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

Systematic review of machine learning models in predicting the risk of bleed/grade of esophageal varices in patients with liver cirrhosis: A comprehensive methodological analysis

Esophageal varices (EV) in liver cirrhosis carry high mortality risks. Traditional endoscopy, which is costly and subjective, prompts a shift towards machine learning (ML). This review critically evaluates ML applications in predicting bleeding risks and grading EV in patients with liver cirrhosis. Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we conducted a systematic review of studies using ML to predict the risk of variceal bleeding and/or grade EV in liver disease patients. Data extraction and bias assessment followed the CHARMS (CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modeling Studies) checklist and PROBAST (Prediction model Risk Of Bias Assessment Tool) tool, respectively. Due to the heterogeneity of the study, a meta-analysis was not feasible; instead, descriptive statistics summarized the findings. Twelve studies were included, highlighting the use of various ML models such as extreme gradient boosting, artificial neural networks, and convolutional neural networks. These studies demonstrated high predictive accuracy, with some models achieving area under the curve values above 99%. However, significant heterogeneity was noted in input variables, methodologies, and outcome measures. Moreover, a substantial portion of the studies exhibited unclear or high risk of bias, mainly due to insufficient participant numbers, unclear handling of missing data, and a lack of detailed reporting on endoscopic procedures. ML models show significant promise in predicting the risk of variceal bleeding and grading EV in patients with cirrhosis, potentially reducing the need for invasive procedures. Nonetheless, the current literature reveals considerable heterogeneity and methodological limitations, including high or unclear risks of bias. Future research should focus on larger, prospective trials and the standardization of ML assessment criteria to confirm these models' practical utility in clinical settings.

The Prediction and Treatment of Bleeding Esophageal Varices in the Artificial Intelligence Era: A Review

Esophageal varices (EVs), a significant complication of cirrhosis, present a considerable challenge in clinical practice due to their high risk of bleeding and associated morbidity and mortality. This manuscript explores the transformative role of artificial intelligence (AI) in the management of EV, particularly in enhancing diagnostic accuracy and predicting bleeding risks. It underscores the potential of AI in offering noninvasive, efficient alternatives to traditional diagnostic methods such as esophagogastroduodenoscopy (EGD). The complexity of EV management is highlighted, necessitating a multidisciplinary approach that includes pharmacological therapy, endoscopic interventions, and, in some cases, surgical options tailored to individual patient profiles. Additionally, the paper emphasizes the importance of integrating AI into medical education and practice, preparing healthcare professionals for the evolving landscape of medical technology. It projects a future where AI significantly influences the management of gastrointestinal bleeding, improving clinical decision-making, patient outcomes, and overall healthcare efficiency. The study advocates for a patient-centered approach in healthcare, balancing the incorporation of innovative technologies with ethical principles and the diverse needs of patients to optimize treatment efficacy and enhance healthcare accessibility.

A study on the improvement in the ability of endoscopists to diagnose gastric neoplasms using an artificial intelligence system

Background

Artificial intelligence-assisted gastroscopy (AIAG) based on deep learning has been validated in various scenarios, but there is a lack of studies regarding diagnosing neoplasms under white light endoscopy. This study explored the potential role of AIAG systems in enhancing the ability of endoscopists to diagnose gastric tumor lesions under white light.

Methods

A total of 251 patients with complete pathological information regarding electronic gastroscopy, biopsy, or ESD surgery in Xi'an Gaoxin Hospital were retrospectively collected and comprised 64 patients with neoplasm lesions (excluding advanced cancer) and 187 patients with non-neoplasm lesions. The diagnosis competence of endoscopists with intermediate experience and experts was compared for gastric neoplasms with or without the assistance of AIAG, which was developed based on ResNet-50.

Results

For the 251 patients with difficult clinical diagnoses included in the study, compared with endoscopists with intermediate experience, AIAG's diagnostic competence was much higher, with a sensitivity of 79.69% (79.69% vs. 72.50%, p = 0.012) and a specificity of 73.26% (73.26% vs. 52.62%, p < 0.001). With the help of AIAG, the endoscopists with intermediate experience (<8 years) demonstrated a relatively higher specificity (59.79% vs. 52.62%, p < 0.001). Experts (≥8 years) had similar results with or without AI assistance (with AI vs. without AI; sensitivities, 70.31% vs. 67.81%, p = 0.358; specificities, 83.85% vs. 85.88%, p = 0.116).

