Background:Slight mucosal lesions in the early stage of gastric cancer(GC)are difficult to recognize,and the miss rate of early GC by conventional endoscopy is high.Artificial intelligence(AI)systems can assist in the identification of gastric neoplastic lesions and reduce miss rate,but it is not clear whether AI-assisted endoscopic screening is cost-effective.Aims:The subjects of this study were to evaluate the cost-effectiveness of a population-based endoscopy screening program for GC in high-incidence countries(China,Japan and South Korea),and to explore the applicability of domestic AI--Intelligent and real-time endoscopy analytical device(IREAD)-assisted endoscopy for GC screening in these three countries.Methods:Based on the natural history of GC,a Markov model with cycle year of 1 year was constructed to compare cost-effectiveness of two strategies for GC screening in recommended age group:no screening(the control strategy),conventional endoscopy screening and IREAD-assisted endoscopy screening.Data such as transition probabilities of different states and treatment costs were obtained from previously published studies.The cost-effectiveness analysis was conducted from the perspective of society by calculating cost,Quality adjusted life years(QALY),Incremental cost effectiveness ratio(ICER).Results:The cohort results showed that 15.87%and 24.52%of GC-related deaths could be respectively avoid by conventional endoscopy screening and IREAD-assisted endoscopy screening in China,which the screening effects were similar to Japan;In South Korea,Conventional endoscopic screening and IREAD-assisted endoscopic screening averted 41.34%and 53.15%of GC-related deaths,respectively.Between the two strategies,IREAD-assisted endoscopic screening is more economic,with ICER of $34 827.61/QALY,$87 978.71/QALY and $10 574.30/QALY in China,Japan and South Korea,respectively,which were lower than the willingness-to-pay(WTP)threshold.Conclusions:When the threshold of WTP is 3 times Gross domestic product per capita,the application of AI-assisted endoscopy for GC screening in age-specific population in high-incidence countries may be more cost-effective.Meanwhile,this study provides important evidence for the promotion of domestic IRAED-assisted endoscopy in GC screening in China,Japan and South Korea.

Objective:To evaluate the clinical efficacy of percutaneous intramyocardial septal radiofrequency ablation (PIMSRA) in the treatment of obstructive hypertrophic cardiomyopathy (HOCM) with mild septal hypertrophy.Methods:Forty-five HOCM patients with mild septal hypertrophy (the maximal left ventricular wall thickness is 15-19 mm) who were treated with PIMSRA between November 2016 to February 2021 in the Hypertrophic Cardiomyopathy Center of Xijing Hospital of Air Force Military Medical University were enrolled, and their clinical datas were collected and analyzed. The clinical symptoms and NYHA functional class before operation, 6 months and 1 year after operation were collected. Interventricular septum thickness, left ventricular outflow tract pressure gradient, left ventricular outflow tract diameter, mitral regurgitation, left ventricular systolic and diastolic function were evaluated by transthoracic echocardiography before operation, 6 months and 1 year after operation, intraoperative complications were monitored and recorded. Postoperative arrhythmias were monitored by routine 12 lead ECG and 24-hour ambulatory ECG.Results:All patients successfully completed PIMSRA procedure.No clinical adverse events such as death, bleeding and stroke occurred during and around the operation.No left bundle branch block, complete atrioventricular block and malignant arrhythmia occurred after the operation. All patients did not need permanent pacemaker implantation.NYHA functional class and clinical symptoms of patients were significantly improved after 6 months compared with values before operation (all P<0.001, respectively), it remained stable for 1 year after operation; Anterior interventricular septum, posterior interventricular septum, maximal left ventricular wall thickness all significantly decreased (all P<0.001, respectively), left ventricular outflow tract diameter widened ( P<0.001), continuous improvement 1 year after operation; left ventricular outflow tract gradient and provoked left ventricular outflow tract gradient all significantly decreased, mitral regurgitation decreased and SAM classification reduced after 6 months compared with values before operation (all P<0.001, respectively); left ventricular end-diastolic diameter widened and left atrial diameter decreased (all P<0.001, respectively), it remained stable for 1 year after operation. Left atrial volume index decreased ( P<0.001), with continuous improvement 1 year after operation; The ratio of early diastolic mitral valve velocity to early diastolic mitral annulus velocity (E/e′) decreased ( P=0.001), it remained stable for 1 year after operation. There were no significant differences in left ventricular end diastolic volume, left ventricular end systolic volume and left ventricular ejection fraction among the three groups (all P>0.05). Conclusions:PIMSRA is effective in the treatment of obstructive hypertrophic cardiomyopathy with mild ventricular septal hypertrophy.

