Impact of 3-second rule for high confidence assignment on the performance of endoscopists for the real-time optical diagnosis of colorectal polyps.

BACKGROUND: Confusion between high and low confidence decisions in optical diagnosis hinders the implementation of real-time optical diagnosis in clinical practice. We evaluated the effect of a 3-second rule (decision time limited to 3 seconds for a high confidence assignment) in expert and nonexpert endoscopists. METHODS: This single-center prospective study included eight board-certified gastroenterologists. A 2-month baseline phase used standard real-time optical diagnosis for colorectal polyps < 10 mm and was followed by a 6-month intervention phase using optical diagnosis with the 3-second rule. Performance, including high confidence accuracy, and Preservation and Incorporation of Valuable Endoscopic Innovations (PIVI) and Simple Optical Diagnosis Accuracy (SODA) thresholds, was measured. RESULTS: Real-time optical diagnosis was performed on 1793 patients with 3694 polyps. There was significant improvement in high confidence accuracy between baseline and intervention phases in the nonexpert group (79.2 % vs. 86.3 %; P = 0.01) but not in the expert group (85.3 % vs. 87.5 %; P = 0.53). Using the 3-second rule improved the overall performance of PIVI and SODA in both groups. CONCLUSIONS: The 3-second rule was effective in improving real-time optical diagnosis performance, especially in nonexperts.

Impact of comprehensive optical diagnosis training using Workgroup serrAted polypS and Polyposis classification on detection of adenoma and sessile serrated lesion.

OBJECTIVES: Many interventions have been attempted to improve adenoma detection rate (ADR) and sessile serrated lesion detection rate (SDR), and one of these interventions is educational training to recognize polyp characteristics. This study aimed to investigate the change in polyp detection rates of endoscopists before and after comprehensive training through the Gangnam-Real Time Optical Diagnosis (Gangnam-READI) program. METHODS: Fifteen gastroenterologists participated in a 1-year comprehensive training program that consisted of ex vivo and in vivo training that encompasses knowledge and skills in endoscopic characterization of colonic polyps using the Workgroup serrAted polypS and Polyposis (WASP) classification. We evaluated the impact of the training program by comparing the overall and individual ADR and SDR 6 months before and after the training. RESULTS: Overall, 18,280 polyps (9337 adenomas and 855 sessile serrated lesion) were collected. The optical diagnosis training had no significant impact on the difference in ADR after training compared to before training (47.7% vs. 46.5%, P = 0.608). A tendency for a decrease in ADR variance was noted among the endoscopists after training (74.9 vs. 32.7, P = 0.121). The overall pre-training period SDR was 4.5% and showed a statistically significant increase to 5.6%, 8.0%, and 7.1% in the first and second half of the training period, and post-training period, respectively (P = 0.003). The optical diagnosis training did not decrease variance in SDR (8.9 vs. 8.8, P = 0.985). CONCLUSION: Comprehensive optical diagnosis training with WASP classification has a significant impact on increasing the overall SDR of expert endoscopists.

Improved Accuracy in Optical Diagnosis of Colorectal Polyps Using Convolutional Neural Networks with Visual Explanations.

