Development of an Artificial Intelligence Diagnostic System Using Linked Color Imaging for Barrett's Esophagus.

Background: Barrett's esophagus and esophageal adenocarcinoma cases are increasing as gastroesophageal reflux disease increases. Using artificial intelligence (AI) and linked color imaging (LCI), our aim was to establish a method of diagnosis for short-segment Barrett's esophagus (SSBE). Methods: We retrospectively selected 624 consecutive patients in total at our hospital, treated between May 2017 and March 2020, who experienced an esophagogastroduodenoscopy with white light imaging (WLI) and LCI. Images were randomly chosen as data for learning from WLI: 542 (SSBE+/- 348/194) of 696 (SSBE+/- 444/252); and LCI: 643 (SSBE+/- 446/197) of 805 (SSBE+/- 543/262). Using a Vision Transformer (Vit-B/16-384) to diagnose SSBE, we established two AI systems for WLI and LCI. Finally, 126 WLI (SSBE+/- 77/49) and 137 LCI (SSBE+/- 81/56) images were used for verification purposes. The accuracy of six endoscopists in making diagnoses was compared to that of AI. Results: Study participants were 68.2 ± 12.3 years, M/F 330/294, SSBE+/- 409/215. The accuracy/sensitivity/specificity (%) of AI were 84.1/89.6/75.5 for WLI and 90.5/90.1/91.1/for LCI, and those of experts and trainees were 88.6/88.7/88.4, 85.7/87.0/83.7 for WLI and 93.4/92.6/94.6, 84.7/88.1/79.8 for LCI, respectively. Conclusions: Using AI to diagnose SSBE was similar in accuracy to using a specialist. Our finding may aid the diagnosis of SSBE in the clinic.

Risk Factors for Mucosal Redness in the Duodenal Bulb as Detected via Linked Color Imaging.

Linked color imaging (LCI) for image-enhanced endoscopy (IEE) highlights mucosal color differences. We investigated risk factors associated with mucosal redness of the duodenal bulb using LCI. Consecutive patients were retrospectively selected after their duodenal bulbs were observed via LCI. A symptom questionnaire (Izumo scale) was completed. The LCI of the duodenal bulb was subjectively evaluated on whether redness was present and objectively evaluated based on L* a* b* color values. The clinical characteristics of the 302 study participants were: male/female, 120/182; mean age, 70.9 years. Twenty-one cases (7.0%) were in the redness (+) group. After multiple regression analysis, independent predictors for the red component (a*) of the duodenal bulb using LCI were: age (ß = -0.154, p < 0.01), female (ß = -0.129, p < 0.05), body mass index (BMI; ß = -0.136, p < 0.05), Helicobacter pylori eradication (ß = 0.137, p < 0.05), endoscopic gastric mucosal atrophy score (EGAS; ß = -0.149, p < 0.05), and constipation-related quality of life (QOL) (ß = -0.122, p < 0.05) scores. Lower age, lower BMI, lower EGAS, a constipation-related QOL score, post-H. pylori eradication, and being male were associated with mucosal redness in the duodenal bulb with IEE using LCI.

Endoscopic Diagnosis Strategy of Raspberry-Shaped Gastric Lesion in Helicobacter Pylori-Uninfected Patient.

OBJECTIVES: We aimed to clarify the endoscopic and clinicopathological features of raspberry-shaped gastric lesions (RSGLs) and to establish an endoscopic diagnostic algorithm for RSGLs. METHODS: We collected RSGLs from an endoscopic database at our hospital between May 2009 and August 2021. All RSGLs were histopathologically classified and compared based on their endoscopic and clinicopathological characteristics. RESULTS: Sixty-five RSGLs in 54 patients were classified into five histopathological types: gastric adenocarcinoma of foveolar type (GA-FV, n = 43), gastric adenocarcinoma of fundic-gland type (GA-FG, n = 2), gastric adenocarcinoma of fundic-gland mucosa type (GA-FGM, n = 4), hyperplastic polyp (HP, n = 12), and proton pump inhibitor-related lesion (PPI-L, n = 4). All RSGLs exhibited polygonal or curved marginal crypt epithelium (MCE). GA-FV lesions had homogenously reddish (95%) and an irregular microvascular (MV) pattern (91%). GA-FG lesions were heterogeneously reddish with a submucosal tumor shape (100%) and had a regular MV pattern (50%). GA-FGM lesions were homogen+ously reddish (75%) and occasionally had a submucosal tumor shape (50%) with an irregular MV pattern (75%). HPs and PPI-Ls were homogeneously reddish (93%), with linear or dotted MCE (81%) and a regular MV pattern (100%). CONCLUSION: Our diagnostic algorithm for RSGLs constructed using endoscopic features might be useful for the endoscopic differential diagnosis of RSGLs.

