Digestion最新文献

{"title":"Deep Learning-Based Detection of Malignant Bile Duct Stenosis in Fluoroscopy Images of Endoscopic Retrograde Cholangiopancreatography.","authors":"Kien Vu Trung, Marcus Hollenbach, Gregory Patrick Veldhuizen, Oliver Lester Saldanha, Jakob Garbe, Jonas Rosendahl, Sebastian Krug, Patrick Michl, Jürgen Feisthammel, Thomas Karlas, Jochen Hampe, Albrecht Hoffmeister, Jakob Nikolas Kather","doi":"10.1159/000543049","DOIUrl":"10.1159/000543049","url":null,"abstract":"<p><strong>Introduction: </strong>The accurate distinction between benign and malignant biliary strictures (BSs) poses a significant challenge. Despite the use of bile duct biopsies and brush cytology via endoscopic retrograde cholangiopancreaticography (ERCP), the results remain suboptimal. Single-operator cholangioscopy can enhance the diagnostic yield in BS, but its limited availability and high costs are substantial barriers. Convolutional neural network-based systems may improve the diagnostic process and enhance reproducibility. Therefore, we assessed the feasibility of using deep learning to differentiate BS using fluoroscopy images during ERCP.</p><p><strong>Methods: </strong>We conducted a retrospective review of adult patients (n = 251) from three university centers in Germany (Leipzig, Dresden, Halle) who underwent ERCP. We developed and evaluated a deep learning-based model using fluoroscopy images. The performance of the classifier was evaluated by measuring the area under the receiver operating characteristic curve (AUROC), and we utilized saliency map analyses to understand the decision-making process of the model.</p><p><strong>Results: </strong>In cross-validation experiments, malignant BSs were detected with a mean AUROC of 0.89 ± 0.03. The test set of the Leipzig cohort demonstrated an AUROC of 0.90. In two independent external validation cohorts (Dresden, Halle), the deep learning-based classifier achieved an AUROC of 0.72 and 0.76, respectively. The artificial intelligence model's predictions identified plausible characteristics within the fluoroscopy images.</p><p><strong>Conclusion: </strong>By using a deep learning model, we were able to discriminate malignant BS from benign biliary conditions. The application of artificial intelligence enhances the diagnostic yield of malignant BS and should be validated in a prospective design.</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-16"},"PeriodicalIF":3.0,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142827872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimation of Invasion Depth of Early Colorectal Cancer Using Endoscopic Ultrasonography and Magnifying Chromoendoscopy: A Meta-Analysis.","authors":"Runhua Chen, Yafang Huang, Fusheng Liu","doi":"10.1159/000542620","DOIUrl":"10.1159/000542620","url":null,"abstract":"<p><strong>Introduction: </strong>Magnifying chromoendoscopy (MCE) and endoscopic ultrasonography (EUS) are often used as diagnostic tools to estimate the depth of invasion in early colorectal cancers (CRCs). The aim of this study was to compare MCE with EUS in distinguishing between slight submucosal invasion (invasion depth <1,000 μm) and massively submucosal invasion in patients with early CRCs, since slight submucosal invasion is currently considered as an indication for endoscopic resection and submucosal cancer with massively submucosal invasion should be surgically treated due to an increased risk of lymph node metastasis.</p><p><strong>Methods: </strong>For this meta-analysis, relevant studies were identified from PubMed, Embase, and the Cochrane Library databases between the time of the establishment and April 2023. Data on the yield of tumors were extracted, pooled, and analyzed by STATA15.0 software. The sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio in differentiating massive submucosal invasion from slight submucosal invasion were calculated for both diagnostic modalities.