Conclusion

With the assistance of artificial intelligence (AI) systems, the ability of endoscopists with intermediate experience to diagnose gastric neoplasms is significantly improved, but AI systems have little effect on experts.

Applications of artificial intelligence in gastroscopy: a narrative review

Gastroscopy, a critical tool for the diagnosis of upper gastrointestinal diseases, has recently incorporated artificial intelligence (AI) technology to alleviate the challenges involved in endoscopic diagnosis of some lesions, thereby enhancing diagnostic accuracy. This narrative review covers the current status of research concerning various applications of AI technology to gastroscopy, then discusses future research directions. By providing this review, we hope to promote the integration of gastroscopy and AI technology, with long-term clinical applications that can assist patients.

Diagnosis and Management of Esophagogastric Varices

Acute variceal bleeding (AVB) is a potentially fatal complication of clinically significant portal hypertension and is one of the most common causes of acute upper gastrointestinal bleeding. Thus, esophagogastric varices represent a major economic and population health issue. Patients with advanced chronic liver disease typically undergo an upper endoscopy to screen for esophagogastric varices. However, upper endoscopy is not recommended for patients with liver stiffness < 20 KPa and platelet count > 150 × 10⁹/L as there is a low probability of high-risk varices. Patients with high-risk varices should receive primary prophylaxis with either nonselective beta-blockers or endoscopic band ligation. In cases of AVB, patients should receive upper endoscopy within 12 h after resuscitation and hemodynamic stability, whereas endoscopy should be performed as soon as possible if patients are unstable. In cases of suspected variceal bleeding, starting vasoactive therapy as soon as possible in combination with endoscopic treatment is recommended. On the other hand, in cases of uncontrolled bleeding, balloon tamponade or self-expandable metal stents can be used as a bridge to more definitive therapy such as transjugular intrahepatic portosystemic shunt. This article aims to offer a comprehensive review of recommendations from international guidelines as well as recent updates on the management of esophagogastric varices.

An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding

Bleeding risk factors for gastroesophageal varices (GEV) detected by endoscopy in cirrhotic patients determine the prophylactical treatment patients will undergo in the following 2 years. We propose a methodology for measuring the risk factors. We create an artificial intelligence system (ENDOANGEL-GEV) containing six models to segment GEV and to classify the grades (grades 1-3) and red color signs (RC, RC0-RC3) of varices. It also summarizes changes in the above results with region in real time. ENDOANGEL-GEV is trained using 6034 images from 1156 cirrhotic patients across three hospitals (dataset 1) and validated on multicenter datasets with 11009 images from 141 videos (dataset 2) and in a prospective study recruiting 161 cirrhotic patients from Renmin Hospital of Wuhan University (dataset 3). In dataset 1, ENDOANGEL-GEV achieves intersection over union values of 0.8087 for segmenting esophageal varices and 0.8141 for gastric varices. In dataset 2, the system maintains fairly accuracy across images from three hospitals. In dataset 3, ENDOANGEL-GEV surpasses attended endoscopists in detecting RC of GEV and classifying grades (p < 0.001). When ranking the risk of patients combined with the Child‒Pugh score, ENDOANGEL-GEV outperforms endoscopists for esophageal varices (p < 0.001) and shows comparable performance for gastric varices (p = 0.152). Compared with endoscopists, ENDOANGEL-GEV may help 12.31% (16/130) more patients receive the right intervention. We establish an interpretable system for the endoscopic diagnosis and risk stratification of GEV. It will assist in detecting the first bleeding risk factors accurately and expanding the scope of quantitative measurement of diseases.

Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video)

The artificial intelligence (AI)-assisted endoscopic detection of early gastric cancer (EGC) has been preliminarily developed. The currently used algorithms still exhibit limitations of large calculation and low-precision expression. The present study aimed to develop an endoscopic automatic detection system in EGC based on a mask region-based convolutional neural network (Mask R-CNN) and to evaluate the performance in controlled trials. For this purpose, a total of 4,471 white light images (WLIs) and 2,662 narrow band images (NBIs) of EGC were obtained for training and testing. In total, 10 of the WLIs (videos) were obtained prospectively to examine the performance of the RCNN system. Furthermore, 400 WLIs were randomly selected for comparison between the Mask R-CNN system and doctors. The evaluation criteria included accuracy, sensitivity, specificity, positive predictive value and negative predictive value. The results revealed that there were no significant differences between the pathological diagnosis with the Mask R-CNN system in the WLI test (χ² = 0.189, P=0.664; accuracy, 90.25%; sensitivity, 91.06%; specificity, 89.01%) and in the NBI test (χ² = 0.063, P=0.802; accuracy, 95.12%; sensitivity, 97.59%). Among 10 WLI real-time videos, the speed of the test videos was up to 35 frames/sec, with an accuracy of 90.27%. In a controlled experiment of 400 WLIs, the sensitivity of the Mask R-CNN system was significantly higher than that of experts (χ² = 7.059, P=0.000; 93.00% VS 80.20%), and the specificity was higher than that of the juniors (χ² = 9.955, P=0.000, 82.67% VS 71.87%), and the overall accuracy rate was higher than that of the seniors (χ² = 7.009, P=0.000, 85.25% VS 78.00%). On the whole, the present study demonstrates that the Mask R-CNN system exhibited an excellent performance status for the detection of EGC, particularly for the real-time analysis of WLIs. It may thus be effectively applied to clinical settings.

Endoscopic Treatment of Esophageal Varices

Acute variceal bleeding is a complication of portal hypertension, usually due to cirrhosis, with high morbidity and mortality. There are 3 scenarios for endoscopic treatment of esophageal varices: prevention of first variceal bleed, treatment of active variceal bleed, and prevention of rebleeding. Patients with cirrhosis should be screened for esophageal varices. Recommended endoscopic therapy for acute variceal bleeding is endoscopic variceal banding. Although banding is the first-choice treatment, sclerotherapy may have a role. Treatment with Sengstaken-Blakemore tube or self-expanding covered metallic esophageal stent can be used for acute variceal bleeding refractory to standard pharmacologic and endoscopic therapy.

Artificial Intelligence in the Analysis of Upper Gastrointestinal Disorders

In the past, conventional machine learning was applied to analyze tabulated medical data while deep learning was applied to study afflictions such as gastrointestinal disorders. Neural networks were used to detect, classify, and delineate various images of lesions because the local feature selection and optimization of the deep learning model enabled accurate image analysis. With the accumulation of medical records, the evolution of computational power and graphics processing units, and the widespread use of open-source libraries in large-scale machine learning processes, medical artificial intelligence (AI) is overcoming its limitations. While early studies prioritized the automatic diagnosis of cancer or pre-cancerous lesions, the current expanded scope of AI includes benign lesions, quality control, and machine learning analysis of big data. However, the limited commercialization of medical AI and the need to justify its application in each field of research are restricting factors. Modeling assumes that observations follow certain statistical rules, and external validation checks whether assumption is correct or generalizable. Therefore, unused data are essential in the training or internal testing process to validate the performance of the established AI models. This article summarizes the studies on the application of AI models in upper gastrointestinal disorders. The current limitations and the perspectives on future development have also been discussed.

Convolutional neural network-based object detection model to identify gastrointestinal stromal tumors in endoscopic ultrasound images

BACKGROUND AND AIM

We aimed to develop a convolutional neural network (CNN)-based object detection model for the discrimination of gastric subepithelial tumors, such as gastrointestinal stromal tumors (GISTs), and leiomyomas, in endoscopic ultrasound (EUS) images.

METHODS

We used 376 images from 114 patients with histologically confirmed gastric GIST or leiomyoma to train the EUS-CNN. We constructed the EUS-CNN using an EfficientNet CNN model for feature extraction and a weighted bi-directional feature pyramid network for object detection. We assessed the performance of our EUS-CNN by calculating its accuracy, sensitivity, specificity, and area under receiver operating characteristic curve (AUC) using a validation set of 170 images from 54 patients. Four EUS experts and 15 EUS trainees were asked to judge the same validation dataset, and the diagnostic yields were compared between the EUS-CNN and human assessments.

