The effect of incorporating domain knowledge with deep learning in identifying benign and malignant gastric whitish lesions: A retrospective study.

BACKGROUND AND AIM: Early whitish gastric neoplasms can be easily misdiagnosed; differential diagnosis of gastric whitish lesions remains a challenge. We aim to build a deep learning (DL) model to diagnose whitish gastric neoplasms and explore the effect of adding domain knowledge in model construction. METHODS: We collected 4558 images from two institutions to train and test models. We first developed two sole DL models (1 and 2) using supervised and semi-supervised algorithms. Then we selected diagnosis-related features through literature research and developed feature-extraction models to determine features including boundary, surface, roundness, depression, and location. Then predictions of the five feature-extraction models and sole DL model were combined and inputted into seven machine-learning (ML) based fitting-diagnosis models. The optimal model was selected as ENDOANGEL-WD (whitish-diagnosis) and compared with endoscopists. RESULTS: Sole DL 2 had higher sensitivity (83.12% vs 68.67%, Bonferroni adjusted P = 0.024) than sole DL 1. Adding domain knowledge, the decision tree performed best among the seven ML models, achieving higher specificity than DL 1 (84.38% vs 72.27%, Bonferroni adjusted P < 0.05) and higher accuracy than DL 2 (80.47%, Bonferroni adjusted P < 0.001) and was selected as ENDOANGEL-WD. ENDOANGEL-WD showed better accuracy compared with 10 endoscopists (75.70%, P < 0.001). CONCLUSIONS: We developed a novel system ENDOANGEL-WD combining domain knowledge and traditional DL to detect gastric whitish neoplasms. Adding domain knowledge improved the performance of traditional DL, which provided a novel solution for establishing diagnostic models for other rare diseases potentially.

A newly developed deep learning-based system for automatic detection and classification of small bowel lesions during double-balloon enteroscopy examination.

BACKGROUND: Double-balloon enteroscopy (DBE) is a standard method for diagnosing and treating small bowel disease. However, DBE may yield false-negative results due to oversight or inexperience. We aim to develop a computer-aided diagnostic (CAD) system for the automatic detection and classification of small bowel abnormalities in DBE. DESIGN AND METHODS: A total of 5201 images were collected from Renmin Hospital of Wuhan University to construct a detection model for localizing lesions during DBE, and 3021 images were collected to construct a classification model for classifying lesions into four classes, protruding lesion, diverticulum, erosion & ulcer and angioectasia. The performance of the two models was evaluated using 1318 normal images and 915 abnormal images and 65 videos from independent patients and then compared with that of 8 endoscopists. The standard answer was the expert consensus. RESULTS: For the image test set, the detection model achieved a sensitivity of 92% (843/915) and an area under the curve (AUC) of 0.947, and the classification model achieved an accuracy of 86%. For the video test set, the accuracy of the system was significantly better than that of the endoscopists (85% vs. 77 ± 6%, p < 0.01). For the video test set, the proposed system was superior to novices and comparable to experts. CONCLUSIONS: We established a real-time CAD system for detecting and classifying small bowel lesions in DBE with favourable performance. ENDOANGEL-DBE has the potential to help endoscopists, especially novices, in clinical practice and may reduce the miss rate of small bowel lesions.

An artificial intelligence system for chronic atrophic gastritis diagnosis and risk stratification under white light endoscopy.

BACKGROUND AND AIMS: The diagnosis and stratification of gastric atrophy (GA) predict patients' gastric cancer progression risk and determine endoscopy surveillance interval. We aimed to construct an artificial intelligence (AI) system for GA endoscopic identification and risk stratification based on the Kimura-Takemoto classification. METHODS: We constructed the system using two trained models and verified its performance. First, we retrospectively collected 869 images and 119 videos to compare its performance with that of endoscopists in identifying GA. Then, we included original image cases of 102 patients to validate the system for stratifying GA and comparing it with endoscopists with different experiences. RESULTS: The sensitivity of model 1 was higher than that of endoscopists (92.72% vs. 76.85 %) at image level and also higher than that of experts (94.87% vs. 85.90 %) at video level. The system outperformed experts in stratifying GA (overall accuracy: 81.37 %, 73.04 %, p = 0.045). The accuracy of this system in classifying non-GA, mild GA, moderate GA, and severe GA was 80.00 %, 77.42 %, 83.33 %, and 85.71 %, comparable to that of experts and better than that of seniors and novices. CONCLUSIONS: We established an expert-level system for GA endoscopic identification and risk stratification. It has great potential for endoscopic assessment and surveillance determinations.

