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

Efficacy of a real-time intelligent quality-control system for the detection of early upper gastrointestinal neoplasms: a multicentre, single-blinded, randomised controlled trial

Background

Oesophagogastroduodenoscopy (OGD) quality and identification of the early upper gastrointestinal (UGI) neoplasm play an important role in detecting the UGI neoplasm. However, the optimal method for quality control in daily OGD procedures is currently lacking. We aimed to evaluate the efficacy of a real-time intelligent quality-control system (IQCS), which combines OGD quality control with lesion detection of early UGI neoplasms.

Methods

We performed a multicentre, single-blinded, randomised controlled trial at 6 hospitals in China. Patients aged 40-80 years old who underwent painless OGD were screened for enrolment in this study. Patients with a history of advanced UGI cancer, stenosis, or obstruction in UGI tract were excluded. Eligible subjects were randomly assigned (1:1) to either the routine or IQCS group to undergo standard OGD examination and OGD examination aided by IQCS, respectively. Patients were masked to the randomisation status. The primary outcome was the detection of early UGI neoplasms. All analyses were done on a per-protocol basis. This trial is registered with ClinicalTrials.gov, NCT04720924.

Findings

Between January 16, 2021 and December 23, 2022, 1840 patients were randomised (IQCS group: 919, routine group: 921). The full analysis set consisted of 914 in the IQCS group and 915 in the routine group. The early UGI neoplasms detection rate in the IQCS group (6.1%, 56/914) was significantly higher than in the routine group (2.3%, 21/915; P = 0.0001). The IQCS group had fewer blind spots (2.3 vs. 6.2, P < 0.0001). The IQCS group had higher stomach cleanliness on cardia or fundus (99.5% vs. 87.9%, P < 0.0001), body (98.9% vs. 88.0%, P < 0.0001), angulus (99.8% vs. 88.4%, P < 0.0001) and antrum or pylorus (100.0% vs. 87.4%, P < 0.0001). The inspection time (576.2 vs. 574.5s, P = 0.91) and biopsy rate (57.2% vs. 56.6%, P = 0.83) were not different between the groups. The early UGI neoplasms detection rate in the IQCS group increased in both non-academic centres (RR = 3.319, 95% CI 1.277-9.176; P = 0.0094) and academic centres (RR = 2.416, 95% CI 1.301-4.568; P = 0.0034). The same improvements were observed for both less-experienced endoscopists (RR = 2.650, 95% CI 1.330-5.410; P = 0.0034) and experienced endoscopists (RR = 2.710, 95% CI 1.226-6.205; P = 0.010). No adverse events or serious adverse events were reported in the two groups.

Interpretation

The IQCS improved the OGD quality and increased early UGI neoplasm detection in different hospital types and endoscopist experiences. IQCS could play an important role in primary basic hospitals and non-expert endoscopists to improve the diagnostic accuracy of early UGI neoplasms. The effectiveness of IQCS in real-world clinical settings needs a larger population validation.

Funding

Key R&D Program of Shandong Province, China (Major Scientific and Technological Innovation Project), National Natural Science Foundation of China, the Taishan Scholars Program of Shandong Province, the National Key Research and Development Program of China, and the Shandong Provincial Natural Science Foundation.

Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett's esophagus: a tandem randomized and video trial

BACKGROUND

This study evaluated the effect of an artificial intelligence (AI)-based clinical decision support system on the performance and diagnostic confidence of endoscopists in their assessment of Barrett's esophagus (BE).

METHODS

96 standardized endoscopy videos were assessed by 22 endoscopists with varying degrees of BE experience from 12 centers. Assessment was randomized into two video sets: group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett's esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level.

RESULTS

AI had a stand-alone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.3%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1%, and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.8% [95%CI 65.2%-74.2%] to 78.0% [95%CI 74.0%-82.0%]; specificity 67.3% [95%CI 62.5%-72.2%] to 72.7% [95%CI 68.2%-77.3%]). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI.

CONCLUSION

BE nonexperts benefitted significantly from additional AI. BE experts and nonexperts remained significantly below the stand-alone performance of AI, suggesting that there may be other factors influencing endoscopists' decisions to follow or discard AI advice.

The standardized training and assessment system for magnetically controlled capsule gastroscopy (with video)

BACKGROUND AND AIM

To explore the feasibility of a standardized training and assessment system for magnetically controlled capsule gastroscopy (MCCG).

METHODS

The results of 90 trainees who underwent the standardized training and assessment system of the MCCG at the First Affiliated Hospital of Xi'an Jiaotong University from May 2020 to November 2023 was retrospectively analyzed. The trainees were divided into three groups according to their medical backgrounds: doctor, nurse, and non-medical groups. The training and assessment system adopted the '7 + 2' mode, seven days of training plus two days of theoretical and operational assessment. The passing rates of theoretical, operational, and total assessment were the primary outcomes. Satisfaction and mastery of the MCCG was checked.

RESULTS

Ninety trainees were assessed; theoretical assessment's passing rates in the three groups were 100%. The operational and total assessment passing rates were 100% (25/25), 97.92% (47/48), and 94.12% (16/17), for the doctor, nurse, and non-doctor groups respectively, with no significant difference (χ2 = 1.741, p = 0.419). No bleeding or perforation occurred during the procedure. Approximately, 96.00% (24/25), 95.83% (46/48), and 94.12% (16/17) of the doctor, nurse and non-medical groups anonymously expressed great satisfaction, respectively, without statistically significant difference (χ2 = 0.565, p = 1.000). The average follow-up time was 4-36 months, and 87 trainees (96.67%) had mastered the operation of the MCCG in daily work.