BACKGROUND & AIMS: Narrow-band imaging (NBI) can be used to determine whether colorectal polyps are adenomatous or hyperplastic. We investigated whether an artificial intelligence (AI) system can increase the accuracy of characterizations of polyps by endoscopists of different skill levels. METHODS: We developed convolutional neural networks (CNNs) for evaluation of diminutive colorectal polyps, based on efficient neural architecture searches via parameter sharing with augmentation using NBIs of diminutive (≤5 mm) polyps, collected from October 2015 through October 2017 at the Seoul National University Hospital, Healthcare System Gangnam Center (training set). We trained the CNN using images from 1100 adenomatous polyps and 1050 hyperplastic polyps from 1379 patients. We then tested the system using 300 images of 180 adenomatous polyps and 120 hyperplastic polyps, obtained from January 2018 to May 2019. We compared the accuracy of 22 endoscopists of different skill levels (7 novices, 4 experts, and 11 NBI-trained experts) vs the CNN in evaluation of images (adenomatous vs hyperplastic) from 180 adenomatous and 120 hyperplastic polyps. The endoscopists then evaluated the polyp images with knowledge of the CNN-processed results. We conducted mixed-effect logistic and linear regression analyses to determine the effects of AI assistance on the accuracy of analysis of diminutive colorectal polyps by endoscopists (primary outcome). RESULTS: The CNN distinguished adenomatous vs hyperplastic diminutive polyps with 86.7% accuracy, based on histologic analysis as the reference standard. Endoscopists distinguished adenomatous vs hyperplastic diminutive polyps with 82.5% overall accuracy (novices, 73.8% accuracy; experts, 83.8% accuracy; and NBI-trained experts, 87.6% accuracy). With knowledge of the CNN-processed results, the overall accuracy of the endoscopists increased to 88.5% (P < .05). With knowledge of the CNN-processed results, the accuracy of novice endoscopists increased to 85.6% (P < .05). The CNN-processed results significantly reduced endoscopist time of diagnosis (from 3.92 to 3.37 seconds per polyp, P = .042). CONCLUSIONS: We developed a CNN that significantly increases the accuracy of evaluation of diminutive colorectal polyps (as adenomatous vs hyperplastic) and reduces the time of diagnosis by endoscopists. This AI assistance system significantly increased the accuracy of analysis by novice endoscopists, who achieved near-expert levels of accuracy without extra training. The CNN assistance system can reduce the skill-level dependence of endoscopists and costs.

Multidirectional Colonoscopy Quality Improvement Increases Adenoma Detection Rate: Results of the Seoul National University Hospital Healthcare System Gangnam Center Colonoscopy Quality Upgrade Project (Gangnam-CUP).

BACKGROUND: To prevent colorectal cancer, high-quality colonoscopy is advocated, undertaken by endoscopists with high adenoma detection rates (ADRs). Despite reports that various factors may impact ADRs, the significance of such factors is still unclear. AIMS: The analysis was aimed at quality-oriented interventions for boosting ADRs. METHODS: Study enrollees were adults subjected to screening colonoscopy between September 2013 and August 2016 at the Gangnam Center of Seoul National University Hospital Healthcare System. The investigation entailed six periods (P1-6) of 6 months each, during which serial multidirectional quality improvement efforts were instituted. In particular, we sought to further educate endoscopists, provide feedback on individual ADRs, and introduce a split-dose regimen, gauging results via the Boston Bowel Preparation Score. Changes in polyp detection rates (PDRs) and ADRs were then analyzed. RESULTS: A total of 13,430 colonoscopies were undertaken by 15 experienced endoscopists. Overall, the ADR increased from 45.6% (P1) to 48.2% (P6, p < 0.001). The PDR, ADR, and advanced adenoma detection rate (AdvADR) showed the greatest increases between P3 and P4 [PDR 67.8% → 71.2% (p < 0.001); ADR 44.1% → 47.7% (p = 0.001); AdvADR 2.3% → 3.3% (p = 0.028)] in keeping with the introduction of a split-dose regimen. The sessile serrated adenoma detection rate (SSADR) increased substantially from 2.1% (P1) to 7.9% (P6, p < 0.001), with the largest gain between P1 and P2, just after education (p = 0.023). CONCLUSIONS: Successful quality improvement in colonoscopy was achieved through comprehensive multidirectional efforts in education, feedback, and enhanced bowel preparation. Achieving high-level bowel preparation was paramount in ADR improvement. The SSADR was improved through education.

The exploration of feature extraction and machine learning for predicting bone density from simple spine X-ray images in a Korean population.

