complete resolution of attacks at 24 weeks. No serious adverse events were observed. However, one patient had small intestinal ulceration which led to the discontinuation of canakinumab. Although the number of cases is small, this study suggests that canakinumab is efficacious and safe for use in Japanese patients with colchicine-resistant or colchicine-intolerant FMF in a real-world clinical setting in Japan.

DOP80 Automatic detection of ulcers and erosions in PillCam™ Crohn’s capsule using a convolutional neural network

Abstract 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 Detective Value of Magnetically Controlled Robotic Capsule Endoscopy in Patients With Suspected Small Intestinal Disease.

Objective: To explore the detective value of magnetically controlled robotic capsule endoscopy (MCRCE) in patients with suspected small intestinal disease.Patients and Methods: In total, 1,802 patients with suspected small intestinal disease and negative gastroenteroscopy from Shanghai Jiao Tong University Affiliated Sixth People's Hospital were examined with MCRCE, and the data were collected for further analysis.Results: Among the 1,802 patients who were examined with MCRCE, 974 were diagnosed with small intestinal disease, reaching a positive detection rate of 54.1%. The five most common conditions that were detected include non-specific enteritis in 722 cases (40.1%), small intestinal ulcers in 87 cases (4.8%), abnormal small bowel evacuation in 45 cases (2.5%), small intestinal bleeding in 33 cases (1.8%), and small intestinal yellow spots in 31 cases (1.7%). The running time of the capsules in the small intestine ranged from 85–437 min, with an average of 210.24 ± 89.08 min. No complications, such as intestinal obstruction or capsule retention, were observed in all patients.Conclusion: MCRCE is a safe and non-invasive endoscopic examination with a highly accurate detection rate for small intestinal diseases.

A narrative review of recent progress and current perspectives on video capsule endoscopy

: Since its introduction in 2000, capsule endoscopy (CE) has undergone various improvements, with several CE types currently available across the globe. This review focuses on the current status and expected future developments in small-bowel CE (SBCE) and colon CE (CCE). In addition to the demonstrated efficacy of SBCE in identifying the source of bleeding in obscure gastrointestinal bleeding (OGIB), the advent of patency capsules allowed the use of SBCE as a feasible option in patients with Crohn’s disease (CD), with several studies demonstrating the efficacy of SBCE in assessing CD activity. Following its first use in 2006, second-generation CCEs with the adaptive frame rate function, which automatically recognizes the movement speed of the capsule and accelerates the frame rate, are currently used worldwide. The utility of CCE in detecting colorectal polyps and assessing disease activity in ulcerative colitis (UC) has been reported. Recent efforts are focused on the development in artificial intelligence-based reading systems for CE images. Although there are currently few commercially available systems, several convolutional neural network-based models have been reported to detect small intestinal mucosal disorders, including erosions and ulcers, angioectasia, blood, polyps, celiac disease, and parasites. Further research is expected to reduce the burden of reading CE images on clinicians.

Development of a Convolutional Neural Network for Detection of Erosions and Ulcers With Distinct Bleeding Potential in Capsule Endoscopy

Background and aimsThe 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. MethodsA 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. ResultsOverall, 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. ConclusionOur 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.

A protective effect of acetaminophen on ibuprofen-induced small intestinal damage in rats via the suppression of MMP-13

Capsule endoscopy has revealed that nonsteroidal anti-inflammatory drugs may cause damage not only to the stomach but also to the small intestine, which has become one of the most serious issues in gastroenterology. However, few studies have reported the effect of ibuprofen (IBP), which is widely prescribed worldwide, on the small intestine, and it remains unclear whether IBP can cause small intestinal damage. We have previously shown that acetaminophen (APAP), which is used as an antipyretic/analgesic drug, inhibits IBP-induced gastric damage by suppressing matrix metalloprotease-13 (MMP-13) gene expression. In this study, we investigated the ability of IBP to induce small intestinal damage and the efficacy of APAP against IBP-induced small intestinal damage in rats. Nonfasted male Sprague-Dawley rats were orally administered with IBP (200mg/kg) and then euthanized at various time points (0, 4, 8, 16, and 24h) after the administration. The small intestine, jejunum, and ileum were removed, and intestinal lesions were measured. To elucidate the efficacy of APAP against IBP-induced small intestinal damage, the rats were treated with IBP (200mg/kg) with or without APAP (200mg/kg), and small intestinal damage was evaluated 24h after the administration. Moreover, the expression levels of GAPDH, TNFα, iNOS, and MMP-13 genes were determined at various time points (8, 16, and 24h) by RT-qPCR. The oral administration of IBP induced obvious small intestinal damage, which was found to be significant at 24h (p<0.05 vs 0h, Dunnett's test). The coadministration of APAP significantly prevented IBP-induced damage (p<0.05, Student's t-test). In addition, the expression levels of TNFα and iNOS genes were significantly increased by IBP (p<0.01 and p<0.05 vs. vehicle, respectively, Tukey-Kramer test), whereas the cotreatment with APAP suppressed the increases at 8h. Moreover, compared with the vehicle, the IBP treatment significantly increased the expression level of the MMP-13 gene (p<0.01) at each time point (8, 16, and 24h, Tukey-Kramer test), whereas the APAP cotreatment significantly suppressed the increase (p<0.01 vs. IBP at 8h, p<0.05 vs. IBP at 16 and 24h, Tukey-Kramer test). This study suggested that a single administration of IBP was associated with the risk of inducing small intestinal ulcers in rats, and APAP could prevent IBP-induced small intestinal damage by suppressing the MMP-13 gene expression.