CONCLUSIONS

Standardized training and assessment of magnetically controlled capsule endoscopists is effective and feasible. Additionally, a strict assessment system and long-term communication and learning can improve teaching effects.

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.

Endoscopic Artificial Intelligence for Image Analysis in Gastrointestinal Neoplasms

BACKGROUND

Artificial intelligence (AI) using deep learning systems has recently been utilized in various medical fields. In the field of gastroenterology, AI is primarily implemented in image recognition and utilized in the realm of gastrointestinal (GI) endoscopy. In GI endoscopy, computer-aided detection/diagnosis (CAD) systems assist endoscopists in GI neoplasm detection or differentiation of cancerous or noncancerous lesions. Several AI systems for colorectal polyps have already been applied in colonoscopy clinical practices. In esophagogastroduodenoscopy, a few CAD systems for upper GI neoplasms have been launched in Asian countries. The usefulness of these CAD systems in GI endoscopy has been gradually elucidated.

SUMMARY

In this review, we outline recent articles on several studies of endoscopic AI systems for GI neoplasms, focusing on esophageal squamous cell carcinoma (ESCC), esophageal adenocarcinoma (EAC), gastric cancer (GC), and colorectal polyps. In ESCC and EAC, computer-aided detection (CADe) systems were mainly developed, and a recent meta-analysis study showed sensitivities of 91.2% and 93.1% and specificities of 80% and 86.9%, respectively. In GC, a recent meta-analysis study on CADe systems demonstrated that their sensitivity and specificity were as high as 90%. A randomized controlled trial (RCT) also showed that the use of the CADe system reduced the miss rate. Regarding computer-aided diagnosis (CADx) systems for GC, although RCTs have not yet been conducted, most studies have demonstrated expert-level performance. In colorectal polyps, multiple RCTs have shown the usefulness of the CADe system for improving the polyp detection rate, and several CADx systems have been shown to have high accuracy in colorectal polyp differentiation.

KEY MESSAGES

Most analyses of endoscopic AI systems suggested that their performance was better than that of nonexpert endoscopists and equivalent to that of expert endoscopists. Thus, endoscopic AI systems may be useful for reducing the risk of overlooking lesions and improving the diagnostic ability of endoscopists.

Diagnostic Accuracy of Artificial Intelligence in Endoscopy: Umbrella Review

Background

Some research has already reported the diagnostic value of artificial intelligence (AI) in different endoscopy outcomes. However, the evidence is confusing and of varying quality.

Objective

This review aimed to comprehensively evaluate the credibility of the evidence of AI's diagnostic accuracy in endoscopy.

Methods

Before the study began, the protocol was registered on PROSPERO (CRD42023483073). First, 2 researchers searched PubMed, Web of Science, Embase, and Cochrane Library using comprehensive search terms. Then, researchers screened the articles and extracted information. We used A Measurement Tool to Assess Systematic Reviews 2 (AMSTAR2) to evaluate the quality of the articles. When there were multiple studies aiming at the same result, we chose the study with higher-quality evaluations for further analysis. To ensure the reliability of the conclusions, we recalculated each outcome. Finally, the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) was used to evaluate the credibility of the outcomes.

Results

A total of 21 studies were included for analysis. Through AMSTAR2, it was found that 8 research methodologies were of moderate quality, while other studies were regarded as having low or critically low quality. The sensitivity and specificity of 17 different outcomes were analyzed. There were 4 studies on esophagus, 4 studies on stomach, and 4 studies on colorectal regions. Two studies were associated with capsule endoscopy, two were related to laryngoscopy, and one was related to ultrasonic endoscopy. In terms of sensitivity, gastroesophageal reflux disease had the highest accuracy rate, reaching 97%, while the invasion depth of colon neoplasia, with 71%, had the lowest accuracy rate. On the other hand, the specificity of colorectal cancer was the highest, reaching 98%, while the gastrointestinal stromal tumor, with only 80%, had the lowest specificity. The GRADE evaluation suggested that the reliability of most outcomes was low or very low.

Conclusions

AI proved valuabe in endoscopic diagnoses, especially in esophageal and colorectal diseases. These findings provide a theoretical basis for developing and evaluating AI-assisted systems, which are aimed at assisting endoscopists in carrying out examinations, leading to improved patient health outcomes. However, further high-quality research is needed in the future to fully validate AI's effectiveness.

Artificial intelligence for gastric cancer in endoscopy: From diagnostic reasoning to market

Recognition of gastric conditions during endoscopy exams, including gastric cancer, usually requires specialized training and a long learning curve. Besides that, the interobserver variability is frequently high due to the different morphological characteristics of the lesions and grades of mucosal inflammation. In this sense, artificial intelligence tools based on deep learning models have been developed to support physicians to detect, classify, and predict gastric lesions more efficiently. Even though a growing number of studies exists in the literature, there are multiple challenges to bring a model to practice in this field, such as the need for more robust validation studies and regulatory hurdles. Therefore, the aim of this review is to provide a comprehensive assessment of the current use of artificial intelligence applied to endoscopic imaging to evaluate gastric precancerous and cancerous lesions and the barriers to widespread implementation of this technology in clinical routine.