OBJECTIVE: Osteoporosis is hard to detect before it manifests symptoms and complications. In this study, we evaluated machine learning models for identifying individuals with abnormal bone mineral density (BMD) through an analysis of spine X-ray features extracted by deep learning to alert high-risk osteoporosis populations. MATERIALS AND METHODS: We retrospectively used data obtained from health check-ups including spine X-ray and dual-energy X-ray absorptiometry (DXA). Consecutively, we selected people with normal and abnormal bone mineral density. From the regions of interest of X-ray images, deep convolutional networks were used to generate image features. We designed prediction models for abnormal BMD using the image features trained by machine learning classification algorithms. The performances of each model were evaluated. RESULTS: From 334 participants, 170 images of abnormal (T scores < - 1.0 standard deviations (SD)) and 164 of normal BMD (T scores > = - 1.0 SD) were used for analysis. We found that a combination of feature extraction by VGGnet and classification by random forest based on the maximum balanced classification rate (BCR) yielded the best performance in terms of the area under the curve (AUC) (0.74), accuracy (0.71), sensitivity (0.81), specificity (0.60), BCR (0.70), and F1-score (0.73). CONCLUSION: In this study, we explored various machine learning algorithms for the prediction of BMD using simple spine X-ray image features extracted by three deep learning algorithms. We identified the combination for the best performance in predicting high-risk populations with abnormal BMD.

Improved Real-Time Optical Diagnosis of Colorectal Polyps Following a Comprehensive Training Program.

BACKGROUND & AIMS: The optimal training method for endoscopic characterization of colorectal polyps using narrow-band imaging is uncertain, and sessile serrated lesions (SSLs) optical diagnosis data are lacking. We aimed to evaluate a comprehensive training program for real-time optical diagnosis of colorectal polyps, including SSLs. METHODS: We performed a single-institution prospective study of 15 endoscopists trained with the Workgroup Serrated Polyps and Polyposis classification system. After the first phase of in vivo optical diagnosis, their performances were evaluated. After re-education for insufficient competency, they began the second phase. The learning curves and performance on 2 preservation and incorporation of valuable endoscopic innovations benchmarks were assessed. RESULTS: A total of 7294 polyps, including 486 SSLs, were diagnosed in real-time. The overall accuracy improved from 73.5% in the first phase to 77.1% in the second. The accuracy with high confidence was 79.4% and 85.1% in the first and second phases, respectively. In the first and second phases, the negative predictive values for diminutive neoplastic polyps were 82.1% and 92.5%, respectively, and concordances of the surveillance intervals were 80.7% and 89.7%, respectively. Eight endoscopists achieved the preservation and incorporation of valuable endoscopic innovations benchmarks after the second phase compared with none after the first. In contrast, the high confidence rate decreased from 74.6% to 70.2% as training progressed. CONCLUSION: A comprehensive training program for real-time optical diagnosis significantly improved performance and reduced individual variability in less-experienced endoscopists. ClinicalTrials.gov no: NCT02516748.

Risk of progression for incidental small subepithelial tumors in the upper gastrointestinal tract.

BACKGROUND AND STUDY AIMS: Subepithelial tumor is a relatively common finding in upper gastrointestinal endoscopy. This study aimed to evaluate the natural course of incidentally detected small subepithelial tumors in the upper gastrointestinal tract and to analyze risk factors for increase in the size of such tumors. PATIENTS AND METHODS: Medical records of 1684 patients with subepithelial tumors in the upper gastrointestinal tract incidentally detected between 2004 and 2013 were retrospectively reviewed. If serial follow-up endoscopy showed significant size increase, endoscopic or surgical resection was recommended because of possibility of malignant change. RESULTS: 954 participants with subepithelial tumors underwent serial upper gastrointestinal endoscopy for a period > 6 months. Initial mean size of subepithelial tumors was 8.7 mm (range 1 - 35 mm). During a mean follow-up of 47.3 months (range 6 - 118 months), lesion size was unchanged in 920 participants (96.4 %), and in 34 participants (3.6 %) lesions had increased at least 25 % in diameter (mean increment 6.2 mm, range 2 - 15 mm). Subepithelial tumors with overlying mucosal changes (hyperemia, erosion, or ulcer) had a significantly higher risk of increasing in size (odds ratio [OR] = 3.61, 95 % confidence interval [95 %CI] 1.06 - 12.28). Growth rates (size increment per year) for enlarging lesions were significantly correlated with initial size (r = 0.44, P = 0.009). CONCLUSIONS: Most incidentally detected small subepithelial tumors in the upper gastrointestinal tract showed no size change during follow-up. Thus, regular follow-up with serial endoscopy may be sufficient for small subepithelial tumors (< 2 cm) with intact overlying mucosa.