Objective:To investigate the effect of percutaneous intramyocardial septal radiofrequency ablation (PIMSRA) guided by echocardiography on the Lown classification of ventricular arrhythmias in patients with hypertrophic obstructive cardiomyopathy (HOCM).Methods:A total of 85 patients with HOCM who received PIMSRA treatment at Xijing Hospital of Air Force Military Medical University from May 2017 to October 2019 were retrospectively selected. All patients underwent 24-hour Holter examinations before and 1 year after PIMSRA to obtain parameters related to Lown classification. The changes in Lown grades after PIMSRA were analyzed. The patients were divided into improved group and unimproved group according to whether there was significant improvement in Lowen′s grades, and the difference of the parameters related were compared. The influencing factors of the changes in Lown classification were analyzed.Results:Compared with before PIMSRA, there was a significant improvement in the Lown classification after PIMSRA ( P=0.001). The patients with Lown grade Ⅰ increased significantly ( P=0.001), and the patients with grade Ⅲ decreased significantly ( P=0.005). There were no significant changes in patients with Lown grades 0, Ⅱ, and Ⅳ (all P>0.05). The proportion of patients with family history of hypertrophic cardiomyopathy (HCM), the baseline Lown classes, the reduction rate of the maximum left ventricular wall thickness and the reduction rate of the provocative left ventricular outflow tract gradient (LVOTG) were higher in the improved group than the unimproved group (all P<0.05). Multivariate Logistic regression results showed that HCM family history ( OR=3.95, 95% CI=1.34-11.64, P=0.013), baseline Lown classes ( OR=2.01, 95% CI=1.25-3.22, P=0.004) and the reduction rate of the provocative LVOTG gradient ( OR=1.02, 95% CI=1.00-1.04, P=0.041) were independent factors of postoperative Lown classification improvement. Conclusions:The Lown classes of HOCM patients after PIMSRA is significantly improved.HCM family history, the baseline Lown classes, and the reduction rate of postoperative provocative LVOTG are independent influencing factors for the improvement of Lown grade.

Objective:To evaluate deep learning for differentiating invasion depth of colorectal adenomas under image enhanced endoscopy (IEE).Methods:A total of 13 246 IEE images from 3 714 lesions acquired from November 2016 to June 2021 were retrospectively collected in Renmin Hospital of Wuhan University, Shenzhen Hospital of Southern Medical University and the First Hospital of Yichang to construct a deep learning model to differentiate submucosal deep invasion and non-submucosal deep invasion lesions of colorectal adenomas. The performance of the deep learning model was validated in an independent test and an external test. The full test was used to compare the diagnostic performance between 5 endoscopists and the deep learning model. A total of 35 videos were collected from January to June 2021 in Renmin Hospital of Wuhan University to validate the diagnostic performance of the endoscopists with the assistance of deep learning model.Results:The accuracy and Youden index of the deep learning model in image test set were 93.08% (821/882) and 0.86, which were better than those of endoscopists [the highest were 91.72% (809/882) and 0.78]. In video test set, the accuracy and Youden index of the model were 97.14% (34/35) and 0.94. With the assistance of the model, the accuracy of endoscopists was significantly improved [the highest was 97.14% (34/35)].Conclusion:The deep learning model obtained in this study could identify submucosal lesions with deep invasion accurately for colorectal adenomas, and could improve the diagnostic accuracy of endoscopists.

Objective:To explore the effectiveness of the artificial intelligence-endoscopic ultrasound (AI-EUS) biliary and pancreatic recognition system in assisting the recognition of EUS images.Methods:Subjects who received EUS due to suspicious biliary and pancreatic diseases from December 2019 to August 2020 were prospectively collected from the database of Department of Gastroenterology, Renmin Hospital of Wuhan University. Pancreatic EUS images of 28 subjects were included for recognition of pancreas standard station. EUS images of bile duct of 29 subjects were included for recognition of bile duct standard station. Eight new endoscopists from the Gastroenterology Department of Renmin Hospital of Wuhan University read the 57 EUS videos with and without the assistance of AI-EUS biliary and pancreatic recognition system. Accuracy of endoscopists' identification of biliary and pancreatic standard sites with and without the assistance of AI-EUS was compared.Results:The accuracy of pancreas standard station identification of the new endoscopists increased from 67.2% (903/1 344) to 78.4% (1 054/1 344) with the assistance of AI-EUS. The accuracy of bile duct standard station identification increased from 56.4% (523/928) to 73.8% (685/928).Conclusion:AI-EUS biliary and pancreatic recognition system can improve the accuracy of EUS images recognition of biliary and pancreatic system, which can assist diagnosis in clinical work.