Development and Evaluation of a Surveillance System for Follow-Up After Colorectal Polypectomy.

Importance: The adherence of physicians and patients to published colorectal postpolypectomy surveillance guidelines varies greatly, and patient follow-up is critical but time consuming. Objectives: To evaluate the accuracy of an automatic surveillance (AS) system in identifying patients after polypectomy, assigning surveillance intervals for different risks of patients, and proactively following up with patients on time. Design, Setting, and Participants: In this diagnostic/prognostic study, endoscopic and pathological reports of 47 544 patients undergoing colonoscopy at 3 hospitals between January 1, 2017, and June 30, 2022, were collected to develop an AS system based on natural language processing. The performance of the AS system was fully evaluated in internal and external tests according to 5 guidelines worldwide and compared with that of physicians. A multireader, multicase (MRMC) trial was conducted to evaluate use of the AS system and physician guideline adherence, and prospective data were collected to evaluate the success rate in contacting patients and the association with reduced human workload. Data analysis was conducted from July to September 2022. Exposures: Assistance of the AS system. Main Outcomes and Measures: The accuracy of the system in identifying patients after polypectomy, stratifying patient risk levels, and assigning surveillance intervals in internal (Renmin Hospital of Wuhan University), external 1 (Wenzhou Central Hospital), and external 2 (The First People's Hospital of Yichang) test sets; the accuracy of physicians and their time burden with and without system assistance; and the rate of successfully informed patients of the system were evaluated. Results: Test sets for 16 106 patients undergoing colonoscopy (mean [SD] age, 51.90 [13.40] years; 7690 females [47.75%]) were evaluated. In internal, external 1, and external 2 test sets, the system had an overall accuracy of 99.91% (95% CI, 99.83%-99.95%), 99.54% (95% CI, 99.30%-99.70%), and 99.77% (95% CI, 99.41%-99.91%), respectively, for identifying types of patients and achieved an overall accuracy of at least 99.30% (95% CI, 98.67%-99.63%) in the internal test set, 98.89% (95% CI, 98.33%-99.27%) in external test set 1, and 98.56% (95% CI, 95.86%-99.51%) in external test set 2 for stratifying patient risk levels and assigning surveillance intervals according to 5 guidelines. The system was associated with increased mean (SD) accuracy among physicians vs no AS system in 105 patients (98.67% [1.28%] vs 78.10% [18.01%]; P = .04) in the MRMC trial. In a prospective trial, the AS system successfully informed 82 of 88 patients (93.18%) and was associated with reduced burden of follow-up time vs no AS system (0 vs 2.86 h). Conclusions and Relevance: This study found that an AS system was associated with improved adherence to guidelines among physicians and reduced workload among physicians and nurses.

Exploring the challenge of early gastric cancer diagnostic AI system face in multiple centers and its potential solutions.

BACKGROUND: Artificial intelligence (AI) performed variously among test sets with different diversity due to sample selection bias, which can be stumbling block for AI applications. We previously tested AI named ENDOANGEL, diagnosing early gastric cancer (EGC) on single-center videos in man-machine competition. We aimed to re-test ENDOANGEL on multi-center videos to explore challenges applying AI in multiple centers, then upgrade ENDOANGEL and explore solutions to the challenge. METHODS: ENDOANGEL was re-tested on multi-center videos retrospectively collected from 12 institutions and compared with performance in previously reported single-center videos. We then upgraded ENDOANGEL to ENDOANGEL-2022 with more training samples and novel algorithms and conducted competition between ENDOANGEL-2022 and endoscopists. ENDOANGEL-2022 was then tested on single-center videos and compared with performance in multi-center videos; the two AI systems were also compared with each other and endoscopists. RESULTS: Forty-six EGCs and 54 non-cancers were included in multi-center video cohort. On diagnosing EGCs, compared with single-center videos, ENDOANGEL showed stable sensitivity (97.83% vs. 100.00%) while sharply decreased specificity (61.11% vs. 82.54%); ENDOANGEL-2022 showed similar tendency while achieving significantly higher specificity (79.63%, p < 0.01) making fewer mistakes on typical lesions than ENDOANGEL. On detecting gastric neoplasms, both AI showed stable sensitivity while sharply decreased specificity. Nevertheless, both AI outperformed endoscopists in the two competitions. CONCLUSIONS: Great increase of false positives is a prominent challenge for applying EGC diagnostic AI in multiple centers due to high heterogeneity of negative cases. Optimizing AI by adding samples and using novel algorithms is promising to overcome this challenge.