</p><p><strong>Results: </strong>Twenty-six studies involving 12,586 lesions were included: sixteen were studies on MCE and 7 were studies on EUS and 3 were studies on both MCE and EUS. The pooled sensitivity of MCE was 0.78 (95% CI 0.72-0.83), the specificity was 0.95 (0.95% CI 0.91-0.97), the positive likelihood ratio was 15.4 (0.95% CI 8.7-27.4), and the negative likelihood ratio was 0.23 (0.95% CI 0.18-0.30). The pooled sensitivity of EUS was 0.88 (95% CI 0.81-0.93), the specificity was 0.87 (0.95% CI 0.80-0.91), the positive likelihood ratio was 6.7 (0.95% CI 4.4-10.3), and the negative likelihood ratio was 0.13 (0.95% CI 0.08-0.23).</p><p><strong>Conclusion: </strong>The sensitivity tended to be higher in EUS than MCE for early CRCs with massively submucosal invasion, whereas the specificity was significantly lower in EUS than in MCE.</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-19"},"PeriodicalIF":3.0,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142738788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of a Protease Inhibitor Camostat Mesilate on Gut Microbial Function in Patients with Irritable Bowel Syndrome: A Pilot Randomized Placebo-Controlled Study.","authors":"Motoyori Kanazawa, Kentaro Miyamoto, Michiko Kano, Kyoko Inooka, Kentaro Oka, Motomichi Takahashi, Nariyasu Mano, Shin Fukudo","doi":"10.1159/000542758","DOIUrl":"10.1159/000542758","url":null,"abstract":"<p><strong>Introduction: </strong>Increased fecal protease activity, which may induce visceral hypersensitivity, has been observed in patients with irritable bowel syndrome (IBS). Serine proteases modulate FK506 binding protein (FKBP)-type peptidylprolyl cis-trans isomerase (PPIase) activity associated with immune and glucocorticoid receptor functions. The aim was to investigate whether camostat mesilate (CM), a serine protease inhibitor, modifies fecal bacterial function related to FKBP-type PPIases in patients with IBS.</p><p><strong>Methods: </strong>Randomly assigned 16 patients with IBS received 200 mg po tid of CM and 16 patients received placebo for 14 days. Self-reported adequate relief (AR) as a primary endpoint, IBS Symptom Severity Scale (IBS-SSS), and colonic motor and pain thresholds to colorectal distention were assessed before and after treatment. The fecal bacterial content was inferred from 16S rRNA gene sequence data using Phylogenetic Investigation of Communities by Reconstruction of Unobserved States and the Kyoto Encyclopedia of Genes and Genomes database.</p><p><strong>Results: </strong>CM significantly increased the relative abundance of Streptococcus and the functional abundances of serine protease and FKBP-type PPIase FkpA, FklB and SlyD more than placebo after treatment. CM treatment was not superior to placebo in proportion of AR although colonic motor response partially changed.</p><p><strong>Conclusion: </strong>CM modulated the fecal microbiome composition and functional potentials that are related to FKBP-type PPIase activity in IBS patients. These findings suggest that protease inhibitors may modify gut microbial function along with abnormal immunological and/or stress responses that underlie pathophysiology of IBS.</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-12"},"PeriodicalIF":3.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142715455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DYRK2 regulates epithelial-mesenchymal transition restriction in pancreatic cancer liver metastasis by inhibiting Twist.","authors":"Hang Pan, Yin Liu, Kejiu Bao, Yulin Wang, Yuping Zhang, Lina Zhou","doi":"10.1159/000541039","DOIUrl":"https://doi.org/10.1159/000541039","url":null,"abstract":"<p><strong>Objectives: </strong>To explore the underlying variables and molecular pathways leading to pancreatic cancer liver metastasis.</p><p><strong>Methods: </strong>Hs766T and Hs766T-L3 cells were used to create in vitro and in vivo pancreatic cancer liver metastasis models. DYRK2 involvement in pancreatic cancer metastasis was investigated using cell adhesion assays, wound healing assays, and migration and invasion assays. To examine the link between DYRK2 expression and epithelial-mesenchymal transition, Western blot, quantitative real-time PCR, immunofluorescence assays, and immunoprecipitation (IP) were utilized. We found that mice with DYRK2 overexpression had a lower incidence of liver metastasis compared to controls.