Comparison of Texture and Color Enhancement Imaging with White Light Imaging in 52 Patients with Short-Segment Barrett's Esophagus.

BACKGROUND Texture and color enhancement imaging (TXI), a new type of image-enhanced endoscopy, may improve the detection of gastrointestinal lesions. Barrett's esophagus (BE) requires an accurate diagnosis since it may undergo neoplastic transformation. We aimed to evaluate the usefulness of TXI compared with white light imaging (WLI) in BE. MATERIAL AND METHODS In this prospective study at a single hospital from February 2021 to February 2022, we enrolled 52 consecutive patients with BE. Endoscopic images of BE using WLI, TXI mode 1 (TXI-1), TXI mode 2 (TXI-2), and narrow-band imaging (NBI) were compared by 10 endoscopists (5 experts and 5 trainees). Endoscopists scored visibility for the images as follows: 5 (improved), 4 (somewhat improved), 3 (equivalent), 2 (somewhat decreased), and 1 (decreased). Total visibility scores for all 10 endoscopists, and subgroups composed of the 5 expert endoscopists and the 5 trainee endoscopists, were evaluated. Main-group (10 endoscopists) scores of ≥40, 21-39, and ≤20, and subgroup (5 endoscopists) scores of ≥20, 11-19, and ≤10, were considered "improved", "equivalent", and "decreased", respectively. Inter-rater reliability (intra-class correlation coefficient [ICC]) was calculated and images were objectively assessed based on L*a*b* color values and color differences (ΔE*). RESULTS All 52 cases were diagnosed as short-segment BE (SSBE). TXI-1/TXI-2 improved visibility compared with WLI was: 78.8%/32.7% for all endoscopists; 82.7%/40.4% for trainees; and 76.9%/34.6% for experts. NBI did not improve visibility. The ICC for TXI-1 and TXI-2 compared with WLI was "excellent" for all endoscopists. The ΔE* between esophageal and Barrett's mucosae, and between Barrett's and gastric mucosae, was higher for TXI-1 than for WLI (P<0.01, P<0.05, respectively). CONCLUSIONS TXI, especially TXI-1, improves the endoscopic diagnosis of SSBE compared with WLI, regardless of the endoscopist's skill.

Gastric Juvenile Polyposis with Intramucosal Cancer Diagnosed by Magnifying Endoscopy with Narrow-band Imaging.

Although gastric juvenile polyposis (GJP) often coexists with gastric cancer, a preoperative accurate diagnosis is still difficult to obtain. A 70-year-old woman was referred for epigastralgia and anemia. Esophagogastroduodenoscopy with a conventional endoscope showed numerous gastric polyps with no cancerous findings. Magnifying endoscopy with narrow-band imaging (M-NBI) showed cancerous findings, and a target biopsy revealed adenocarcinoma. Histopathological findings after endoscopic resection confirmed a diagnosis of juvenile polyposis with intramucosal adenocarcinoma. Genetic analyses revealed a germline pathogenic variant of SMAD4. A target biopsy using M-NBI and endoscopic resection proved useful for confirming the preoperative diagnosis of coexisting cancerous lesions in GJP.

Correlation between Constipation Symptoms and Abdominal CT Imaging: A Cross-Sectional Pilot Study.