The effectiveness of a computer-aided system in improving the detection rate of gastric neoplasm and early gastric cancer: study protocol for a multi-centre, randomized controlled trial.

BACKGROUND: This protocol is for a multi-centre randomised controlled trial to determine whether the computer-aided system ENDOANGEL-GC improves the detection rates of gastric neoplasms and early gastric cancer (EGC) in routine oesophagogastroduodenoscopy (EGD). METHODS: Study design: Prospective, single-blind, parallel-group, multi-centre randomised controlled trial. SETTINGS: The computer-aided system ENDOANGEL-GC was used to monitor blind spots, detect gastric abnormalities, and identify gastric neoplasms during EGD. PARTICIPANTS: Adults who underwent screening, diagnosis, or surveillance EGD. Randomisation groups: 1. Experiment group, EGD examinations with the assistance of the ENDOANGEL-GC; 2. Control group, EGD examinations without the assistance of the ENDOANGEL-GC. RANDOMISATION: Block randomisation, stratified by centre. PRIMARY OUTCOMES: Detection rates of gastric neoplasms and EGC. SECONDARY OUTCOMES: Detection rate of premalignant gastric lesions, biopsy rate, observation time, and number of blind spots on EGD. BLINDING: Outcomes are undertaken by blinded assessors. SAMPLE SIZE: Based on the previously published findings and our pilot study, the detection rate of gastric neoplasms in the control group is estimated to be 2.5%, and that of the experimental group is expected to be 4.0%. With a two-sided α level of 0.05 and power of 80%, allowing for a 10% drop-out rate, the sample size is calculated as 4858. The detection rate of EGC in the control group is estimated to be 20%, and that of the experiment group is expected to be 35%. With a two-sided α level of 0.05 and power of 80%, a total of 270 cases of gastric cancer are needed. Assuming the proportion of gastric cancer to be 1% in patients undergoing EGD and allowing for a 10% dropout rate, the sample size is calculated as 30,000. Considering the larger sample size calculated from the two primary endpoints, the required sample size is determined to be 30,000. DISCUSSION: The results of this trial will help determine the effectiveness of the ENDOANGEL-GC in clinical settings. TRIAL REGISTRATION: ChiCTR (Chinese Clinical Trial Registry), ChiCTR2100054449, registered 17 December 2021.

A metal-organic framework-supported dinuclear iron catalyst for hydroboration of carbonyl compounds.

Preparation of catalytically active dinuclear transition metal complexes with an open coordination sphere is a challenging task because the metal sites tend to be "saturated" with excess donor atoms around during synthesis. By isolating the binding scaffolds with the metal-organic framework (MOF) skeleton and installing metal sites through post-synthetic modification, we succeed in constructing a MOF-supported metal catalyst, namely FICN-7-Fe2, with dinuclear Fe2 sites. FICN-7-Fe2 effectively catalyses the hydroboration of a broad range of ketone, aldehyde, and imine substrates with a low loading of 0.05 mol%. Remarkably, kinetic measurements showed that FICN-7-Fe2 is 15 times more active than its mononuclear counterpart FICN-7-Fe1, indicating that cooperative substrate activation on the two Fe centres significantly enhances the catalysis.

Explainable artificial intelligence incorporated with domain knowledge diagnosing early gastric neoplasms under white light endoscopy.

White light endoscopy is the most pivotal tool for detecting early gastric neoplasms. Previous artificial intelligence (AI) systems were primarily unexplainable, affecting their clinical credibility and acceptability. We aimed to develop an explainable AI named ENDOANGEL-ED (explainable diagnosis) to solve this problem. A total of 4482 images and 296 videos with focal lesions from 3279 patients from eight hospitals were used for training, validating, and testing ENDOANGEL-ED. A traditional sole deep learning (DL) model was trained using the same dataset. The performance of ENDOANGEL-ED and sole DL was evaluated on six levels: internal and external images, internal and external videos, consecutive videos, and man-machine comparison with 77 endoscopists in videos. Furthermore, a multi-reader, multi-case study was conducted to evaluate the ENDOANGEL-ED's effectiveness. A scale was used to compare the overall acceptance of endoscopists to traditional and explainable AI systems. The ENDOANGEL-ED showed high performance in the image and video tests. In man-machine comparison, the accuracy of ENDOANGEL-ED was significantly higher than that of all endoscopists in internal (81.10% vs. 70.61%, p < 0.001) and external videos (88.24% vs. 78.49%, p < 0.001). With ENDOANGEL-ED's assistance, the accuracy of endoscopists significantly improved (70.61% vs. 79.63%, p < 0.001). Compared with the traditional AI, the explainable AI increased the endoscopists' trust and acceptance (4.42 vs. 3.74, p < 0.001; 4.52 vs. 4.00, p < 0.001). In conclusion, we developed a real-time explainable AI that showed high performance, higher clinical credibility, and acceptance than traditional DL models and greatly improved the diagnostic ability of endoscopists.

