Capsule endoscopy has been widely used as a non-invasive diagnostic tool for small or large intestinal lesions. In recent years, automated lesion detection systems using machine learning have been devised. This study aimed to develop an automated system for capsule endoscopic severity in patients with ulcerative colitis along the entire length of the colon using ResNet50. Capsule endoscopy videos from patients with ulcerative colitis were collected prospectively. Each single examination video file was partitioned into four segments: the cecum and ascending colon, transverse colon, descending and sigmoid colon, and rectum. Fifty still pictures (576 × 576 pixels) were extracted from each partitioned video. A patch (128 × 128 pixels) was trimmed from the still picture at every 32-pixel-strides. A total of 739,021 patch images were manually classified into six categories: 0) Mayo endoscopic subscore (MES) 0, 1) MES1, 2) MES2, 3) MES3, 4) inadequate quality for evaluation, and 5) ileal mucosa. ResNet50, a deep learning framework, was trained using 483,644 datasets and validated using 255,377 independent datasets. In total, 31 capsule endoscopy videos from 22 patients were collected. The accuracy rates of the training and validation datasets were 0.992 and 0.973, respectively. An automated evaluation system for the capsule endoscopic severity of ulcerative colitis was developed. This could be a useful tool for assessing topographic disease activity, thus decreasing the burden of image interpretation on endoscopists.

Background/Aims: Thiopurines are key drugs for inflammatory bowel disease (IBD), including ulcerative colitis (UC) and Crohn’s disease (CD). Recently, NUDT15 polymorphism (R139C, c.415C > T) has been shown to be associated with thiopurineinduced adverse events in Asian populations. In patients with the C/T genotype, low-dose thiopurine treatment is recommended, but its long-term efficacy and tolerability remain unclear. This study aimed to uncover the long-term efficacy and appropriate dosage of thiopurine for IBD patients with the C/T genotype.Methods: A total of 210 patients with IBD (103 UC and 107 CD) determined to have NUDT15 R139C variants were enrolled. Clinical data were retrospectively reviewed from medical records.Results: Of 46 patients (21.9%) with the C/T genotype, 30 patients (65.2%) were treated with thiopurines. Three of whom (10.0%) discontinued thiopurine treatment due to adverse events and 27 of whom continued. The median maintenance dosage of 6-mercaptopurine was 0.25 mg/kg/day (range, 0.19–0.36 mg/kg/day), and 6-thioguanine nucleotides level was 230 (104–298) pmol/8 × 108 red blood cells. Cumulative thiopurine continuation rates for 120 months for patients with the C/C and C/T genotypes were not significantly different (P= 0.895). Cumulative non-relapse rates in the patients with UC treated with thiopurine monotherapy and surgery-free rates in CD patients treated with combination therapy (thiopurines and anti-tumor necrosis factor-α agents) for maintenance remission were not significantly different at 60 months (C/C vs. C/T, P= 0.339 and P= 0.422, respectively).Conclusions: Low-dose thiopurine treatment is an effective and acceptable treatment for patients with C/T genotype.

Surgery avoidance is an important goal in Crohn’s disease (CD) treatment and predicting the risk of subsequent surgery is important to determine adequate therapeutic strength for patients with newly diagnosed CD. Herein, we aimed to construct a prediction model for the risk of subsequent surgery based on disease characteristics at the patients’ initial visit. We retrospectively collected disease characteristic data from 93 patients with newly diagnosed CD. A logistic regression model with a brute force method was used to maximize the area under the receiver operating characteristic curve (auROC) by employing a combination of potential predictors from 14 covariates (16,383). The auROC remained almost constant when one to 12 covariates were considered, reaching a peak of 0.89 at four covariates (small-bowel patency, extensive small-bowel lesions, main lesions, and the number of poor prognostic factors), and it decreased with increasing covariate size. The most significant predictors were small-bowel patency, extensive small-bowel lesions, and age or major lesions. Therefore, this prediction model using covariates may be helpful in determining the likelihood that a patient with newly diagnosed CD will require surgery, which can aid in appropriate treatment selection for high-risk patients.

Recently, the importance of achieving clinical and deep remissions with mucosal healing (MH) has been demonstrated as a therapeutic goal to avoid Crohn’s disease (CD) surgical operations. Although ileocolonoscopy (CS) is considered the gold standard, there are increasing reports on the benefits of capsule endoscopy (CE) and serum leucine-rich α2-glycoprotein (LRG) for evaluating small-bowel lesions in CD. We evaluated the data of 20 patients with CD who underwent CE in our department between July 2020 and June 2021 and whose serum LRG level was measured within 2 months. Concerning the mean LRG value, there was no significant difference between the CS-MH and CS-non-MH groups. Conversely, the mean LRG level was 10.0 μg/mL in seven patients in the CE-MH group and 15.2 μg/mL in 11 patients in the CE-non-MH group with a significant difference between the two groups (p = 0.0025). This study’s findings show that CE can sufficiently determine total MH in most cases, and LRG is useful for evaluating CD small-bowel MH because of its correlation with CE-MH. Furthermore, satisfying CS-MH criteria and a cut-off value of 13.4 μg/mL for LRG suggests its usefulness as a CD small-bowel MH marker, which could be incorporated into the treat-to-target strategy.

Vitamin A ensures intestinal homeostasis, impacting acquired immunity and epithelial barrier function; however, its role in innate immunity is mostly unknown. Here, we studied the impact of vitamin A in different dextran sulfate sodium (DSS)-induced colitis animal models. Interestingly, more severe DSS-induced colitis was observed in vitamin A-deficient (VAD) mice than in vitamin A-sufficient (VAS) mice; the same was observed in VAD severe combined immunodeficient mice lacking T/B cells. Remarkably, IL-1β production, LC3B-II expression, and inflammasome activity in the lamina propria were significantly elevated in VAD mice. Electron microscopy revealed numerous swollen mitochondria with severely disrupted cristae. In vitro, non-canonical inflammasome signaling-induced pyroptosis, LC3B-II and p62 expression, and mitochondrial superoxide levels were increased in murine macrophages (RAW 264.7) pretreated with retinoic acid receptor antagonist (Ro41-5253). These findings suggest that vitamin A plays a crucial role in the efficient fusion of autophagosomes with lysosomes in colitis.

Esophageal endoscopic submucosal dissection (ESD) is considered to be more complex than gastric ESD. This study aimed to assess the physical invasiveness of esophageal ESD during perioperative periods by measuring resting energy expenditure (REE). The factors affecting REE that could be used to identify patients requiring perioperative management were also investigated. Overall, 75 patients who had undergone esophageal ESD were prospectively enrolled. REE, body weight, and basal energy expenditure were measured on the day of and the day following ESD. The mean REE/body weight was 20.2 kcal/kg/day on the day of ESD and significantly increased to 23.0 kcal/kg/day one day after ESD. The stress factor on the day after ESD was 1.11. White blood cell, neutrophil, and C-reactive protein levels increased on the day after ESD and correlated with the changes in REE. Among the factors including age, body mass index, total resection area, operation time, and sarcopenia, only the total resection area was associated with changes in REE. In conclusion, energy metabolism increases during the perioperative period for esophageal ESD. The increase in the stress factor for esophageal ESD was higher than that in gastric and colorectal ESD. Furthermore, patients with large resection areas require greater attention in perioperative management.