Real-World Application of Artificial Intelligence for Detecting Pathologic Gastric Atypia and Neoplastic Lesions

PURPOSE

Results of initial endoscopic biopsy of gastric lesions often differ from those of the final pathological diagnosis. We evaluated whether an artificial intelligence-based gastric lesion detection and diagnostic system, ENdoscopy as AI-powered Device Computer Aided Diagnosis for Gastroscopy (ENAD CAD-G), could reduce this discrepancy.

MATERIALS AND METHODS

We retrospectively collected 24,948 endoscopic images of early gastric cancers (EGCs), dysplasia, and benign lesions from 9,892 patients who underwent esophagogastroduodenoscopy between 2011 and 2021. The diagnostic performance of ENAD CAD-G was evaluated using the following real-world datasets: patients referred from community clinics with initial biopsy results of atypia (n=154), participants who underwent endoscopic resection for neoplasms (Internal video set, n=140), and participants who underwent endoscopy for screening or suspicion of gastric neoplasm referred from community clinics (External video set, n=296).

RESULTS

ENAD CAD-G classified the referred gastric lesions of atypia into EGC (accuracy, 82.47%; 95% confidence interval [CI], 76.46%-88.47%), dysplasia (88.31%; 83.24%-93.39%), and benign lesions (83.12%; 77.20%-89.03%). In the Internal video set, ENAD CAD-G identified dysplasia and EGC with diagnostic accuracies of 88.57% (95% CI, 83.30%-93.84%) and 91.43% (86.79%-96.07%), respectively, compared with an accuracy of 60.71% (52.62%-68.80%) for the initial biopsy results (P<0.001). In the External video set, ENAD CAD-G classified EGC, dysplasia, and benign lesions with diagnostic accuracies of 87.50% (83.73%-91.27%), 90.54% (87.21%-93.87%), and 88.85% (85.27%-92.44%), respectively.

CONCLUSIONS

ENAD CAD-G is superior to initial biopsy for the detection and diagnosis of gastric lesions that require endoscopic resection. ENAD CAD-G can assist community endoscopists in identifying gastric lesions that require endoscopic resection.

Smartphone application for artificial intelligence-based evaluation of stool state during bowel preparation before colonoscopy

OBJECTIVES

Colonoscopy (CS) is an important screening method for the early detection and removal of precancerous lesions. The stool state during bowel preparation (BP) should be properly evaluated to perform CS with sufficient quality. This study aimed to develop a smartphone application (app) with an artificial intelligence (AI) model for stool state evaluation during BP and to investigate whether the use of the app could maintain an adequate quality of CS.

METHODS

First, stool images were collected in our hospital to develop the AI model and were categorized into grade 1 (solid or muddy stools), grade 2 (cloudy watery stools), and grade 3 (clear watery stools). The AI model for stool state evaluation (grades 1-3) was constructed and internally verified using the cross-validation method. Second, a prospective study was conducted on the quality of CS using the app in our hospital. The primary end-point was the proportion of patients who achieved Boston Bowel Preparation Scale (BBPS) ≥6 among those who successfully used the app.

RESULTS

The AI model showed mean accuracy rates of 90.2%, 65.0%, and 89.3 for grades 1, 2, and 3, respectively. The prospective study enrolled 106 patients and revealed that 99.0% (95% confidence interval 95.3-99.9%) of patients achieved a BBPS ≥6.

CONCLUSION

The proportion of patients with BBPS ≥6 during CS using the developed app exceeded the set expected value. This app could contribute to the performance of high-quality CS in clinical practice.

Risk factors of missed early gastric cancer in endoscopic resected population: a retrospective, case-control study

BACKGROUND

Missed early gastric cancer (MEGC) is prevalent during esophagogastroduodenoscopy (EGD), which is the first-line recommended strategy for detecting early gastric cancer (EGC). Hence, we explored the risk factors for MEGC and different types of MEGC, based on the endoscopic resected population.

METHODS

This retrospective, case-control study was conducted at Nanjing Drum Tower Hospital (NJDTH). We included patients who were diagnosed with EGC during screening EGD, underwent endoscopic resection, and were confirmed by postoperative pathology at the NJDTH from January 2014 to December 2021, and classified them into different types according to the different root causes of misses. Univariable, multivariable, subgroup and propensity score analyses were used to explore the risk factors for MEGC and different types of MEGC.

RESULTS

A total of 447 patients, comprising 345 with initially detected early gastric cancer (IDEGC) and 102 with MEGC, were included in this study. Larger size (≥ 1 cm) (OR 0.45, 95% CI 0.27-0.74, P = 0.002) and invasion depth of submucosa (OR 0.26, 95% CI 0.10-0.69, P = 0.007) were negatively associated with MEGC. Use of sedation (OR 0.32, 95% CI 0.20-0.52, P < 0.001) and longer observation time (OR 0.60, 95% CI 0.37-0.96, P = 0.034) exhibited protective effect on MEGC.

CONCLUSIONS

Smaller and more superficial EGC lesions are more susceptible to misdiagnosis. The use of sedation and prolonged observation time during EGD could help reduce the occurrence of MEGC.