The Relationship Between Colonoscopy Procedure Order and Adenoma Detection Rates: A Prospective Study.

GOALS: The aim of this study was to prospectively assess the effects of the order of colonoscopic procedures and other possible factors on the adenoma detection rate (ADR). BACKGROUND: There have been conflicting studies regarding the timing or order of a colonoscopy and its ability to detect adenomas. STUDY: Between March 2011 and July 2011, consecutive colonoscopies were prospectively performed by 7 board-certified staff endoscopists at the Seoul National University Hospital Healthcare System Gangnam Center. The primary outcome was the overall ADR according to the procedure order of the colonoscopies, and the secondary outcome was the identification of other possible factors influencing the ADR. RESULTS: A total of 1908 colonoscopies were analyzed. The detection rate was 56.5% for all polyps and 37.3% for adenomas. The ADR increased as the performance order of the colonoscopy increased and was highest for the third procedure (43.4%). However, the ADR of the remaining procedures, including later procedures, was similar throughout the workday. In the multivariable analysis, the ADR was significantly associated with older age, male sex, high body mass index, personal history of colorectal polyps, long withdrawal time, and an experienced endoscopist. However, the colonoscopy procedure order was not significantly associated with the ADR. CONCLUSIONS: The ADR was stable according to the procedure order for the later procedures of the workday in a setting of moderate daily procedure volumes. The withdrawal time and experience level of the endoscopist were more important than the procedure order in detecting adenomas by colonoscopy.

Comparison of Narrow Band Imaging and Fujinon Intelligent Color Enhancement in Predicting Small Colorectal Polyp Histology.

BACKGROUND: There are limited data on the performance of narrow band imaging (NBI) and Fujinon intelligent color enhancement (FICE) for differentiating polyp histologies. AIMS: The aim of this study was to compare the diagnostic performances of NBI and FICE in differentiating neoplastic from non-neoplastic colorectal polyps <10 mm during screening colonoscopy. METHODS: A total of 955 average-risk adults undergoing screening colonoscopies were randomly allocated to NBI or FICE groups. Four board-certified staff endoscopists without prior experience using NBI or FICE participated. The main outcomes of this study were overall accuracy, sensitivity, and specificity of FICE and NBI in identifying neoplastic polyps. RESULTS: There was no significant difference in the number of subjects with adenoma between the NBI (143/475, 30.1 %) and FICE groups (139/480, 29.0 %) (after excluding adenoma ≥1 cm) (P > 0.05). The overall accuracy of NBI was 81.0 %, compared with 81.4 % for FICE (P = 0.867). The overall sensitivity and specificity of NBI and FICE were 84.6 and 78.0 % (P = 0.054); 75.1 and 86.5 % (P = 0.009), respectively. For polyps measuring ≤5 mm, the accuracy was 79.4 % for NBI and 80.1 % for FICE (P = 0.835; sensitivity 81.9 vs. 74.5 %, P = 0.064; specificity 75.7 vs. 88.4 %, P = 0.006). CONCLUSIONS: The overall accuracy of NBI and FICE was similar for differentiating small polyp histologies during screening colonoscopy. However, better results should be achieved before using NBI or FICE as real-time optical biopsy of colorectal polyps in screening colonoscopy.

Comparison of detection and miss rates of narrow band imaging, flexible spectral imaging chromoendoscopy and white light at screening colonoscopy: a randomised controlled back-to-back study.