Evaluation of chronic constipation is important, although it is often difficult to satisfactorily treat due to the complex interplay of factors. This study aimed to determine whether the volume of intraluminal contents and lateral diameter of the colon measured from computed tomography (CT) images were correlated with the symptoms of chronic constipation and stool consistency. Consecutive patients who underwent the Constipation Scoring System (CSS), Bristol Stool Form Scale (BSFS) questionnaires and simple abdominal CT were selected retrospectively. The intestinal tract diameter at each site was measured, and the amounts of stool and gas in the intestinal tract were evaluated at five levels. Of the 149 study participants, 54 were males and 95 were females and their mean age was 72.1 years. In the right hemi-colon, CSS5 (Time) correlated significantly with gas volume (p < 0.01). In the left hemi-colon, stool volume correlated significantly with CSS2 (Difficulty), CSS3 (Completeness), CSS5 (Time) and CSS total (p < 0.05). The BSFS negatively correlated with gas volume and diameter in the right hemi-colon and with gas volume in the rectum (p < 0.05). CT findings including stool volume, gas volume and diameter correlated with some constipation symptoms and stool consistency. These findings may be useful in evaluating and treating constipation.

Mediastinal Thoracic Duct Cyst Infection after Endoscopic Submucosal Dissection for Early Esophageal Cancer.

A mediastinal thoracic duct cyst that originates from the thoracic duct is a very rare disease in the mediastinum. There have been no reports of mediastinal thoracic duct cyst infection caused by endoscopic treatment. This is the first case of mediastinal thoracic duct cyst infection after endoscopic submucosal dissection for early esophageal cancer. We herein report a 75-year-old man with mediastinal thoracic duct cyst infection caused by esophageal endoscopic submucosal dissection. In cases where a mediastinal thoracic duct cyst is found before performing endoscopic esophageal treatment, we should carefully consider the potential risk of post-treatment cyst infection.

Yersinia enterocolitica Enteritis Diagnosed with Erythema Nodosum.

We herein report a rare case of Yersinia enterocolitica enteritis with a fever and abdominal pain followed by erythema nodosum (EN) a few days later. The diagnosis was confirmed based on characteristic colonoscopy and computed tomography findings, pathology, and mucosal culture. Yersinia enteritis is a curable disease provided a proper diagnosis and treatment are performed. Although EN is a rare clinical course, it should still be considered as a differential diagnosis.

Endoscopic Features of Gastric Epithelial Neoplasm of Fundic Gland Mucosa Lineage.

The endoscopic features of gastric epithelial neoplasms of fundic gland mucosa lineage (GEN-FGML) have not been well investigated. We aimed to clarify the endoscopic features of GEN-FGML and differences between gastric adenocarcinoma of the fundic gland type (GA-FG) and fundic gland mucosa type (GA-FGM). A total of 62 GEN-FGML lesions, including 52 GA-FG and 10 GA-FGM, were retrospectively analyzed using endoscopic and clinicopathological findings to provide information of diagnostic value using white light imaging (WLI) and magnifying endoscopy with narrow-band imaging (M-NBI). GA-FG frequently presented with a whitish, submucosal tumor (SMT) shape with dilated vessels with branching architecture and background mucosa without atrophic change in WLI, an indistinct demarcation line (DL), dilatation of the crypt opening and intervening part (IP), and microvessels without distinct irregularity in M-NBI. GA-FGM frequently presented as a reddish, elevated lesion in WLI, with a distinct DL, dilatation of the IP, and an irregular microvascular pattern in M-NBI. As for an M-NBI diagnosis, five GA-FGM lesions met the diagnostic criteria for cancer, whereas none of the GA-FG lesions met the same criteria. We highlight the endoscopic features of GEN-FGML, and the differentiation between GA-FG and GA-FGM might be possible by combination of lesion color and morphology in WLI and M-NBI diagnoses.

Comparison of the Degree of Gastric Mucosal Injury between Patients Who Are Receiving Dual Antiplatelet Therapy or Single Antiplatelet Therapy.