An explainable artificial intelligence system for diagnosing Helicobacter Pylori infection under endoscopy: a case-control study.

Background: Changes in gastric mucosa caused by Helicobacter pylori (H. pylori) infection affect the observation of early gastric cancer under endoscopy. Although previous researches reported that computer-aided diagnosis (CAD) systems have great potential in the diagnosis of H. pylori infection, their explainability remains a challenge. Objective: We aim to develop an explainable artificial intelligence system for diagnosing H. pylori infection (EADHI) and giving diagnostic basis under endoscopy. Design: A case-control study. Methods: We retrospectively obtained 47,239 images from 1826 patients between 1 June 2020 and 31 July 2021 at Renmin Hospital of Wuhan University for the development of EADHI. EADHI was developed based on feature extraction combining ResNet-50 and long short-term memory networks. Nine endoscopic features were used for H. pylori infection. EADHI's performance was evaluated and compared to that of endoscopists. An external test was conducted in Wenzhou Central Hospital to evaluate its robustness. A gradient-boosting decision tree model was used to examine the contributions of different mucosal features for diagnosing H. pylori infection. Results: The system extracted mucosal features for diagnosing H. pylori infection with an overall accuracy of 78.3% [95% confidence interval (CI): 76.2-80.3]. The accuracy of EADHI for diagnosing H. pylori infection (91.1%, 95% CI: 85.7-94.6) was significantly higher than that of endoscopists (by 15.5%, 95% CI: 9.7-21.3) in internal test. And it showed a good accuracy of 91.9% (95% CI: 85.6-95.7) in external test. Mucosal edema was the most important diagnostic feature for H. pylori positive, while regular arrangement of collecting venules was the most important H. pylori negative feature. Conclusion: The EADHI discerns H. pylori gastritis with high accuracy and good explainability, which may improve the trust and acceptability of endoscopists on CADs. Plain language summary: An explainable AI system for Helicobacter pylori with good diagnostic performance Helicobacter pylori (H. pylori) is the main risk factor for gastric cancer (GC), and changes in gastric mucosa caused by H. pylori infection affect the observation of early GC under endoscopy. Therefore, it is necessary to identify H. pylori infection under endoscopy. Although previous research showed that computer-aided diagnosis (CAD) systems have great potential in H. pylori infection diagnosis, their generalization and explainability are still a challenge. Herein, we constructed an explainable artificial intelligence system for diagnosing H. pylori infection (EADHI) using images by case. In this study, we integrated ResNet-50 and long short-term memory (LSTM) networks into the system. Among them, ResNet50 is used for feature extraction, LSTM is used to classify H. pylori infection status based on these features. Furthermore, we added the information of mucosal features in each case when training the system so that EADHI could identify and output which mucosal features are contained in a case. In our study, EADHI achieved good diagnostic performance with an accuracy of 91.1% [95% confidence interval (CI): 85.7-94.6], which was significantly higher than that of endoscopists (by 15.5%, 95% CI: 9.7-21.3%) in internal test. In addition, it showed a good diagnostic accuracy of 91.9% (95% CI: 85.6-95.7) in external tests. The EADHI discerns H. pylori gastritis with high accuracy and good explainability, which may improve the trust and acceptability of endoscopists on CADs. However, we only used data from a single center to develop EADHI, and it was not effective in identifying past H. pylori infection. Future, multicenter, prospective studies are needed to demonstrate the clinical applicability of CADs.

Association between age at diabetes onset or diabetes duration and subsequent risk of pancreatic cancer: Results from a longitudinal cohort and mendelian randomization study.