OBJECTIVE: Virtual chromoendoscopy (CE) is expected to enhance adenoma yield and reduce variation in performance between colonoscopists. This study aimed to compare the efficacy of narrow band imaging (NBI), flexible spectral imaging CE (FICE) and white light (WL) colonoscopy and their impact for less experienced endoscopists. METHODS: We performed a randomised tandem colonoscopy trial controlling for withdrawal time and bowel preparation. Average-risk adults undergoing screening colonoscopy were enrolled and randomly assigned to first withdrawal with one of the three imaging modalities (NBI (NBI-WL group), FICE (FICE-WL group) and WL (WL-WL group)). Eight colonoscopists were categorised into expert and non-expert subgroups. RESULTS: 1650 subjects (mean age 51.4 years, 63.9% men) were included (550 in each group). Compared with WL, neither NBI nor FICE increased the mean number of adenomas detected per patient (0.37 vs 0.35 and 0.36; p=0.591) or the percentage of patients with adenoma (25.3% vs 24.5% and 23.6%; p=0.753). For all three modalities, expert subgroups had higher yields of adenomas than non-expert subgroups. Learning curves were observed only for non-expert subgroups with all three modalities. The percentage of missed adenomas did not differ between the three groups (20.8% by WL vs 22.9% by NBI and 26.0% by FICE, p=0.300) and was not affected by endoscopists' expertise. CONCLUSIONS: Neither NBI nor FICE improved adenoma detection or miss rates, with no difference in diagnostic efficacy between the two systems. Virtual CE had no additional benefits over WL for non-experts. CLINICAL TRIAL REGISTRATION NUMBER: KCT0000570.

Factors that determine prolonged cecal intubation time during colonoscopy: impact of visceral adipose tissue.

OBJECTIVE: Various factors including age, sex, body mass index (BMI) and history of operation have been linked to the colonoscopic intubation time. The aims of this study were to identify the factors predicting cecal intubation time (CIT) and to evaluate the effect of the visceral adipose tissue (VAT) area on CIT. MATERIAL AND METHODS: A total of 1386 consecutive subjects who underwent colonoscopy and abdominal CT on the same day for a health checkup at a single health care center in Korea from August to December 2011 were studied prospectively. Age, sex, BMI, height, waist circumference, history of operation, symptoms of irritable bowel syndrome, bowel preparation status, experience of colonoscopists, VAT amount on abdominal CT and time required to reach the cecum were analyzed. RESULTS: The mean age of the subjects was 53.0 ± 9.6 years, and 63.5% were male. The median CIT was 271 s. Univariate analyses showed that female gender, old age, shorter height, lower BMI, prior history of surgery and lower VAT were associated with longer CIT. To adjust for confounding effects of the gender, we investigated the genders separately in multivariate analysis. Older age and lower VAT were associated with prolonged CIT. However, the significance of association of VAT on prolonged CIT disappeared in women. CONCLUSION: This study demonstrates that CIT is prolonged by lower VAT area in men. This is the first study to demonstrate a direct association between VAT area and CIT.

Clinical Strategies in Gene Screening Counseling for the Healthy General Population.

The burgeoning interest in precision medicine has propelled an increase in the use of genome tests for screening purposes within the healthy population. Gene screening tests aim to pre-emptively identify those individuals who may be genetically predisposed to certain diseases. However, as genetic screening becomes more commonplace, it is essential to acknowledge the unique challenges it poses. A prevalent issue in this regard is the occurrence of falsepositive results, which can lead to unnecessary additional tests or treatments, and psychological distress. Additionally, the interpretation of genomic variants is based on current research evidence, and can accordingly change as new research findings emerge, potentially altering the clinical significance of these variants. Conversely, a further prominent concern regards false assurances in genetic testing, as genetic tests can yield false-negative results, potentially posing a significant clinical risk. Moreover, the results obtained for the same disease can vary among different genetic testing services, due to differences in the types of variants assessed, the scope of tests, analytical methods, and the algorithms used for predicting diseases. Consequently, whereas genetic testing holds significant promise for the future of medicine, it poses unique challenges. If conducted without a full understanding of its implications, genetic testing may fail to achieve its purpose potentially hindering effective health management. Therefore, to ensure a comprehensive understanding of the implications of genetic testing within the general population, sufficient discussion and careful consideration should be given to counseling based on gene test results.

The association between platelet-related parameters and nonalcoholic fatty liver disease in a metabolically healthy nonobese population.