Efficacy of artificial intelligence in reducing miss rates of GI adenomas, polyps, and sessile serrated lesions: a meta-analysis of randomized controlled trials

BACKGROUND AND AIMS

The aim of this study was to determine if utilization of artificial intelligence (AI) in the course of endoscopic procedures can significantly diminish both the adenoma miss rate (AMR) and the polyp miss rate (PMR) compared with standard endoscopy.

METHODS

We performed an extensive search of various databases, encompassing PubMed, Embase, Cochrane Library, Web of Science, and Scopus, until June 2023. The search terms used were artificial intelligence, machine learning, deep learning, transfer machine learning, computer-assisted diagnosis, convolutional neural networks, gastrointestinal (GI) endoscopy, endoscopic image analysis, polyp, adenoma, and neoplasms. The main study aim was to explore the impact of AI on the AMR, PMR, and sessile serrated lesion miss rate.

RESULTS

A total of 7 randomized controlled trials were included in this meta-analysis. Pooled AMR was markedly lower in the AI group versus the non-AI group (pooled relative risk [RR], .46; 95% confidence interval [CI], .36-.59; P < .001). PMR was also reduced in the AI group in contrast with the non-AI control (pooled RR, .43; 95% CI, .27-.69; P < .001). The results showed that AI decreased the miss rate of sessile serrated lesions (pooled RR, .43; 95% CI, .20 to .92; P < .05) and diminutive adenomas (pooled RR, .49; 95% CI, .26-.93) during endoscopy, but no significant effect was observed for advanced adenomas (pooled RR, .48; 95% CI, .17-1.37; P = .17). The average number of polyps (Hedges' g = -.486; 95% CI, -.697 to -.274; P = .000) and adenomas (Hedges' g = -.312; 95% CI, -.551 to -.074; P = .01) detected during the second procedure also favored AI. However, AI implementation did not lead to a prolonged withdrawal time (P > .05).

CONCLUSIONS

This meta-analysis suggests that AI technology leads to significant reduction of miss rates for GI adenomas, polyps, and sessile serrated lesions during endoscopic surveillance. These results underscore the potential of AI to improve the accuracy and efficiency of GI endoscopic procedures.

Deep learning assists detection of esophageal cancer and precursor lesions in a prospective, randomized controlled study

Endoscopy is the primary modality for detecting asymptomatic esophageal squamous cell carcinoma (ESCC) and precancerous lesions. Improving detection rate remains challenging. We developed a system based on deep convolutional neural networks (CNNs) for detecting esophageal cancer and precancerous lesions [high-risk esophageal lesions (HrELs)] and validated its efficacy in improving HrEL detection rate in clinical practice (trial registration ChiCTR2100044126 at www.chictr.org.cn). Between April 2021 and March 2022, 3117 patients ≥50 years old were consecutively recruited from Taizhou Hospital, Zhejiang Province, and randomly assigned 1:1 to an experimental group (CNN-assisted endoscopy) or a control group (unassisted endoscopy) based on block randomization. The primary endpoint was the HrEL detection rate. In the intention-to-treat population, the HrEL detection rate [28 of 1556 (1.8%)] was significantly higher in the experimental group than in the control group [14 of 1561 (0.9%), P = 0.029], and the experimental group detection rate was twice that of the control group. Similar findings were observed between the experimental and control groups [28 of 1524 (1.9%) versus 13 of 1534 (0.9%), respectively; P = 0.021]. The system's sensitivity, specificity, and accuracy for detecting HrELs were 89.7, 98.5, and 98.2%, respectively. No adverse events occurred. The proposed system thus improved HrEL detection rate during endoscopy and was safe. Deep learning assistance may enhance early diagnosis and treatment of esophageal cancer and may become a useful tool for esophageal cancer screening.

Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines

The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77-94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.

Latest Advances in Endoscopic Detection of Oesophageal and Gastric Neoplasia

Endoscopy is the gold standard for the diagnosis of cancers and cancer precursors in the oesophagus and stomach. Early detection of upper GI cancers requires high-quality endoscopy and awareness of the subtle features these lesions carry. Endoscopists performing surveillance of high-risk patients including those with Barrett's oesophagus, previous squamous neoplasia or chronic atrophic gastritis should be familiar with endoscopic features, classification systems and sampling techniques to maximise the detection of early cancer. In this article, we review the current approach to diagnosis of these conditions and the latest advanced imaging and diagnostic techniques.

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.

Effect of an artificial intelligence-assisted system on endoscopic diagnosis of superficial oesophageal squamous cell carcinoma and precancerous lesions: a multicentre, tandem, double-blind, randomised controlled trial

BACKGROUND

Despite the usefulness of white light endoscopy (WLE) and non-magnified narrow-band imaging (NBI) for screening for superficial oesophageal squamous cell carcinoma and precancerous lesions, these lesions might be missed due to their subtle features and interpretation variations among endoscopists. Our team has developed an artificial intelligence (AI) system to detect superficial oesophageal squamous cell carcinoma and precancerous lesions using WLE and non-magnified NBI. We aimed to evaluate the auxiliary diagnostic performance of the AI system in a real clinical setting.