BACKGROUND: Patients taking low-dose aspirin have a higher incidence of gastroduodenal ulcers and higher risk of upper gastrointestinal bleeding than patients who do not. Thienopyridine antiplatelet agents may similarly cause bleeding gastroduodenal erosions and ulcers. The incidence of gastrointestinal bleeding is reported to be higher when these antithrombotic drugs are used in combination. Until now, most studies have focused on bleeding, and no study has compared the degree of gastric mucosal injury between patients receiving dual antiplatelet therapy (DAPT) and those receiving single antiplatelet therapy (SAPT) in real-world clinical practice. AIM: Our objective was to compare the degree of gastric mucosal injury in patients taking low-dose aspirin in combination with clopidogrel (one of the thienopyridine antiplatelet agents) with that of patients who were taking aspirin or clopidogrel as a single agent. METHODS: Patients who were taking aspirin and/or clopidogrel and who underwent scheduled esophagogastroduodenoscopy between April 2015 and March 2020 were enrolled in this study. Endoscopic images were reviewed retrospectively, and the degree of gastric mucosal injury was assessed with the modified Lanza score (m-Lanza score). The m-Lanza score was compared between DAPT patients taking aspirin and clopidogrel and SAPT patients taking either aspirin alone or clopidogrel alone. RESULTS: The m-Lanza scores of the DAPT group, the aspirin group, and the clopidogrel group were 1.67 ± 1.81 (mean ± standard deviation), 0.95 ± 1.61, and 0.72 ± 1.29, respectively. The m-Lanza score of the DAPT group tended to be higher than that of the aspirin group (p = 0.06) and was significantly higher than that of the clopidogrel group (p = 0.03). CONCLUSION: The degree of gastric mucosal injury in DAPT patients was significantly higher than that in patients using clopidogrel alone and tended to be higher than that in patients using aspirin alone in real-world clinical practice.

Association between bile area in the duodenal bulb and abdominal symptoms: Quantitative analysis using blue laser imaging.

Bile acids are strongly associated with the pathogenesis of functional gastrointestinal diseases. In recent years, blue laser imaging (BLI) endoscopy has emerged as a novel image-enhanced endoscopic method, which illustrates bile as a reddish hue. The present study investigated the factors that affect the area of bile in duodenal bulbs using BLI. For this purpose, patients (356 cases) who underwent upper endoscopy with BLI between April, 2017 and December, 2019, and completed patient background and symptom questionnaires [Constipation Scoring System (CSS), Bristol Stool Form Scale (BSFS) and Frequency Scale for Symptoms of gastroesophageal reflux disease (FSSG)], were retrospectively investigated. Each BLI bile score was calculated as a percentage of bile area in a field of view in the duodenal bulb using a KS400 image analysis system, and the association with abdominal symptoms was examined using multiple regression analysis. The patient characteristics included the following: Age (in years), 69.9±11.3; male/female ratio, 146/210; body mass index, 23.0±3.8; reflux esophagitis (M/A/B/C), 143/19/3/3; atrophic gastritis (C-0/C1-3/O1-3), 132/100/124; proton pump inhibitor potassium competitive acid blocker/aspirin/ursodeoxycholic acid/gall bladder stones/cholecystectomy, 105/27/18/43/18; BLI bile score, 7.10 (±14.34); CSS score, 3.55 (±3.80); BSFS score, 3.91 (±1.02); and FSSG score, 4.80 (±5.76). Correlation coefficients (P<0.05) for the BLI bile score were found for cholecystectomy (Rho=0.137) and aspirin use (Rho=0.118). In multiple regression analysis, independent predictors of the BLI bile score were cholecystectomy [standardized partial regression coefficient (ß)=0.169, P=0.001] and the BSFS score (ß=0.107, P=0.042). On the whole, the present study demonstrates that the duodenal bile area in BLI upper endoscopy is associated with cholecystectomy and fecal characteristics.

Clinicopathological and molecular characterization of early gastric adenocarcinoma in Helicobacter pylori-uninfected patients: emphasis on differentiated gastric adenocarcinoma.