Nonalcoholic fatty liver disease (NAFLD) is the most common chronic liver disease characterized by subclinical inflammation and is related to obesity and metabolic syndrome (MS), but it is also frequently observed in nonobese populations. We aimed to evaluate the relationship between the white blood cell count-to-mean platelet volume ratio (WBC/MPV), platelet-to-lymphocyte count ratio (PLR) and lymphocyte-monocyte ratio (LMR) in association with NAFLD, considering the presence of obesity and MS. Additionally, we aimed to investigate whether these parameters exhibited similar correlations in metabolic dysfunction-associated steatotic liver disease (MASLD) as observed in NAFLD. This cross-sectional study included subjects who underwent a comprehensive health evaluation, including blood tests and abdominal ultrasonography. Subgroup analyses were conducted based on obesity and MS. Out of a total 5929 subjects (3271 males, mean age 49.7 ± 10.6 years), 2253 (38.0%) had NAFLD. WBC/MPV was significantly higher, and PLR was significantly lower in subjects with NAFLD. In the analysis restricted to the nonobese (BMI < 25 kg/m2) population without MS, both WBC/MPV and PLR were independently associated with NAFLD: WBC/MPV (adjusted OR 3.366; 95% CI 2.238-5.066) and PLR (adjusted OR 0.997; 95% CI 0.996-0.999). When assessing the risk of NAFLD based on the WBC/MPV and PLR quartiles, the adjusted OR and 95% CI for the lowest quartile compared to the highest were 2.055 (95% CI 1.626-2.602) for WBC/MPV and 0.660 (95% CI 0.523-0.832) for PLR in the nonobese, metabolically healthy group. The levels of WBC/MPV and PLR were independently associated with NAFLD. Furthermore, in MASLD, an association with WBC/MPV, PLR and LMR was identified, similar to the results observed in NAFLD, even after adjusting for confounding variables. In conclusion, the present study demonstrated a significant association between NAFLD and platelet-related parameters, especially in nonobese, metabolically healthy subjects.

Density clustering-based automatic anatomical section recognition in colonoscopy video using deep learning.

Recognizing anatomical sections during colonoscopy is crucial for diagnosing colonic diseases and generating accurate reports. While recent studies have endeavored to identify anatomical regions of the colon using deep learning, the deformable anatomical characteristics of the colon pose challenges for establishing a reliable localization system. This study presents a system utilizing 100 colonoscopy videos, combining density clustering and deep learning. Cascaded CNN models are employed to estimate the appendix orifice (AO), flexures, and "outside of the body," sequentially. Subsequently, DBSCAN algorithm is applied to identify anatomical sections. Clustering-based analysis integrates clinical knowledge and context based on the anatomical section within the model. We address challenges posed by colonoscopy images through non-informative removal preprocessing. The image data is labeled by clinicians, and the system deduces section correspondence stochastically. The model categorizes the colon into three sections: right (cecum and ascending colon), middle (transverse colon), and left (descending colon, sigmoid colon, rectum). We estimated the appearance time of anatomical boundaries with an average error of 6.31 s for AO, 9.79 s for HF, 27.69 s for SF, and 3.26 s for outside of the body. The proposed method can facilitate future advancements towards AI-based automatic reporting, offering time-saving efficacy and standardization.

Effect of annual endoscopic screening on clinicopathologic characteristics and treatment modality of gastric cancer in a high-incidence region of Korea.