Objective:To evaluate the intelligent gastrointestinal endoscopy quality control system in gastroscopy.Methods:Fourteen endoscopists from Renmin Hospital of Wuhan University were assigned to the quality-control group and the control group by the random number table. In the pre-quality-control stage (from April 20, 2019 to May 31, 2019), data of gastroscopies performed by the enrolled endoscopists were collected. In the training stage (June 1 to 30, 2019), the quality-control group was trained in quality control knowledge and the instructions of intelligent gastrointestinal endoscopy quality control system; but the control group was only trained in quality control knowledge. In the post-quality-control stage (from July 1, 2019 to August 20, 2019), a quality report was submitted weekly to the endoscopists in the quality-control group with a review and feedback, while the control group had no quality control report. Simultaneously, the gastroscopies performed by the enrolled endoscopists were collected during the period. Changes of precancerous lesion detection rate in the two groups were compared.Results:Seven endoscopists were assigned to each group. A total of 3 446 gastroscopies were included in the pre-quality-control stage ( n=1 651, including 753 cases in the quality-control group and 898 cases in the control group) and post-quality-control stage (n=1 795, including 892 cases in the quality-control group and 903 cases in the control group). The detection rate of precancerous lesions in the quality-control group increased by 3.6% [3.3% (29/892) VS 6.9% (52/753), χ2=11.65, P<0.01], while that of the control group increased by 0.4% [3.3% (30/903) VS 3.7% (33/898), χ2=0.17, P=0.684]. Conclusion:The intelligent gastrointestinal endoscopy quality control system with a review and feedback could monitor and improve the quality of gastroscopy.

Objective:To construct a deep learning-based artificial intelligence endoscopic ultrasound (EUS) bile duct scanning substation system to assist endoscopists in learning multi-station imaging and improve their operation skills.Methods:A total of 522 EUS videos in Renmin Hospital of Wuhan University and Wuhan Union Hospital from May 2016 to October 2020 were collected, and images were captured from these videos, including 3 000 white light images and 31 003 EUS images from Renmin Hospital of Wuhan University, and 799 EUS images from Wuhan Union Hospital. The pictures were divided into training set and test set in the EUS bile duct scanning system. The system included filtering model of white light gastroscopy images (model 1), distinguishing model of standard station images and non-standard station images (model 2) and substation model of EUS bile duct scanning standard images (model 3), which were used to classify the standard images into liver window, stomach window, duodenal bulb window, and duodenal descending window. Then 110 pictures were randomly selected from the test set for a man-machine competition to compare the accuracy of multi-station imaging by experts, advanced endoscopists and the artificial intelligence model.Results:The accuracies of model 1 and model 2 were 100.00% (1 200/1 200) and 93.36% (2 938/3 147) respectively. Those of model 3 on the internal validation dataset in each classification were 97.23% (1 687/1 735) in liver window, 96.89% (1 681/1 735) in stomach window, 98.73% (1 713/1 735) in duodenal bulb window, and 97.18% (1 686/1 735) in duodenal descending window. And those on the external validation dataset were 89.61% (716/799) in liver window, 92.74% (741/799) in stomach window, 90.11% (720/799) in duodenal bulb window, and 92.24% (737/799) in duodenal descending window. In the man-machine competition, the accuracy of the substation model was 89.09% (98/110), which was higher than that of senior endoscopists [85.45% (94/110), 74.55% (82/110), and 85.45% (94/110)] and close to the level of experts [92.73% (102/110) and 90.00% (99/110)].Conclusion:The deep learning-based EUS bile duct scanning system constructed in the current study can assist endoscopists to perform standard multi-station scanning in real time more accurately and improve the completeness and quality of EUS.