METHODS

We did a multicentre, tandem, double-blind, randomised controlled trial at 12 hospitals in China. Eligible patients were aged 18 years or older and underwent sedated upper gastrointestinal endoscopy for screening, investigation of gastrointestinal symptoms, or surveillance. Patients were randomly assigned (1:1) to either the AI-first group or the routine-first group using a computerised random number generator. Patients, pathologists, and statistical analysts were masked to group assignment, whereas endoscopists and research assistants were not. The same endoscopist at each centre did tandem upper gastrointestinal endoscopy for each eligible patient on the same day. In the AI-first group, the endoscopist did the first examination with the assistance of the AI system and the second examination without it. In the routine-first group, the order of examinations was reversed. The primary outcome was the miss rate of superficial oesophageal squamous cell carcinoma and precancerous lesions, calculated on a per-lesion and per-patient basis. All analyses were done on a per-protocol basis. This trial is registered with the Chinese Clinical Trial Registry (ChiCTR2100052116) and is completed.

FINDINGS

Between Oct 19, 2021, and June 8, 2022, 5934 patients were randomly assigned to the AI-first group and 5912 to the routine-first group, of whom 5865 and 5850 were eligible for analysis. Per-lesion miss rates were 1·7% (2/118; 95% CI 0·0-4·0) in the AI-first group versus 6·7% (6/90; 1·5-11·8) in the routine-first group (risk ratio 0·25, 95% CI 0·06-1·08; p=0·079). Per-patient miss rates were 1·9% (2/106; 0·0-4·5) in AI-first group versus 5·1% (4/79; 0·2-9·9) in the routine-first group (0·37, 0·08-1·71; p=0·40). Bleeding after biopsy of oesophageal lesions was observed in 13 (0·2%) patients in the AI-first group and 11 (0·2%) patients in the routine-first group. No serious adverse events were reported by patients in either group.

INTERPRETATION

The observed effect of AI-assisted endoscopy on the per-lesion and per-patient miss rates of superficial oesophageal squamous cell carcinoma and precancerous lesions under WLE and non-magnified NBI was consistent with substantial benefit through to a neutral or small negative effect. The effectiveness and cost-benefit of this AI system in real-world clinical settings remain to be further assessed.

FUNDING

National Natural Science Foundation of China, 1·3·5 project for disciplines of excellence, West China Hospital, Sichuan University, and Chengdu Science and Technology Project.

TRANSLATION

For the Chinese translation of the abstract see Supplementary Materials section.

Current status of quality control in screening esophagogastroduodenoscopy and the emerging role of artificial intelligence

Esophagogastroduodenoscopy (EGD) screening is being implemented in countries with a high incidence of upper gastrointestinal (UGI) cancer. High-quality EGD screening ensures the yield of early diagnosis and prevents suffering from advanced UGI cancer and minimal operational-related discomfort. However, performance varied dramatically among endoscopists, and quality control for EGD screening remains suboptimal. Guidelines have recommended potential measures for endoscopy quality improvement and research has been conducted for evidence. Moreover, artificial intelligence offers a promising solution for computer-aided diagnosis and quality control during EGD examinations. In this review, we summarized the key points for quality assurance in EGD screening based on current guidelines and evidence. We also outline the latest evidence, limitations, and future prospects of the emerging role of artificial intelligence in EGD quality control, aiming to provide a foundation for improving the quality of EGD screening.

Deep Learning and Gastric Cancer: Systematic Review of AI-Assisted Endoscopy

BACKGROUND

Gastric cancer (GC), a significant health burden worldwide, is typically diagnosed in the advanced stages due to its non-specific symptoms and complex morphological features. Deep learning (DL) has shown potential for improving and standardizing early GC detection. This systematic review aims to evaluate the current status of DL in pre-malignant, early-stage, and gastric neoplasia analysis.

METHODS

A comprehensive literature search was conducted in PubMed/MEDLINE for original studies implementing DL algorithms for gastric neoplasia detection using endoscopic images. We adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The focus was on studies providing quantitative diagnostic performance measures and those comparing AI performance with human endoscopists.

RESULTS

Our review encompasses 42 studies that utilize a variety of DL techniques. The findings demonstrate the utility of DL in GC classification, detection, tumor invasion depth assessment, cancer margin delineation, lesion segmentation, and detection of early-stage and pre-malignant lesions. Notably, DL models frequently matched or outperformed human endoscopists in diagnostic accuracy. However, heterogeneity in DL algorithms, imaging techniques, and study designs precluded a definitive conclusion about the best algorithmic approach.

CONCLUSIONS

The promise of artificial intelligence in improving and standardizing gastric neoplasia detection, diagnosis, and segmentation is significant. This review is limited by predominantly single-center studies and undisclosed datasets used in AI training, impacting generalizability and demographic representation. Further, retrospective algorithm training may not reflect actual clinical performance, and a lack of model details hinders replication efforts. More research is needed to substantiate these findings, including larger-scale multi-center studies, prospective clinical trials, and comprehensive technical reporting of DL algorithms and datasets, particularly regarding the heterogeneity in DL algorithms and study designs.