We investigated risk factors for gastric cancer (GC) and effect of annual endoscopic screening on detection and treatment modality of GC. Asymptomatic adults who underwent upper endoscopy during health checkups at Seoul National University Hospital Healthcare System Gangnam Center were enrolled. We compared clinicopathologic characteristics of GC according to screening interval (repeated vs. infrequent, annual vs. biennial). After age- and sex-matching, relative risk was computed by hazard ratio (HR) using Cox proportional regression with multivariate adjustment. Of the 58,849 subjects who received screening endoscopy, 277 (0.47%) were found to have GC. Intestinal type comprised 55.4% (102/184) followed by diffuse type (n = 65, 35.3%). Age ≥ 50 years, family history and smoking independently increased the risk of GC for both types, whereas male gender [HR = 4.81, 95% confidence interval (CI): 2.72-8.03] and intestinal metaplasia (IM) (HR = 10.87, 95% CI: 3.36-22.30) were significant predictors for intestinal type only. Proportion of early gastric cancer (EGC) was 98.6% (71/72) in annual screening group and 80.7% (46/57) in biennial screening group (p < 0.01). In the former, tumor size was smaller (1.7 ± 1.3 vs. 2.3 ± 1.8 cm; p < 0.01] and proportion of intramucosal cancer was larger (75.0 vs. 56.1%; p = 0.04). Endoscopic resection was performed more frequently in annual screening group (56.9 vs. 33.3%; p = 0.02). IM along with male gender and older age was a strong risk factor for intestinal type GC. Annual screening group improved detection of early-stage and endoscopically treatable GC suggesting that intensive screening and surveillance may be useful for high-risk subpopulations with epidemiologic risk factors or premalignant lesions such as IM.

Effect of Helicobacter pylori eradication according to the IL-8-251 polymorphism in Koreans.

Previous studies suggested that polymorphisms of proinflammatory cytokine genes are important host genetic factors in Helicobacter pylori infection. The present study evaluated whether IL-8-251 polymorphism affected H. pylori eradication rate and to investigate the effect of H. pylori eradication on angiogenesis and the inflammatory process according to the IL-8-251 polymorphism. A total of 250 H. pylori-positive patients treated by endoscopic resection of the gastric neoplasm were classified into 3 groups (134 H. pylori-eradicated group, 19 H. pylori-eradication failure group, and 97 H. pylori-infected group). H. pylori status, histology, and angiogenic factor levels were evaluated at baseline, 6 months, and 18 months. H. pylori eradication rate was 92.9% in AA genotype, 85.7% in AT genotype and 88.4% in TT genotype (P value = 0.731). Elevated IL-8 and matrix metalloproteinase-9 concentrations in H. pylori-infected gastric mucosa were reversible by successful eradication of H. pylori, independent of the IL-8-251 polymorphism. It is suggested that elevated IL-8 and MMP-9 concentrations in H. pylori-infected gastric mucosa are altered significantly after successful eradication and these conditions continue for 18 months. However, IL-8-251 polymorphism does not affect H. pylori eradication rate and the sequential changes of related angiogenic factors after H. pylori eradication in Koreans.

A genome-wide association study implicates the pleiotropic effect of NMUR2 on asthma and COPD.

Asthma and chronic obstructive pulmonary disease (COPD) are two distinct diseases that are associated with chronic inflammation. They share common features in terms of their advanced stages and genetic factors. This study aimed to identify novel genes underlying both asthma and COPD using genome-wide association study (GWAS) to differentiate between the two diseases. We performed a GWAS of asthma and COPD in 7828 Koreans from three hospitals. In addition, we investigated genetic correlations. The UK Biobank dataset was used for the replication studies. We found that rs2961757, located near neuromedin U receptor 2 (NMUR2) on chromosome 5, was genome-wide significant ([Formula: see text] = 0.44, P-valueAsthma-COPD = 3.41 × 10-8), and significant results were replicated with the UK Biobank data ([Formula: see text] = 0.04, P-valueAsthma-COPD = 0.0431). A positive genetic correlation was observed between asthma and COPD (39.8% in the Korean dataset and 49.8% in the UK Biobank dataset). In this study, 40-45% of the genetic effects were common to asthma and COPD. Moreover, NMUR2 increases the risk of asthma development and suppresses COPD development. This indicates that NMUR2 allows for better differentiation of both diseases, which can facilitate tailored medical therapy.

Colonoscopic image synthesis with generative adversarial network for enhanced detection of sessile serrated lesions using convolutional neural network.