</p><p><strong>Results: </strong>DYRK2 expression decreased pancreatic cancer tumorigenic activities, including proliferation, migration, and invasion. By analyzing the expression levels of epithelial-mesenchymal transition markers and IP results after overexpressing DYRK2, we found that DYRK2 decreased Twist levels by increasing Twist ubiquitination, thereby inhibiting epithelial-mesenchymal transition.</p><p><strong>Conclusions: </strong>Our findings provide theoretical and experimental support for the ongoing development of DYRK2-based targeted therapies for pancreatic cancer liver metastases.</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-18"},"PeriodicalIF":3.0,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142675321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementation of Machine Learning Algorithms to Screen for Advanced Liver Fibrosis in Metabolic Dysfunction-Associated Steatotic Liver Disease: An In-Depth Explanatory Analysis.","authors":"Shoham Dabbah, Itamar Mishani, Yana Davidov, Ziv Ben Ari","doi":"10.1159/000542241","DOIUrl":"10.1159/000542241","url":null,"abstract":"<p><strong>Introduction: </strong>This study aimed to train machine learning algorithms (MLAs) to detect advanced fibrosis (AF) in metabolic dysfunction-associated steatotic liver disease (MASLD) patients at the level of primary care setting and to explain the predictions to ensure responsible use by clinicians.</p><p><strong>Methods: </strong>Readily available features of 618 MASLD patients followed up at a tertiary center were used to train five MLAs. AF was defined as liver stiffness ≥9.3 kPa, measured via 2-dimension shear wave elastography (n = 495) or liver biopsy ≥F3 (n = 123). MLAs were compared to Fibrosis-4 index (FIB-4) and non-alcoholic fatty liver disease (NAFLD) fibrosis score (NFS) on 540 MASLD patients from the primary care setting as validation. Feature importance, partial dependence, and shapely additive explanations (SHAPs) were utilized for explanation.</p><p><strong>Results: </strong>Extreme gradient boosting (XGBoost) achieved an AUC = 0.91, outperforming FIB-4 (AUC = 0.78) and NFS (AUC = 0.81, both p < 0.05) with specificity = 76% versus 59% and 48% for FIB-4 ≥1.3 and NFS ≥-1.45, respectively (p < 0.05). Its sensitivity (91%) was superior to FIB-4 (79%). XGBoost confidently excluded AF (negative predictive value = 99%) with the highest positive predictive value (31%), superior to FIB-4 and NFS (all p < 0.05). The most important features were HbA1c and gamma glutamyl transpeptidase (GGT) with a steep increase in AF probability at HbA1c >6.5%. The strongest interaction was between AST and age. XGBoost, but not logistic regression, extracted informative patterns from ALT, low-density lipoprotein cholesterol, and alkaline phosphatase (p < 0.001). One-quarter of the false positives (FPs) were correctly reclassified with only one additional false negative based on the SHAP values of GGT, platelets, and ALT which were found to be associated with a FP classification.</p><p><strong>Conclusions: </strong>An explainable XGBoost algorithm was demonstrated superior to FIB-4 and NFS for screening of AF in MASLD patients at the primary care setting. The algorithm also proved safe for use as clinicians can understand the predictions and flag FP classifications.</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-14"},"PeriodicalIF":3.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142497008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Urgent Contrast-Enhanced Computed Tomography before Early Colonoscopy in the Management of Colonic Diverticular Bleeding: A Multicenter Randomized Controlled Trial.","authors":"Yuichiro Hirai, Toshio Uraoka, Michiko Wada, Hideki Mori, Ai Fujimoto, Yuko Sakakibara, Tatsuya Toyokawa, Takashi Kagaya, Yoshihiro Sasaki, Tomohiko Mannami, Toshio Kuwai, Noriko Watanabe, Hiroshige Hamada, Naoki Esaka, Toshihisa Kimura, Hiroyuki Fujii, Yasuo Hosoda, Masaaki Shimada, Hideharu Miyabayashi, Shinichi Somada, Katsuhiro Mabe, Shuji Inoue, Hiroki Saito, Kensuke