Third Eye? The Assistance of Artificial Intelligence (AI) in the Endoscopy of Gastrointestinal Neoplasms

Gastrointestinal cancers are characterized by high incidence and mortality. However, there are well-established methods of screening. The endoscopy exam provides the macroscopical image and enables harvesting the tissue samples for further histopathological diagnosis. The efficiency of endoscopies relies not only on proper patient preparation, but also on the skills of the personnel conducting the exam. In recent years, a number of reports concerning the application of artificial intelligence (AI) in medicine have arisen. Numerous studies aimed to assess the utility of deep learning/ neural network systems supporting endoscopies. In this review, we summarized the most recent reports and randomized clinical trials regarding the application of AI in screening and surveillance of gastrointestinal cancers among patients suffering from esophageal, gastric, and colorectal cancer, along with the advantages, limitations, and controversies of those novel solutions.

Enhancement of Non-Linear Deep Learning Model by Adjusting Confounding Variables for Bone Age Estimation in Pediatric Hand X-rays

In medicine, confounding variables in a generalized linear model are often adjusted; however, these variables have not yet been exploited in a non-linear deep learning model. Sex plays important role in bone age estimation, and non-linear deep learning model reported their performances comparable to human experts. Therefore, we investigate the properties of using confounding variables in a non-linear deep learning model for bone age estimation in pediatric hand X-rays. The RSNA Pediatric Bone Age Challenge (2017) dataset is used to train deep learning models. The RSNA test dataset is used for internal validation, and 227 pediatric hand X-ray images with bone age, chronological age, and sex information from Asan Medical Center (AMC) for external validation. U-Net based autoencoder, U-Net multi-task learning (MTL), and auxiliary-accelerated MTL (AA-MTL) models are chosen. Bone age estimations adjusted by input, output prediction, and without adjusting the confounding variables are compared. Additionally, ablation studies for model size, auxiliary task hierarchy, and multiple tasks are conducted. Correlation and Bland-Altman plots between ground truth and model-predicted bone ages are evaluated. Averaged saliency maps based on image registration are superimposed on representative images according to puberty stage. In the RSNA test dataset, adjusting by input shows the best performances regardless of model size, with mean average errors (MAEs) of 5.740, 5.478, and 5.434 months for the U-Net backbone, U-Net MTL, and AA-MTL models, respectively. However, in the AMC dataset, the AA-MTL model that adjusts the confounding variable by prediction shows the best performance with an MAE of 8.190 months, whereas the other models show the best performances by adjusting the confounding variables by input. Ablation studies of task hierarchy reveal no significant differences in the results of the RSNA dataset. However, predicting the confounding variable in the second encoder layer and estimating bone age in the bottleneck layer shows the best performance in the AMC dataset. Ablations studies of multiple tasks reveal that leveraging confounding variables plays an important role regardless of multiple tasks. To estimate bone age in pediatric X-rays, the clinical setting and balance between model size, task hierarchy, and confounding adjustment method play important roles in performance and generalizability; therefore, proper adjusting methods of confounding variables to train deep learning-based models are required for improved models.

Endoscopic diagnosis and treatment of superficial non-ampullary duodenal epithelial tumors: A review

The surface of the small bowel mucosa is covered more than any other section of the digestive canal; however, the overall prevalence of small bowel tumors of the whole gastrointestinal tract is evidently low. Owing to the improvement in endoscopic techniques, the prevalence of small bowel tumors has increased across multiple countries, which is mainly due to an increase in duodenal tumors. Superficial non-ampullary duodenal epithelial tumors (SNADETs) are defined as tumors originating from the non-ampullary region in the duodenum that share similarities and discrepancies with their gastric and colorectal counterparts in the pathogenesis and clinicopathologic characteristics. To date, white light endoscopy (WLE) remains the cornerstone of endoscopic diagnosis for SNADETs. Besides, narrow-band imaging (NBI) techniques and magnifying endoscopy (ME) have been widely used in the clinic and endorsed by multiple guidelines and consensuses for SNADETs' evaluation. Confocal laser endomicroscopy (CLE), endocytoscopy (ECS), and artificial intelligence (AI) are also up-and-coming methods, showing an exceptional value in the diagnosis of SNADETs. Similar to the endoscopic treatment for colorectal polyps, the choices for SNADETs mainly include cold snare polypectomy (CSP), endoscopic mucosal resection (EMR), endoscopic submucosal dissection (ESD), and laparoscopic endoscopic cooperative surgery (LECS). However, owing to the narrow lumen, rich vascularity, weak muscle layer, abundant Brunner's gland, and the hardship of endoscope control, the duodenum ranks as one of the most dangerous operating areas in the digestive tract. Therefore, endoscopists must anticipate the difficulties in endoscopic maneuverability, remain aware of the increased risk of complications, and then select the appropriate treatment according to the advantages and disadvantages of each method.

Comparing artificial intelligence to humans for endoscopic diagnosis of gastric neoplasia: An external validation study

OBJECTIVES

Artificial intelligence (AI) uses deep learning functionalities that may enhance the detection of early gastric cancer during endoscopy. An AI-based endoscopic system for upper endoscopy was recently developed in Japan. We aim to validate this AI-based system in a Singaporean cohort.

METHODS

There were 300 de-identified still images prepared from endoscopy video files obtained from subjects that underwent gastroscopy in National University Hospital (NUH). Five specialists and 6 non-specialists (trainees) from NUH were assigned to read and categorize the images into "neoplastic" or "non-neoplastic." Results were then compared with the readings performed by the endoscopic AI system.