Computer-aided detection (CADe) systems have been actively researched for polyp detection in colonoscopy. To be an effective system, it is important to detect additional polyps that may be easily missed by endoscopists. Sessile serrated lesions (SSLs) are a precursor to colorectal cancer with a relatively higher miss rate, owing to their flat and subtle morphology. Colonoscopy CADe systems could help endoscopists; however, the current systems exhibit a very low performance for detecting SSLs. We propose a polyp detection system that reflects the morphological characteristics of SSLs to detect unrecognized or easily missed polyps. To develop a well-trained system with imbalanced polyp data, a generative adversarial network (GAN) was used to synthesize high-resolution whole endoscopic images, including SSL. Quantitative and qualitative evaluations on GAN-synthesized images ensure that synthetic images are realistic and include SSL endoscopic features. Moreover, traditional augmentation methods were used to compare the efficacy of the GAN augmentation method. The CADe system augmented with GAN synthesized images showed a 17.5% improvement in sensitivity on SSLs. Consequently, we verified the potential of the GAN to synthesize high-resolution images with endoscopic features and the proposed system was found to be effective in detecting easily missed polyps during a colonoscopy.

Genome-Wide Association Study of Korean Asthmatics: A Comparison With UK Asthmatics.

PURPOSE: Although genome-wide association studies (GWASs) represent the most powerful approach for identifying genes that influence asthma, to date, no studies have established genetic susceptibility to asthma in the Korean population. This study aimed to identify genetic variants associated with adult Korean asthmatics and compare them with the significant single nucleotide polymorphisms (SNPs) of UK asthmatics from the UK Biobank. METHODS: Patients were defined as having asthma if they were diagnosed by a doctor or taking medications for asthma. Controls were defined as individuals without asthma or chronic obstructive pulmonary disease. We performed quality control, genotype imputation, GWAS, and PrediXcan analyses. In the GWAS, a P value of < 5 × 10-8 was considered significant. We compared significant SNPs between Korean and UK patients with asthma. RESULTS: A total of 1,386 asthmatic patients and 5,205 controls were analyzed. The SNP rs1770, located near the human leukocyte antigen (HLA)-DQB1, was the most significant SNP (P = 4.5 × 10-10). In comparison with 24 SNPs in a GWAS of UK asthmatics, six SNPs were significant with the same odds ratio (OR) direction, including signals related to type 2 inflammation (e.g., IL1RL1, TSLP, and GATA3) and mucus plugging (e.g., MUC5AC). HLA-DQA1 showed an opposite OR direction. The HLA-DQB1 gene demonstrated significantly imputed mRNA expression in the lung tissue and whole blood. CONCLUSIONS: The SNP rs1770 of HLA-DQB1 was the most significant in Korean asthmatics. Similarities and discrepancies were found in the genetic variants between Korean and UK asthmatics. GWAS of Korean asthmatics should be replicated and compared with those of GWAS of other ethnicities.

Clinical outcomes of endoscopic submucosal dissection for undifferentiated early gastric cancer.

BACKGROUND: Early gastric cancer (EGC) with undifferentiated histology has not been generally accepted as an indication for endoscopic treatment. This study was designed to evaluate the outcomes and clinicopathological factors associated with the complete resection of undifferentiated EGC using endoscopic submucosal dissection (ESD). METHODS: A retrospective analysis of prospectively collected data was performed on consecutive patients who underwent ESD. Among the 456 EGCs treated using ESD at the Seoul National University Hospital, Seoul, Korea, between April 2005 and June 2008, 60 lesions (13.2%) were diagnosed as undifferentiated gastric cancer (poorly differentiated adenocarcinoma or signet ring cell carcinoma). RESULTS: En bloc resection was performed in all lesions without significant complications. The size discrepancy between the pretreatment endoscopy and the resected specimen was significantly higher in undifferentiated EGCs than differentiated EGCs (p = 0.002). The complete resection rate was significantly lower for undifferentiated EGC (55%) cases than differentiated EGC cases (84.1%; p < 0.001). Independent risk factors for incomplete resection of undifferentiated EGC included tumor size >20 mm, submucosal invasion, and presence of ulceration. During a mean observation time of 16 months, no recurrence developed in any of the patients with undifferentiated EGCs thought to be completely resected by ESD. CONCLUSIONS: ESD might be considered an alternative treatment modality in carefully selected cases of undifferentiated EGC.