RESULTS

In the per-image analysis, the sensitivity, specificity, accuracy, and AUC of our EUS-CNN were 95.6%, 82.1%, 91.2%, and 0.9234, respectively. In the per-patient analysis, the sensitivity, specificity, accuracy, and AUC for our object detection model were 100.0%, 85.7%, 96.3%, and 0.9929, respectively. The EUS-CNN outperformed human assessment in terms of accuracy, sensitivity, and negative predictive value.

CONCLUSIONS

We developed the EUS-CNN system, which demonstrated high diagnostic ability for gastric GIST prediction. This EUS-CNN system can be helpful not only for less-experienced endoscopists but also for experienced ones. Additional EUS image accumulation and prospective studies are required alongside validation in a large multicenter trial.

Artificial intelligence in the diagnosis of cirrhosis and portal hypertension

Clinically significant portal hypertension is associated with an increased risk of developing gastroesophageal varices and hepatic decompensation. Hepatic venous pressure gradient measurement and esophagogastroduodenoscopy are the gold-standard methods for assessing clinically significant portal hypertension and gastroesophageal varices, respectively. However, invasiveness, cost, and feasibility limit their widespread use, especially if repeated and serial evaluations are required to assess the efficacy of pharmacotherapy. Artificial intelligence describes a range of techniques that allow machines to perform tasks typically thought to require human reasoning and problem-solving skills. Artificial intelligence has made great strides in the field of medicine, and is also involved in portal hypertension diagnosis. Artificial intelligence tools will potentially transform our practice by leveraging massive amounts of data to personalize care to the right patient, in the right amount, at the right time. This review focuses on the recent advances in artificial intelligence for the noninvasive diagnosis of portal hypertension and gastroesophageal varices and monitoring of risk assessment of its complications in clinical practice.

Artificial intelligence in the diagnosis of gastric precancerous conditions by image-enhanced endoscopy: a multicenter, diagnostic study (with video)

BACKGROUND AND AIMS

Gastric precancerous conditions, including gastric atrophy (GA) and intestinal metaplasia (IM), play an important role in the development of gastric cancer. Image-enhanced endoscopy (IEE) shows great potential in diagnosing gastric precancerous conditions and adenocarcinoma. In this study, a deep convolutional neural network system, named ENDOANGEL, was constructed to detect gastric precancerous conditions by IEE.

METHODS

Endoscopic images were retrospectively obtained from 5 hospitals in China for the development, validation, and internal and external test of the system. Prospective consecutive patients receiving IEE were enrolled from January 13, 2020 to October 29, 2020 in Renmin Hospital of Wuhan University to assess in real time the applicability of the proposed computer-aided detection (CADe) system in clinical practice, and the performance of CADe was compared with that of endoscopists.

RESULTS

Six thousand two hundred fifty endoscopic images from 760 patients and 98 video clips from 77 individuals undergoing IEE were enrolled in this study. The diagnostic accuracy of GA was .901 (95% confidence interval [CI], .883-.917) in the internal test set, .864 (95% CI, .842-.884) in the multicenter external test set, and .878 (95% CI, .796-.935) in the prospective video test set. The diagnostic accuracy of IM was .908 (95% CI, .889-.924) in the internal test set, .859 (95% CI, .837-.880) in the multicenter external test set, and .898 (95% CI, .820-.950) in the prospective video test set. CADe achieved similar diagnostic accuracy to that of the experts for detecting GA (.869 [95% CI, .790-.927] vs .846 [95% CI, .808-.879], P = .396) and IM (.888 [95% CI, .812-.941] vs .820 [95% CI, .780-.855], P = .117) and was superior to that of nonexperts for GA (.750 [95% CI, .711-.786], P = .008) and IM (.736 [95% CI, .697-.773], P = .028).

CONCLUSIONS

CADe achieved high diagnostic accuracy in gastric precancerous conditions, which was similar to that of experts and superior to that of nonexperts. Thus, CADe provides possibilities for a wide application in assisting in the diagnosis of gastric precancerous conditions.