RESULTS

The mean accuracy, sensitivity, and specificity for the 11 endoscopists were 0.847, 0.525, and 0.872, respectively. These values for the AI-based system were 0.777, 0.591, and 0.791, respectively. While AI in general did not perform better than endoscopists on the whole, in the subgroup of high-grade dysplastic lesions, only 29.1% were picked up by the endoscopist rating, but 80% were classified as neoplastic by AI (P = 0.0011). The average diagnostic time was also faster in AI compared with endoscopists (677.1 s vs 42.02 s (P < 0.001).

CONCLUSION

We demonstrated that an AI system developed in another health system was comparable in diagnostic accuracy in the evaluation of static images. AI systems are faster and not fatigable and may have a role in augmenting human diagnosis during endoscopy. With more advances in AI and larger studies to support its efficacy it would likely play a larger role in screening endoscopy in future.

Application of artificial intelligence for improving early detection and prediction of therapeutic outcomes for gastric cancer in the era of precision oncology

Gastric cancer is a leading contributor to cancer incidence and mortality globally. Recently, artificial intelligence approaches, particularly machine learning and deep learning, are rapidly reshaping the full spectrum of clinical management for gastric cancer. Machine learning is formed from computers running repeated iterative models for progressively improving performance on a particular task. Deep learning is a subtype of machine learning on the basis of multilayered neural networks inspired by the human brain. This review summarizes the application of artificial intelligence algorithms to multi-dimensional data including clinical and follow-up information, conventional images (endoscope, histopathology, and computed tomography (CT)), molecular biomarkers, etc. to improve the risk surveillance of gastric cancer with established risk factors; the accuracy of diagnosis, and survival prediction among established gastric cancer patients; and the prediction of treatment outcomes for assisting clinical decision making. Therefore, artificial intelligence makes a profound impact on almost all aspects of gastric cancer from improving diagnosis to precision medicine. Despite this, most established artificial intelligence-based models are in a research-based format and often have limited value in real-world clinical practice. With the increasing adoption of artificial intelligence in clinical use, we anticipate the arrival of artificial intelligence-powered gastric cancer care.

Effect of a deep learning-based automatic upper GI endoscopic reporting system: a randomized crossover study (with video)

BACKGROUND AND AIMS

EGD is essential for GI disorders, and reports are pivotal to facilitating postprocedure diagnosis and treatment. Manual report generation lacks sufficient quality and is labor intensive. We reported and validated an artificial intelligence-based endoscopy automatic reporting system (AI-EARS).

METHODS

The AI-EARS was designed for automatic report generation, including real-time image capturing, diagnosis, and textual description. It was developed using multicenter datasets from 8 hospitals in China, including 252,111 images for training, 62,706 images, and 950 videos for testing. Twelve endoscopists and 44 endoscopy procedures were consecutively enrolled to evaluate the effect of the AI-EARS in a multireader, multicase, crossover study. The precision and completeness of the reports were compared between endoscopists using the AI-EARS and conventional reporting systems.

RESULTS

In video validation, the AI-EARS achieved completeness of 98.59% and 99.69% for esophageal and gastric abnormality records, respectively, accuracies of 87.99% and 88.85% for esophageal and gastric lesion location records, and 73.14% and 85.24% for diagnosis. Compared with the conventional reporting systems, the AI-EARS achieved greater completeness (79.03% vs 51.86%, P < .001) and accuracy (64.47% vs 42.81%, P < .001) of the textual description and completeness of the photo-documents of landmarks (92.23% vs 73.69%, P < .001). The mean reporting time for an individual lesion was significantly reduced (80.13 ± 16.12 seconds vs 46.47 ± 11.68 seconds, P < .001) after the AI-EARS assistance.

CONCLUSIONS

The AI-EARS showed its efficacy in improving the accuracy and completeness of EGD reports. It might facilitate the generation of complete endoscopy reports and postendoscopy patient management. (Clinical trial registration number: NCT05479253.).

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.

Endoscopic Imaging for the Diagnosis of Neoplastic and Pre-Neoplastic Conditions of the Stomach

Gastric cancer is an aggressive disease with low long-term survival rates. An early diagnosis is essential to offer a better prognosis and curative treatment. Upper gastrointestinal endoscopy is the main tool for the screening and diagnosis of patients with gastric pre-neoplastic conditions and early lesions. Image-enhanced techniques such as conventional chromoendoscopy, virtual chromoendoscopy, magnifying imaging, and artificial intelligence improve the diagnosis and the characterization of early neoplastic lesions. In this review, we provide a summary of the currently available recommendations for the screening, surveillance, and diagnosis of gastric cancer, focusing on novel endoscopy imaging technologies.

Quality indicators in the endoscopic detection of gastric cancer

Gastroscopy is the reference standard for the diagnosis of gastric cancer, but it is operator-dependent and associated with missed gastric cancer. The proliferation of gastroscopic examinations, increasingly for the screening and detection of subtle premalignant lesions, has motivated scrutiny of quality in gastroscopy. The concept of a high-quality endoscopic examination for the detection of superficial gastric neoplasia has been defined by expert guidelines to improve mucosal visualization, engender a systematic examination process and detect superficial neoplasia. This review discusses the evidence supporting the components of a high-quality diagnostic gastroscopic examination in relation to the detection of gastric cancer, and their potential role as procedural quality indicators to drive a structured improvement in clinically meaningful outcomes.

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.