Objective:To evaluate the left ventricular myocardial strain in patients with light chain cardiac amyloidosis (AL-CA) with normal left ventricular ejection fraction (LVEF) by three-dimensional speckle tracking imaging(3D-STI), and to explore the clinical value of 3D-STI in predicting the prognosis of AL-CA patients with normal LVEF.Methods:A total of 80 patients with AL-CA and LVEF≥50% were retrospectively analyzed in the Xijing Hospital of Air Force Military Medical University from October 2014 to May 2020.According to whether the patients had endpoint events, they were divided into endpoint event group and non-endpoint event group. The clinical data, conventional echocardiographic parameters, 3D-STI related parameters and follow-up results were collected. Cox regression proportional hazards model was used to analyze the survival status of AL-CA patients with univariate and multivariate regression analyses, in order to find the relevant indicators of conventional echocardiography and 3D-STI to predict adverse events.Results:All patients were followed up for 20(7.3, 40.8) months. At the end of follow-up, 25 patients had all-cause deaths. Compared with the non-endpoint group, the endpoint event group had significantly increased left ventricular end diastolic maximum wall thickness (MLVWT), peak early diastolic flow velocity/peak early diastolic velocity at mitral annulus(E/e′) (all P<0.05), and decreased LVEF, left ventricular global longitudinal strain (GLS) and basal segment longitudinal strain (LS) (all P<0.05). Multivariate cox regression analysis after adjusting for age and gender showed that basal segment LS ( HR=0.812, 95% CI=0.675-0.976, P=0.026) was an independent predictor of end-point events in patients with AL-CA. Kaplan-Meier survival curve showed that AL-CA patients with basal segment LS≤13.07% were more likely to have endpoint events. Conclusions:Basal segment LS can be used as a predictor of endpoint events in patients with AL-CA.

Objective:To construct a deep learning-based diagnostic system for gastrointestinal submucosal tumor (SMT) under endoscopic ultrasonography (EUS), so as to help endoscopists diagnose SMT.Methods:From January 1, 2019 to December 15, 2021, at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University, 245 patients with SMT confirmed by pathological diagnosis who underwent EUS and endoscopic submucosal dissection were enrolled. A total of 3 400 EUS images were collected. Among the images, 2 722 EUS images were used for training of lesion segmentation model, while 2 209 EUS images were used for training of stromal tumor and leiomyoma classification model; 283 and 191 images were selected as independent test sets to evaluate lesion segmentation model and classification model, respectively. Thirty images were selected as an independent data set for human-machine competition to compare the lesion classification accuracy between lesion classification models and 6 endoscopists. The performance of the segmentation model was evaluated by indexes such as Intersection-over-Union and Dice coefficient. The performance of the classification model was evaluated by accuracy. Chi-square test was used for statistical analysis.Results:The average Intersection-over-Union and Dice coefficient of lesion segmentation model were 0.754 and 0.835, respectively, and the accuracy, recall and F1 score were 95.2%, 98.9% and 97.0%, respectively. Based on the lesion segmentation, the accuracy of classification model increased from 70.2% to 92.1%. The results of human-machine competition showed that the accuracy of classification model in differential diagnosis of stromal tumor and leiomyoma was 86.7% (26/30), which was superior to that of 4 out of the 6 endoscopists(56.7%, 17/30; 56.7%, 17/30; 53.3%, 16/30; 60.0%, 18/30; respectively), and the differences were statistically significant( χ2=7.11, 7.36, 8.10, 6.13; all P<0.05). There was no significant difference between the accuracy of the other 2 endoscopists(76.7%, 23/30; 73.3%, 22/30; respectively) and model(both P<0.05). Conclusion:This system could be used for the auxiliary diagnosis of SMT under ultrasonic endoscope in the future, and to provide a powerful evidence for the selection of subsequent treatment decisions.

Objective:To construct an intelligent performance measurement system of gastrointestinal endoscopy and to analyze its value for endoscopic quality improvement.Methods:The intelligent gastrointestinal endoscopy performance measurement system was developed by using the deep convolutional neural network (DCNN) and deep reinforcement learning, based on the Digital Imaging and Communications in Medicine. Images were acquired of patients undergoing gastrointestinal endoscopy at Digestive Endoscopy Center of Renmin Hospital of Wuhan University from December 2016 to October 2018. The system applied cecum recognition model (DCNN1), images in vitro and in vivo recognition model (DCNN2), and identification model at 26 gastric sites (DCNN3) to monitor indices such as cecal intubation rate, colonoscopic withdrawal time, gastroscopic inspection time, and gastroscopic coverage. Images of 83 gastroscopies and 205 colonoscopies acquired at Digestive Endoscopy Center of Renmin Hospital of Wuhan University from March to November 2019 were randomly selected to examine the effectiveness of the system. Results:The intelligent gastrointestinal endoscopy performance measurement system consisted of quality analysis of both gastroscopy and colonoscopy, including all indices, and could be generated automatically at any time. The accuracy for cecal intubation rate, colonoscopic withdrawal time, gastroscopic inspection time, and gastroscopic coverage were 92.5% (172/186), 91.7% (188/205), 100.0% (83/83), 89.3% (1 928/2 158), respectively.Conclusion:The intelligent performance measurement system for gastrointestinal endoscopy can be recommended for the quality control of gastrointestinal endoscopy, from which endoscopists can get feedback and improve the quality of gastrointestinal endoscopy.