BACKGROUND: Recently, Helicobacter pylori (HP)-uninfected gastric mucosal cancer has been reported; however, the clinicopathological and molecular features of HP-uninfected gastric cancer have not been elucidated. METHODS: We evaluated the clinicopathological, immunohistochemical, and genetic alterations in HP-uninfected early gastric adenocarcinoma using next-generation sequencing (NGS). RESULTS: Among 968 primary early gastric carcinomas, 64 (6.6%) were HP-uninfected gastric adenocarcinoma and were pathologically classified as gastric adenocarcinoma of fundic-gland type (GA-FG, n = 39), differentiated gastric adenocarcinoma (DGA, n = 16), and signet-ring cell carcinoma (SRCC, n = 9). Based on the expression profile of the mucin core protein, DGAs were classified into a gastrointestinal phenotype showing either MUC5AC or MUC6 expression and MUC2 or CD10 expression simultaneously (n = 5), and a gastric phenotype (n = 11) showing either MUC5AC or MUC6 expression. All DGAs with a gastrointestinal phenotype shared similar endoscopic characteristics, such as reddish depressed lesions in the antrum. In contrast, DGAs with a gastric phenotype exhibited several distinct endoscopic features, including a raspberry-shaped appearance and whitish flat-elevated appearance; the former expressed only MUC5AC and the latter exhibited co-expression of MUC5AC and MUC6. Among 16 HP-uninfected DGAs, seven were subjected to NGS. APC was recurrently mutated in DGA (42.9%) and was enriched in DGAs with a gastrointestinal phenotype (75%). CONCLUSIONS: Overall, HP-uninfected gastric adenocarcinomas showed distinct clinicopathologic and endoscopic characteristics. Furthermore, HP-uninfected DGAs, especially those with a gastrointestinal phenotype, may be characterized by recurrent APC mutations.

The relationship between Helicobacter pylori infection and reflux esophagitis and the long-term effects of eradication of Helicobacter pylori on reflux esophagitis.

INTRODUCTION: Whether the incidence of reflux esophagitis (RE) increases after the eradication of Helicobacter pylori (H. pylori) is controversial. Few reports have evaluated the presence or absence of RE after a long period of time, taking into account the degree of atrophy and/or administration of acid secretion inhibitors. We investigated the relationship between H. pylori and RE taking into account these factors. METHODS: This was a retrospective cohort study with approval by the Ethics Committee. Patients who succeeded in H. pylori eradication treatment, and in whom there were images of the gastroesophageal junction on endoscopic examinations within 1 year before eradication treatment and more than 3 years after eradication were included. The degrees of RE and atrophy were retrospectively determined from the endoscopic images. The prevalence of RE before and after eradication and the incidence of newly developed RE after eradication between patients with or without atrophy improvement were compared using Fisher's exact test. RESULTS: A total of 185 cases (male:female = 104:81; mean age, 63.5 years; mean observation period, 6.4 years) were examined. The prevalence of RE before and after eradication was 1.6% (3/185) and 7.0% (13/185), respectively (P = 0.019). RE was present in 8 (7.5%) of 106 cases with closed-type atrophy and in 5 (6.3%) of 79 cases with open-type atrophy after eradication (P = 0.75). Atrophy improved after eradication in 56 cases, of whom 4 (7.1%) had new onset of RE; the degree of atrophy did not improve in 126 cases, of whom 7 (5.4%) had new onset of RE (P = 0.74). There was no difference between the percentage of cases who took acid secretion inhibitors before and after eradication (P = 0.14). CONCLUSION: The prevalence of RE increased a long time after eradication, even in patients who were taking an acid secretion inhibitor. The prevalence of RE was not related to the degree of atrophy or change in atrophy.

Endoscopic findings of Helicobacter pylori gastritis in children and young adults based on the Kyoto classification of gastritis and age-associated changes.