Furuya, Norio Kawamura, Tomohiro Kudo, Keisuke Hori, Naoto Sakamoto, Mototsugu Kato, Nobuya Higuchi, Naohiko Harada","doi":"10.1159/000541942","DOIUrl":"10.1159/000541942","url":null,"abstract":"<p><strong>Introduction: </strong>Contrast-enhanced computed tomography (CE-CT) has been gaining attention as an initial investigation in the management of colonic diverticular bleeding (CDB), yet the role of CE-CT other than its diagnostic yield has not been adequately clarified. We aimed to determine whether the use of urgent CE-CT improves identification of stigmata of recent hemorrhage (SRH) in subsequently performed early colonoscopy (≤24 h of arrival) or other clinical outcomes of CDB.</p><p><strong>Methods: </strong>We conducted a randomized, open-label, controlled trial at 23 institutions in Japan. Outpatients with suspected CDB were randomly assigned to undergo either urgent CE-CT followed by early colonoscopy (urgent-CE-CT + early-colonoscopy group) or early colonoscopy alone (early-colonoscopy group). The primary outcome was SRH identification. Secondary outcomes included successful endoscopic hemostasis, early (<30 days) and late (<1 year) rebleeding, length of hospital stay, and transfusion requirements.</p><p><strong>Results: </strong>In total, 240 patients, mostly in a hemodynamically stable condition, were randomized. A contrast extravasation on CE-CT was observed in 20 of 115 patients (17.4%) in the urgent-CE-CT + early-colonoscopy group. SRH was identified in 23 of 115 patients (20.0%) in the urgent-CE-CT + early-colonoscopy group and 21 of 118 patients (17.8%) in the early-colonoscopy group (difference, 2.2; 95% confidence interval [CI], -7.9 to 12.3; p = 0.739). Successful endoscopic hemostasis was achieved in 21 patients in each group (18.3% and 17.8%, respectively) (difference, 0.5; 95% CI, -9.4 to 10.4; p = 1.000). There were also no significant differences between groups in early and late rebleeding, length of hospital stay, and transfusion requirements.</p><p><strong>Conclusion: </strong>The use of urgent CE-CT before early colonoscopy did not improve SRH identification or other clinical outcomes in patients with suspected CDB in a hemodynamically stable condition. The routine use of urgent CE-CT as an initial investigation is not recommended in this population, also considering the low rate of extravasation-positive cases (UMIN registry number, UMIN000026865).</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-13"},"PeriodicalIF":3.0,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142460479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Link between Metabolic Syndrome and the Brain.","authors":"Spyridon Zouridis, Ahmad Basil Nasir, Patricia Aspichueta, Wing-Kin Syn","doi":"10.1159/000541696","DOIUrl":"10.1159/000541696","url":null,"abstract":"<p><strong>Background: </strong>Metabolic syndrome (MetS) is a cluster of cardiometabolic conditions that has been linked to high risk for cardiovascular disease, liver complications, and several malignancies. More recently, MetS has been associated with cognitive dysfunction.</p><p><strong>Summary: </strong>Studies have shown an association with minimal cognitive impairment, progression to vascular dementia, and even Alzheimer's disease. MetS components have been individually explored, and glucose intolerance has the strongest association with impairment in several cognitive domains. Several hypotheses have been proposed regarding the pathophysiology underlying the MetS-cognitive dysfunction association, and even though insulin resistance plays a major role, more studies are needed to elucidate this topic. Moreover, several other factors contributing to this association have been identified. Liver disease and more specifically metabolic dysfunction-associated steatotic liver disease can on its own contribute to cognitive decline through systemic inflammation and higher ammonia levels. Gut dysbiosis that has also been identified in MetS can also lead to cognitive impairment through several mechanisms that result in neurotoxicity. Finally, there are several other factors that may modify the MetS-cognitive dysfunction relationship, such as lifestyle, diet, education status, and age. More recently, circadian syndrome was explored and was found to be even more strongly associated with cognitive impairment.