Background: The aim of the study is to estimate the incidence of pancreatic cancer among individuals with new-onset type 2 Diabetes (T2DM) and evaluate the relationship of pancreatic cancer risk with age at diabetes onset and diabetes duration. Methods: This longitudinal cohort study included 428,362 new-onset T2DM patients in Shanghai and Mendelian randomization (MR) in the east-Asian population were used to investigate the association. Incidence rates of pancreatic cancer in all patients and by subgroups were calculated and compared to the general population. Findings: A total of 1056 incident pancreatic cancer cases were identified during eight consecutive years of follow-up. The overall pancreatic cancer annual incidence rate was 55·28/100,000 person years in T2DM patients, higher than that in the general population, with a standardized incidence ratio (SIR) of 1·54 (95% confidence interval [CI], 1·45-1·64). The incidence of pancreatic cancer increased with age and a significantly higher incidence was observed in the older groups with T2DM. However, the relative pancreatic cancer risk was inversely related to age of T2DM onset, and a higher SIR of 5·73 (95%CI, 4·49-7·22) was observed in the 20-54 years old group. The risk of pancreatic cancer was elevated at any diabetes duration. Fasting blood glucose ≥10·0 mmol/L was associated with increased risk of pancreatic cancer. MR analysis indicated a positive association between T2DM and pancreatic cancer risk. Interpretation: Efforts toward early and close follow-up programs, especially in individuals with young-onset T2DM, and the improvement of glucose control might represent effective strategies for improving the detection and results of treatment of pancreatic cancer. Funding: Chinese National Natural Science Foundation.

A deep-learning based system using multi-modal data for diagnosing gastric neoplasms in real-time (with video).

BACKGROUND: White light (WL) and weak-magnifying (WM) endoscopy are both important methods for diagnosing gastric neoplasms. This study constructed a deep-learning system named ENDOANGEL-MM (multi-modal) aimed at real-time diagnosing gastric neoplasms using WL and WM data. METHODS: WL and WM images of a same lesion were combined into image-pairs. A total of 4201 images, 7436 image-pairs, and 162 videos were used for model construction and validation. Models 1-5 including two single-modal models (WL, WM) and three multi-modal models (data fusion on task-level, feature-level, and input-level) were constructed. The models were tested on three levels including images, videos, and prospective patients. The best model was selected for constructing ENDOANGEL-MM. We compared the performance between the models and endoscopists and conducted a diagnostic study to explore the ENDOANGEL-MM's assistance ability. RESULTS: Model 4 (ENDOANGEL-MM) showed the best performance among five models. Model 2 performed better in single-modal models. The accuracy of ENDOANGEL-MM was higher than that of Model 2 in still images, real-time videos, and prospective patients. (86.54 vs 78.85%, P = 0.134; 90.00 vs 85.00%, P = 0.179; 93.55 vs 70.97%, P < 0.001). Model 2 and ENDOANGEL-MM outperformed endoscopists on WM data (85.00 vs 71.67%, P = 0.002) and multi-modal data (90.00 vs 76.17%, P = 0.002), significantly. With the assistance of ENDOANGEL-MM, the accuracy of non-experts improved significantly (85.75 vs 70.75%, P = 0.020), and performed no significant difference from experts (85.75 vs 89.00%, P = 0.159). CONCLUSIONS: The multi-modal model constructed by feature-level fusion showed the best performance. ENDOANGEL-MM identified gastric neoplasms with good accuracy and has a potential role in real-clinic.

Evaluating the effect of an artificial intelligence system on the anesthesia quality control during gastrointestinal endoscopy with sedation: a randomized controlled trial.

BACKGROUND: Sedative gastrointestinal endoscopy is extensively used worldwide. An appropriate degree of sedation leads to more acceptability and satisfaction. Artificial intelligence has rapidly developed in the field of digestive endoscopy in recent years and we have constructed a mature computer-aided diagnosis (CAD) system. This system can identify the remaining parts to be examined in real-time endoscopic procedures, which may help anesthetists use anesthetics properly to keep patients in an appropriate degree of sedation. AIMS: This study aimed to evaluate the effects of the CAD system on anesthesia quality control during gastrointestinal endoscopy. METHODS: We recruited 154 consecutive patients at Renmin Hospital of Wuhan University, including 76 patients in the CAD group and 78 in the control group. Anesthetists in the CAD group were able to see the CAD system's indications, while anesthetists in the control group could not. The primary outcomes included emergence time (from examination completion to spontaneous eye opening when doctors called the patients' names), recovery time (from examination completion to achievement of the primary recovery endpoints) and patient satisfaction scores. The secondary outcomes included anesthesia induction time (from sedative administration to successful sedation), procedure time (from scope insertion to scope withdrawal), total dose of propofol, vital signs, etc. This trial was registered in the Primary Registries of the WHO Registry Network, with registration number ChiCTR2100042621. RESULTS: Emergence time in the CAD group was significantly shorter than that in the control group (p < 0.01). The recovery time was also significantly shorter in the CAD group (p < 0.01). Patients in the CAD group were significantly more satisfied with their sedation than those in control group (p < 0.01). Vital signs were stable during the examinations in both groups. Propofol doses during the examinations were comparable between the two groups. CONCLUSION: This CAD system possesses great potential for anesthesia quality control. It can improve patient satisfaction during endoscopic examinations with sedation. TRIAL REGISTRATION: ChiCTR2100042621.