BACKGROUND AND AIM: We aimed to evaluate endoscopic findings of Helicobacter pylori (H. pylori)-positive children and young adults based on the Kyoto classification, and to examine if there are age-associated changes in H. pylori-positive gastritis. METHODS: H. pylori-positive patients under 40 years old who underwent upper gastrointestinal endoscopy from 1 April 2009 to 15 February 2017 were included. Subjects were classified into the Pediatric (<20 years) and Young adult groups (20-39 years). The patients' endoscopic photographs were retrospectively re-evaluated based on the Kyoto classification. We compared endoscopic findings between the two groups and examined alterations in the findings of H. pylori-associated gastritis in 5-year age groups. RESULTS: Forty-three and 163 subjects were classified into the Pediatric and Young adult groups, respectively. In the Pediatric group, nodularity was seen in the majority (93.0%); other endoscopic findings in order of decreasing frequency included mucosal swelling (32.6%), spotty redness (25.6%), diffuse redness (18.6%), and atrophy (9.3%). In the Young adult group, endoscopic findings included atrophy (66.9%), mucosal swelling (49.7%), spotty redness (39.3%), nodularity (31.9%), and diffuse redness (30.3%). The difference in prevalence of nodularity or atrophy between the two groups reached statistical significance (P < 0.0001 each). The rate of nodularity decreased with increasing age in the Young adult group. The rate of atrophy was 33% in young adult patients aged 20-24, and the rate increased to >65% in patients over age 25. CONCLUSION: H. pylori-positive children had endoscopic findings besides nodularity based on the Kyoto classification. The prevalence of atrophy increased in patients over age 20.

miR-33a-5p in small extracellular vesicles as non-invasive biomarker for oxaliplatin sensitivity in human colorectal cancer cells.

microRNAs (miRNAs) contained in small extracellular vesicles (sEVs) are candidates for non-invasive biomarkers. Oxaliplatin (L-OHP) has been approved for advanced colorectal cancer (CRC) chemotherapy. However, the response to L-OHP differs among CRC patients. In addition, CRC cells often acquire the resistance to L-OHP. This study aimed at the prediction of L-OHP sensitivity by measuring extracellular miRNAs levels. Firstly, we compared intracellular miRNAs expressions in L-OHP-sensitive CRC cells (SW620 and HCT116 cells) with those in acquired and intrinsic L-OHP-resistant cells. In microarray and real-time RT-PCR analyses, the intracellular miR-33a-5p, miR-210-3p, and miR-224-5p expressions were lower in acquired and intrinsic L-OHP-resistant CRC cells than sensitive cells. Furthermore, in SW620 cells, L-OHP sensitivity was decreased by miR-33a-5p inhibitor. On the other hand, miR-210-3p or miR-224-5p inhibitor did not affect L-OHP sensitivity in SW620 cells. Secondly, the amount of miR-33a-5p, miR-210-3p, and miR-224-5p in sEVs was compared. The amount of miR-33a-5p and miR-210-3p in sEVs secreted from acquired and intrinsic L-OHP-resistant cells tended to be small. miR-224-5p was not detected in sEVs secreted from three types of CRC cells examined. To the best of our knowledge, this is the first study demonstrating that miR-33a-5p and/or miR-210-3p in sEVs would be candidates for biomarkers of L-OHP sensitivity. In particular, miR-33a-5p is a promising candidate because it would be directly involved in L-OHP sensitivity.

Dynamic diagnosis of early gastric cancer with microvascular blood flow rate using magnifying endoscopy (with video): A pilot study.