</p><p><strong>Key message: </strong>MetS is associated with cognitive decline. Certain cardiometabolic risk factors have a stronger association with cognitive impairment, and there are several factors that may modify this relationship. The aim of this review was to assess and summarize the existing body of evidence on the association between MetS and cognitive impairment and identify areas that necessitate further investigation.</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-9"},"PeriodicalIF":3.0,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142380202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficacy and Safety of Etrasimod in Patients with Ulcerative Colitis in Japan: Data from the Phase 3 ELEVATE UC 12 and ELEVATE UC 40 JAPAN Trials.","authors":"Ken Takeuchi, Tadakazu Hisamatsu, Hiroshi Nakase, Katsuyoshi Matsuoka, Michael Keating, Hirotoshi Yuasa, Motoki Oe, Shoko Arai, Rafal Mazur, Toshifumi Hibi","doi":"10.1159/000541383","DOIUrl":"10.1159/000541383","url":null,"abstract":"<p><strong>Introduction: </strong>Etrasimod is an oral, once-daily (QD), selective sphingosine 1-phosphate (S1P)1,4,5 receptor modulator for the treatment of moderately to severely active ulcerative colitis (UC). Here, we report the primary analysis of a phase 3 trial evaluating the efficacy and safety of etrasimod in patients from Japan with moderately to severely active UC.</p><p><strong>Methods: </strong>Patients from Japan who completed the 12-week ELEVATE UC 12 induction trial could enroll in the 40-week ELEVATE UC 40 JAPAN maintenance trial for a combined 52-week treatment period. Patients in this Japan cohort continued their baseline assigned treatment (etrasimod 2 mg QD or placebo) from ELEVATE UC 12. Efficacy was assessed at week 12 and week 52. Treatment-emergent adverse events (TEAEs) pooled from both trials were assessed up to 52 weeks of exposure.</p><p><strong>Results: </strong>The Japan cohort comprised 32 and 16 patients who received etrasimod and placebo, respectively. A numerically greater proportion of patients who received etrasimod versus placebo achieved clinical remission at week 12 (etrasimod: 14.3%; placebo: 7.1%) and week 52 (etrasimod: 25.0%; placebo: 7.1%); a similar trend was observed for all key secondary efficacy endpoints. TEAEs occurred in 84.4% (27/32) and 62.5% (10/16) of patients who received etrasimod and placebo, respectively. No new safety signals were detected.</p><p><strong>Conclusion: </strong>In these induction and maintenance trials evaluating etrasimod in patients from Japan with UC, numerically higher proportions of patients who received etrasimod versus placebo achieved efficacy endpoints. Efficacy and safety findings were consistent with those from the global ELEVATE UC trial populations.</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-9"},"PeriodicalIF":3.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Intelligence for Contrast-Enhanced Ultrasound of the Liver: A Systematic Review.","authors":"James A Brooks, Michael Kallenbach, Iuliana-Pompilia Radu, Annalisa Berzigotti, Christoph F Dietrich, Jakob N Kather, Tom Luedde, Tobias P Seraphin","doi":"10.1159/000541540","DOIUrl":"10.1159/000541540","url":null,"abstract":"<p><strong>Introduction: </strong>The research field of artificial intelligence (AI) in medicine and especially in gastroenterology is rapidly progressing with the first AI tools entering routine clinical practice, for example, in colorectal cancer screening. Contrast-enhanced ultrasound (CEUS) is a highly reliable, low-risk, and low-cost diagnostic modality for the examination of the liver. However, doctors need many years of training and experience to master this technique and, despite all efforts to standardize CEUS, it is often believed to contain significant interrater variability. As has been shown for endoscopy, AI holds promise to support examiners at all training levels in their decision-making and efficiency.