Development and validation of a feature extraction-based logical anthropomorphic diagnostic system for early gastric cancer: A case-control study.

Background: Prompt diagnosis of early gastric cancer (EGC) is crucial for improving patient survival. However, most previous computer-aided-diagnosis (CAD) systems did not concretize or explain diagnostic theories. We aimed to develop a logical anthropomorphic artificial intelligence (AI) diagnostic system named ENDOANGEL-LA (logical anthropomorphic) for EGCs under magnifying image enhanced endoscopy (M-IEE). Methods: We retrospectively collected data for 692 patients and 1897 images from Renmin Hospital of Wuhan University, Wuhan, China between Nov 15, 2016 and May 7, 2019. The images were randomly assigned to the training set and test set by patient with a ratio of about 4:1. ENDOANGEL-LA was developed based on feature extraction combining quantitative analysis, deep learning (DL), and machine learning (ML). 11 diagnostic feature indexes were integrated into seven ML models, and an optimal model was selected. The performance of ENDOANGEL-LA was evaluated and compared with endoscopists and sole DL models. The satisfaction of endoscopists on ENDOANGEL-LA and sole DL model was also compared. Findings: Random forest showed the best performance, and demarcation line and microstructures density were the most important feature indexes. The accuracy of ENDOANGEL-LA in images (88.76%) was significantly higher than that of sole DL model (82.77%, p = 0.034) and the novices (71.63%, p<0.001), and comparable to that of the experts (88.95%). The accuracy of ENDOANGEL-LA in videos (87.00%) was significantly higher than that of the sole DL model (68.00%, p<0.001), and comparable to that of the endoscopists (89.00%). The accuracy (87.45%, p<0.001) of novices with the assistance of ENDOANGEL-LA was significantly improved. The satisfaction of endoscopists on ENDOANGEL-LA was significantly higher than that of sole DL model. Interpretation: We established a logical anthropomorphic system (ENDOANGEL-LA) that can diagnose EGC under M-IEE with diagnostic theory concretization, high accuracy, and good explainability. It has the potential to increase interactivity between endoscopists and CADs, and improve trust and acceptability of endoscopists for CADs. Funding: This work was partly supported by a grant from the Hubei Province Major Science and Technology Innovation Project (2018-916-000-008) and the Fundamental Research Funds for the Central Universities (2042021kf0084).

A deep learning-based system for real-time image reporting during esophagogastroduodenoscopy: a multicenter study.

BACKGROUND AND STUDY AIMS: Endoscopic reports are essential for the diagnosis and follow-up of gastrointestinal diseases. This study aimed to construct an intelligent system for automatic photo documentation during esophagogastroduodenoscopy (EGD) and test its utility in clinical practice. PATIENTS AND METHODS: Seven convolutional neural networks trained and tested using 210,198 images were integrated to construct the endoscopic automatic image reporting system (EAIRS). We tested its performance through man-machine comparison at three levels: internal, external, and prospective test. Between May 2021 and June 2021, patients undergoing EGD at Renmin Hospital of Wuhan University were recruited. The primary outcomes were accuracy for capturing anatomical landmarks, completeness for capturing anatomical landmarks, and detected lesions. RESULTS: The EAIRS outperformed endoscopists in retrospective internal and external test. A total of 161 consecutive patients were enrolled in the prospective test. The EAIRS achieved an accuracy of 95.2% in capturing anatomical landmarks in the prospective test. It also achieved higher completeness on capturing anatomical landmarks compared with endoscopists: (93.1% vs. 88.8%), and was comparable to endoscopists on capturing detected lesions: (99.0% vs. 98.0%). CONCLUSIONS: The EAIRS can generate qualified image reports and could be a powerful tool for generating endoscopic reports in clinical practice.

Deep learning system compared with expert endoscopists in predicting early gastric cancer and its invasion depth and differentiation status (with videos).