BACKGROUND AND AIM: Magnifying endoscopy (ME) diagnostic algorithm for early gastric cancer (EGC) relies on qualitative features such as microvascular (MV) architecture and microsurface structure; however, it is a "static" diagnostic algorithm that uses still images. ME can visualize red blood cell flow within subepithelial microvessels in real time. Here, we evaluated the utility of using the MV blood flow rate in combination with ME for the diagnosis of EGC as a retrospective study. METHODS: Patients with differentiated-type EGC (n = 10) or patchy redness (n = 10) underwent ME with blue laser imaging. The mean MV blood flow rates of EGC, patchy redness, and background mucosa were calculated by the mean movement distance of one tagging red blood cell using split images of ME with blue laser imaging videos. We compared the mean MV blood flow rate between EGC, patchy redness, and background mucosa and also calculated the MV blood flow imaging ratio (inside lesion/background mucosa) between EGC and patchy redness. RESULTS: Mean MV blood flow rate was significantly lower in EGC (1481 µm/s; range 1057-1762) than in patchy redness (3859 µm/s; 2435-5899) or background mucosa (4140.6 µm/s; 2820-6247) (P < 0.01). The MV blood flow imaging ratio was significantly lower in EGC (0.39; 0.27-0.62) than in patchy redness (0.90; 0.78-1.1) (P < 0.01). CONCLUSIONS: Dynamic diagnosis with MV blood flow rate using ME may be useful for the differential diagnosis of EGC and patchy redness. Endoscopic assessment of dynamic processes within the gastric mucosa may facilitate the diagnosis of EGC.

Application of artificial intelligence using a convolutional neural network for diagnosis of early gastric cancer based on magnifying endoscopy with narrow-band imaging.

BACKGROUND AND AIM: Magnifying endoscopy with narrow-band imaging (ME-NBI) has made a huge contribution to clinical practice. However, acquiring skill at ME-NBI diagnosis of early gastric cancer (EGC) requires considerable expertise and experience. Recently, artificial intelligence (AI), using deep learning and a convolutional neural network (CNN), has made remarkable progress in various medical fields. Here, we constructed an AI-assisted CNN computer-aided diagnosis (CAD) system, based on ME-NBI images, to diagnose EGC and evaluated the diagnostic accuracy of the AI-assisted CNN-CAD system. METHODS: The AI-assisted CNN-CAD system (ResNet50) was trained and validated on a dataset of 5574 ME-NBI images (3797 EGCs, 1777 non-cancerous mucosa and lesions). To evaluate the diagnostic accuracy, a separate test dataset of 2300 ME-NBI images (1430 EGCs, 870 non-cancerous mucosa and lesions) was assessed using the AI-assisted CNN-CAD system. RESULTS: The AI-assisted CNN-CAD system required 60 s to analyze 2300 test images. The overall accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the CNN were 98.7%, 98%, 100%, 100%, and 96.8%, respectively. All misdiagnosed images of EGCs were of low-quality or of superficially depressed and intestinal-type intramucosal cancers that were difficult to distinguish from gastritis, even by experienced endoscopists. CONCLUSIONS: The AI-assisted CNN-CAD system for ME-NBI diagnosis of EGC could process many stored ME-NBI images in a short period of time and had a high diagnostic ability. This system may have great potential for future application to real clinical settings, which could facilitate ME-NBI diagnosis of EGC in practice.

Clinicopathological and Endoscopic Features of Raspberry-Shaped Gastric Cancer in Helicobacter pylori-Uninfected Patients.

BACKGROUND: Gastric adenocarcinoma of foveolar type (GA-FV) is a raspberry-shaped gastric cancer (RSGC) and garners much attention as H. pylori (Hp)-uninfected gastric cancer. However, the classification and clinicopathological and endoscopic features of RSGCs in Hp-uninfected patients are poorly defined. We designed a new histopathological classification of RSGC and compared them via endoscopic and clinicopathological characteristics. SUMMARY: From 996 patients with early gastric cancers resected by endoscopy in our hospital, we studied 24 RSGC lesions from 21 (2.4%) Hp-uninfected patients. RSGCs were classified into 3 histological types as follows: GA-FV (n = 19), gastric adenocarcinoma of fundic gland type (GA-FG, n = 2), and gastric adenocarcinoma of fundic gland mucosa type (GA-FGM, n = 3). Most of the lesions were found at the greater curvature of the upper or middle third of the stomach. GA-FV lesions were homogeneously reddish and frequently accompanied with a whitish area around the tumor and an irregular microvascular (MV) pattern; these features were confirmed histopathologically by the presence of homogeneous neoplastic foveolar epithelium with foveolar hyperplasia around the tumors. GA-FG lesions might be heterogeneously reddish with a submucosal tumor shape and regular MV pattern; these were confirmed by the presence of covered or mixed nonneoplastic epithelium on deeper regions of tumors. GA-FGM lesions might be homogeneously reddish and occasionally had a submucosal tumor shape and irregular MV pattern; these were confirmed by the presence of homogeneous neoplastic foveolar epithelium on deeper regions of the tumors. Key Messages: RSGCs in Hp-uninfected patients are classified into 3 histopathological types. For accurate diagnosis of RSGCs, it may be necessary to fully understand endoscopic features of these lesions based on these histological characteristics and to take a precise biopsy.