</p><p><strong>Methods: </strong>In this systematic review, we analyzed and compared original research studies applying AI methods to CEUS examinations of the liver published between January 2010 and February 2024. We performed a structured literature search on PubMed, Web of Science, and IEEE. Two independent reviewers screened the articles and subsequently extracted relevant methodological features, e.g., cohort size, validation process, machine learning algorithm used, and indicative performance measures from the included articles.</p><p><strong>Results: </strong>We included 41 studies with most applying AI methods for classification tasks related to focal liver lesions. These included distinguishing benign versus malignant or classifying the entity itself, while a few studies tried to classify tumor grading, microvascular invasion status, or response to transcatheter arterial chemoembolization directly from CEUS. Some articles tried to segment or detect focal liver lesions, while others aimed to predict survival and recurrence after ablation. The majority (25/41) of studies used hand-picked and/or annotated images as data input to their models. We observed mostly good to high reported model performances with accuracies ranging between 58.6% and 98.9%, while noticing a general lack of external validation.</p><p><strong>Conclusion: </strong>Even though multiple proof-of-concept studies for the application of AI methods to CEUS examinations of the liver exist and report high performance, more prospective, externally validated, and multicenter research is needed to bring such algorithms from desk to bedside.</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"1-18"},"PeriodicalIF":3.0,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142307299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characteristics and Prognosis of Sporadic Neoplasias Detected in Patients with Ulcerative Colitis.","authors":"Noriko Yamamoto, Ken Yamashita, Yudai Takehara, Shin Morimoto, Fumiaki Tanino, Yuki Kamigaichi, Hidenori Tanaka, Koji Arihiro, Fumio Shimamoto, Shiro Oka","doi":"10.1159/000537756","DOIUrl":"10.1159/000537756","url":null,"abstract":"<p><strong>Introduction: </strong>Patients with ulcerative colitis (UC) develop not only UC-associated neoplasias but also sporadic neoplasias (SNs). However, few studies have described the characteristics of SNs in patients with UC. Therefore, this study aimed to evaluate the clinical features and prognosis of SNs in patients with UC.</p><p><strong>Methods: </strong>A total of 141 SNs in 59 patients with UC, detected by surveillance colonoscopy at Hiroshima University Hospital between January 1999 and December 2021, were included. SNs were diagnosed based on their location, endoscopic features, and histopathologic findings along with immunohistochemical staining for Ki67 and p53.</p><p><strong>Results: </strong>Of the SNs, 91.5% were diagnosed as adenoma and 8.5% were diagnosed as carcinoma (Tis carcinoma, 3.5%; T1 carcinoma, 5.0%). 61.0% of the SNs were located in the right colon, 31.2% were located in the left colon, and 7.8% were located in the rectum. When classified based on the site of the lesion, 70.9% of SNs occurred outside and 29.1% within the affected area. Of all SNs included, 95.7% were endoscopically resected and 4.3% were surgically resected. Among the 59 patients included, synchronous SNs occurred in 23.7% and metachronous multiple SNs occurred in 40.7% during surveillance. The 5-year cumulative incidence of metachronous multiple SNs was higher in patients with synchronous multiple SNs (54.2%) than in those without synchronous multiple SNs (46.4%).</p><p><strong>Conclusion: </strong>Patients with UC with synchronous multiple SNs are at a higher risk of developing metachronous multiple SNs and may require a closer follow-up by total colonoscopy than patients without synchronous SNs.</p>","PeriodicalId":11315,"journal":{"name":"Digestion","volume":" ","pages":"213-223"},"PeriodicalIF":3.2,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139989597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}