BACKGROUND AND AIMS: We aimed to develop and validate a deep learning-based system that covers various aspects of early gastric cancer (EGC) diagnosis, including detecting gastric neoplasm, identifying EGC, and predicting EGC invasion depth and differentiation status. Herein, we provide a state-of-the-art comparison of the system with endoscopists using real-time videos in a nationwide human-machine competition. METHODS: This multicenter, prospective, real-time, competitive comparative, diagnostic study enrolled consecutive patients who received magnifying narrow-band imaging endoscopy at the Peking University Cancer Hospital from June 9, 2020 to November 17, 2020. The offline competition was conducted in Wuhan, China, and the endoscopists and the system simultaneously read patients' videos and made diagnoses. The primary outcomes were sensitivity in detecting neoplasms and diagnosing EGCs. RESULTS: One hundred videos, including 37 EGCs and 63 noncancerous lesions, were enrolled; 46 endoscopists from 44 hospitals in 19 provinces in China participated in the competition. The sensitivity rates of the system for detecting neoplasms and diagnosing EGCs were 87.81% and 100%, respectively, significantly higher than those of endoscopists (83.51% [95% confidence interval [CI], 81.23-85.79] and 87.13% [95% CI, 83.75-90.51], respectively). Accuracy rates of the system for predicting EGC invasion depth and differentiation status were 78.57% and 71.43%, respectively, slightly higher than those of endoscopists (63.75% [95% CI, 61.12-66.39] and 64.41% [95% CI, 60.65-68.16], respectively). CONCLUSIONS: The system outperformed endoscopists in identifying EGCs and was comparable with endoscopists in predicting EGC invasion depth and differentiation status in videos. This deep learning-based system could be a powerful tool to assist endoscopists in EGC diagnosis in clinical practice.

Calmodulin 2 Facilitates Angiogenesis and Metastasis of Gastric Cancer via STAT3/HIF-1A/VEGF-A Mediated Macrophage Polarization.

BACKGROUND: Tumor-associated macrophages (TAMs) are indispensable to mediating the connections between cells in the tumor microenvironment. In this study, we intended to research the function and mechanism of Calmodulin2 (CALM2) in gastric cancer (GC)-TAM microenvironment. MATERIALS AND METHODS: CALM2 expression in GC tissues and GC cells was determined through quantitative real-time PCR (qRT-PCR) and immunohistochemistry (IHC). The correlation between CALM2 level and the survival rate of GC patients was assessed. The CALM2 overexpression or knockdown model was constructed to evaluate its role in GC cell proliferation, migration, and invasion. THP1 cells or HUVECs were co-cultured with the conditioned medium of GC cells. Tubule formation experiment was done to examine the angiogenesis of endothelial cells. The proliferation, migration, and polarization of THP1 cells were measured. A xenograft model was set up in BALB/c male nude mice to study CALM2x's effects on tumor growth and lung metastasis in vivo. Western Blot (WB) checked the profile of JAK2/STAT3/HIF-1/VEGFA in GC tissues and cells. RESULTS: In GC tissues and cell lines, CALM2 expression was elevated and positively relevant to the poor prognosis of GC patients. In in-vitro experiments, CALM2 overexpression or knockdown could facilitate or curb the proliferation, migration, invasion, and angiogenesis of HUVECs and M2 polarization of THP1 cells. In in-vivo experiments, CALM2 boosted tumor growth and lung metastasis. Mechanically, CALM2 could arouse the JAK2/STAT3/HIF-1/VEGFA signaling. It was also discovered that JAK2 and HIF-1A inhibition could attenuate the promoting effects of CALM2 on GC, HUVECs cells, and macrophages. CONCLUSION: CALM2 modulates the JAK2/STAT3/HIF-1/VEGFA axis and bolsters macrophage polarization, thus facilitating GC metastasis and angiogenesis.

Effect of a deep learning-based system on the miss rate of gastric neoplasms during upper gastrointestinal endoscopy: a single-centre, tandem, randomised controlled trial.

BACKGROUND: White light endoscopy is a pivotal first-line tool for the detection of gastric neoplasms. However, gastric neoplasms can be missed during upper gastrointestinal endoscopy due to the subtle nature of these lesions and varying skill among endoscopists. Here, we aimed to evaluate the effect of an artificial intelligence (AI) system designed to detect focal lesions and diagnose gastric neoplasms on reducing the miss rate of gastric neoplasms in clinical practice. METHODS: This single-centre, randomised controlled, tandem trial was done at Renmin Hospital of Wuhan University, China. We recruited consecutive patients (≥18 years old) undergoing routine upper gastrointestinal endoscopy for screening, surveillance, or investigation of symptoms. Same-day tandem upper gastrointestinal endoscopy was done where patients first underwent either AI-assisted (AI-first) or routine (routine-first) white light endoscopy, followed immediately by the other procedure, with targeted biopsies for all detected lesions taken at the end of the second examination. Patients were randomly assigned (1:1) to the AI-first or routine-first group using a computer-generated random numerical series and block randomisation (block size of four). Endoscopists were not blinded to randomisation status, whereas patients and pathologists were. The primary endpoint was the miss rate of gastric neoplasms and the analysis was done per protocol. This trial is registered with the Chinese Clinical Trial Registry, ChiCTR2000034453, and has been completed. FINDINGS: Between July 6, 2020, and Dec 11, 2020, 907 patients were randomly assigned to the AI-first group and 905 to the routine-first group. The gastric neoplasm miss rate was significantly lower in the AI-first group than in the routine-first group (6·1%, 95% CI 1·6-17·9 [3/49] vs 27·3%, 15·5-43·0 [12/44]; relative risk 0·224, 95% CI 0·068-0·744; p=0·015). The only reported adverse event was bleeding from a target lesion after biopsy. INTERPRETATION: The use of an AI system during upper gastrointestinal endoscopy significantly reduced the gastric neoplasm miss rate. AI-assisted endoscopy has the potential to improve the yield of gastric neoplasms by endoscopists. FUNDING: The Project of Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision and the Hubei Province Major Science and Technology Innovation Project.

Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial.

BACKGROUND: Esophagogastroduodenoscopy (EGD) is a prerequisite for detecting upper gastrointestinal lesions especially early gastric cancer (EGC). An artificial intelligence system has been shown to monitor blind spots during EGD. In this study, we updated the system (ENDOANGEL), verified its effectiveness in improving endoscopy quality, and pretested its performance in detecting EGC in a multicenter randomized controlled trial. METHODS: ENDOANGEL was developed using deep convolutional neural networks and deep reinforcement learning. Patients undergoing EGD in five hospitals were randomly assigned to the ENDOANGEL-assisted group or to a control group without use of ENDOANGEL. The primary outcome was the number of blind spots. Secondary outcomes included performance of ENDOANGEL in predicting EGC in a clinical setting. RESULTS: 1050 patients were randomized, and 498 and 504 patients in the ENDOANGEL and control groups, respectively, were analyzed. Compared with the control group, the ENDOANGEL group had fewer blind spots (mean 5.38 [standard deviation (SD) 4.32] vs. 9.82 [SD 4.98]; P < 0.001) and longer inspection time (5.40 [SD 3.82] vs. 4.38 [SD 3.91] minutes; P < 0.001). In the ENDOANGEL group, 196 gastric lesions with pathological results were identified. ENDOANGEL correctly predicted all three EGCs (one mucosal carcinoma and two high grade neoplasias) and two advanced gastric cancers, with a per-lesion accuracy of 84.7 %, sensitivity of 100 %, and specificity of 84.3 % for detecting gastric cancer. CONCLUSIONS: In this multicenter study, ENDOANGEL was an effective and robust system to improve the quality of EGD and has the potential to detect EGC in real time.

Automated and real-time validation of gastroesophageal varices under esophagogastroduodenoscopy using a deep convolutional neural network: a multicenter retrospective study (with video).

BACKGROUND AND AIMS: Rupture of gastroesophageal varices is the most common fatal adverse event of cirrhosis. EGD is considered the criterion standard for diagnosis and risk stratification of gastroesophageal variceal bleeding. The aim of this study was to train and validate a real-time deep convolutional neural network (DCNN) system, named ENDOANGEL, for diagnosing gastroesophageal varices and predicting the risk of rupture. METHODS: After training with 8566 images of endoscopic gastroesophageal varices from 3021 patients and 6152 images of normal esophagus/stomach from 3168 patients, ENDOANGEL was also tested with independent images and videos. It was also compared with endoscopists in several aspects. RESULTS: ENDOANGEL, in contrast with endoscopists, displayed higher accuracy of 97.00% and 92.00% in terms of detecting esophageal varices (EVs) and gastric varices (GVs) in an image contest (97.00% vs 93.94% , P < .01; 92.00% vs 84.43%, P < .05). It also surpassed endoscopists for red color signs of EVs and red spots of GVs (84.21% vs 73.45%, P < .01; 85.26% vs 77.52%, P < .05). Moreover, ENDOANGEL achieved comparable performance in the determination of size, form, color, and bleeding signs. ENDOANGEL also had good performance in making treatment suggestions. With regard to predicting risk factors in multicenter videos, ENDOANGEL showed great stability. CONCLUSIONS: Our data suggest that DCNNs were precise in detecting both EVs and GVs and performed excellently in uncovering the endoscopic risk factors of gastroesophageal variceal bleeding. Thus, the application of DCNNs will assist endoscopists in evaluating gastroesophageal varices more objectively and precisely. (Clinical trial registration number: ChiCTR1900023970.).