Optimization of Analytical Conditions for Hydrophilic Nucleic Acids Using Mixed-Mode and Reversed-Phase Pentabromobenzyl Columns.

The aim of this study was to investigate appropriate analytical conditions for hydrophilic nucleosides and nucleotides (monophosphates and triphosphates) by HPLC methods using a mixed-mode AX-C18 column with anion-exchange and hydrophobic interactions by quaternary ammonium and C18, respectively, and a reversed-phase pentabromobenzyl (PBr) column with dispersion force and hydrophobic interactions by PBr group. The higher compound polarity led to stronger retention on AX-C18 (triphosphates > monophosphates > nucleosides). AX-C18 demonstrated feasible retention of nucleotides via anion-exchange interaction by increasing the salt and methanol concentrations. In contrast, on PBr, the lower compound polarity led to stronger retention. On PBr, feasible retention of both nucleosides and nucleotides was obtained via dispersion interactions with purine and pyrimidine rings by increasing the methanol concentration. Regarding the pH of phosphate buffer used as the mobile phase, pH 7.0 should be used in measuring nucleoside triphosphates on AX-C18, whereas pH 2.5 is better suited for measuring nucleotides on PBr. In terms of selectivity to highly hydrophilic nucleotides, the mixed-mode AX-C18 column had an advantage over the reverse-phase PBr column. In contrast, PBr column was more versatile than the AX-C18 column. Taken together, HPLC analyses of nucleosides and nucleotides should be carried out by optimizing the interactions between the stationary phase and nucleic acids.

Randomized controlled study on the effects of triple therapy including vonoprazan or rabeprazole for the second-line treatment of Helicobacter pylori infection.

BACKGROUND AND AIM: Inhibition of gastric acid secretion is important for eradicating Helicobacter pylori. Vonoprazan (VPZ) is a strong, long-lasting inhibitor of gastric acid secretion. Studies that examined the effectiveness of VPZ-based triple therapy in second-line treatment have been performed. However, there have been no randomized controlled studies to compare the effect between VPZ-based triple therapy and proton pump inhibitor (PPI)-based triple therapy in second-line treatment, and it is not known which is more effective between VPZ-based and PPI-based therapies. This study aimed to compare the effectiveness of second-line triple therapies including VPZ or rabeprazole (RPZ) as the PPI. METHODS: Eligible patients with H. pylori infection who failed first-line triple therapy were assigned randomly to the VPZ [VPZ40 mg/day, amoxicillin (AMPC) 1500 mg/day, metronidazole (MNZ) 500 mg/day] or RPZ (RPZ20 mg/day, AMPC1500 mg/day, MNZ500 mg/day) group. A 13C-urea breath test result of less than 2.5% was considered as successful eradication. RESULTS: In total, 46 and 41 patients were analyzed as intention to treat (ITT) and per protocol (PP), respectively. Eradication rates in the VPZ and RPZ groups were 73.9% [95% confidence interval (CI) 51.6-89.8%] and 82.6% (95% CI 61.2-95.0%) based on ITT analysis, respectively (p = 0.72). Based on PP analysis, the eradication rates in the VPZ and RPZ groups were 89.5% (95% CI 66.9-98.7%) and 86.4% (95% CI 65.1-97.1%), respectively (p = 1.00). Two patients in the VPZ group and one in the RPZ group discontinued treatment due to side effects (p = 1.00). CONCLUSION: There were no significant differences in efficacy and safety between second-line therapies including VPZ or RPZ.