Development of a tongue image-based machine learning tool for the diagnosis of gastric cancer: a prospective multicentre clinical cohort study

BACKGROUND

Tongue images (the colour, size and shape of the tongue and the colour, thickness and moisture content of the tongue coating), reflecting the health state of the whole body according to the theory of traditional Chinese medicine (TCM), have been widely used in China for thousands of years. Herein, we investigated the value of tongue images and the tongue coating microbiome in the diagnosis of gastric cancer (GC).

METHODS

From May 2020 to January 2021, we simultaneously collected tongue images and tongue coating samples from 328 patients with GC (all newly diagnosed with GC) and 304 non-gastric cancer (NGC) participants in China, and 16 S rDNA was used to characterize the microbiome of the tongue coating samples. Then, artificial intelligence (AI) deep learning models were established to evaluate the value of tongue images and the tongue coating microbiome in the diagnosis of GC. Considering that tongue imaging is more convenient and economical as a diagnostic tool, we further conducted a prospective multicentre clinical study from May 2020 to March 2022 in China and recruited 937 patients with GC and 1911 participants with NGC from 10 centres across China to further evaluate the role of tongue images in the diagnosis of GC. Moreover, we verified this approach in another independent external validation cohort that included 294 patients with GC and 521 participants with NGC from 7 centres. This study is registered at ClinicalTrials.gov, NCT01090362.

FINDINGS

For the first time, we found that both tongue images and the tongue coating microbiome can be used as tools for the diagnosis of GC, and the area under the curve (AUC) value of the tongue image-based diagnostic model was 0.89. The AUC values of the tongue coating microbiome-based model reached 0.94 using genus data and 0.95 using species data. The results of the prospective multicentre clinical study showed that the AUC values of the three tongue image-based models for GCs reached 0.88-0.92 in the internal verification and 0.83-0.88 in the independent external verification, which were significantly superior to the combination of eight blood biomarkers.

INTERPRETATION

Our results suggest that tongue images can be used as a stable method for GC diagnosis and are significantly superior to conventional blood biomarkers. The three kinds of tongue image-based AI deep learning diagnostic models that we developed can be used to adequately distinguish patients with GC from participants with NGC, even early GC and precancerous lesions, such as atrophic gastritis (AG).

FUNDING

The National Key R&D Program of China (2021YFA0910100), Program of Zhejiang Provincial TCM Sci-tech Plan (2018ZY006), Medical Science and Technology Project of Zhejiang Province (2022KY114, WKJ-ZJ-2104), Zhejiang Provincial Research Center for Upper Gastrointestinal Tract Cancer (JBZX-202006), Natural Science Foundation of Zhejiang Province (HDMY22H160008), Science and Technology Projects of Zhejiang Province (2019C03049), National Natural Science Foundation of China (82074245, 81973634, 82204828), and Chinese Postdoctoral Science Foundation (2022M713203).

Artificial intelligence and upper gastrointestinal endoscopy: what is the optimal study design?

Upper gastrointestinal cancers (i.e., esophageal and gastric cancers) are common cancers worldwide with high mortality and morbidity. Although there is no randomized controlled trial-based evidence, early detection with endoscopy is expected to positively affect prognosis and morbidity. However, endoscopic procedures are always accompanied by human-induced errors such as overlooking of neoplasia and cancers. Recently, the use of artificial intelligence (AI) during upper gastrointestinal endoscopy is catching attention because it is expected to reduce human-induced variability of the examination. This review article introduces the overview of the expectation and current status of the AI tools for upper gastrointestinal endoscopy and shares possible challenges and corresponding solutions with readers.

Highlighting the Undetectable - Fluorescence Molecular Imaging in Gastrointestinal Endoscopy

Flexible high-definition white-light endoscopy is the current gold standard in screening for cancer and its precursor lesions in the gastrointestinal tract. However, miss rates are high, especially in populations at high risk for developing gastrointestinal cancer (e.g., inflammatory bowel disease, Lynch syndrome, or Barrett's esophagus) where lesions tend to be flat and subtle. Fluorescence molecular endoscopy (FME) enables intraluminal visualization of (pre)malignant lesions based on specific biomolecular features rather than morphology by using fluorescently labeled molecular probes that bind to specific molecular targets. This strategy has the potential to serve as a valuable tool for the clinician to improve endoscopic lesion detection and real-time clinical decision-making. This narrative review presents an overview of recent advances in FME, focusing on probe development, techniques, and clinical evidence. Future perspectives will also be addressed, such as the use of FME in patient stratification for targeted therapies and potential alliances with artificial intelligence. KEY MESSAGES: • Fluorescence molecular endoscopy is a relatively new technology that enables safe and real-time endoscopic lesion visualization based on specific molecular features rather than on morphology, thereby adding a layer of information to endoscopy, like in PET-CT imaging. • Recently the transition from preclinical to clinical studies has been made, with promising results regarding enhancing detection of flat and subtle lesions in the colon and esophagus. However, clinical evidence needs to be strengthened by larger patient studies with stratified study designs. • In the future fluorescence molecular endoscopy could serve as a valuable tool in clinical workflows to improve detection in high-risk populations like patients with Barrett's esophagus, Lynch syndrome, and inflammatory bowel syndrome, where flat and subtle lesions tend to be malignant up to five times more often. • Fluorescence molecular endoscopy has the potential to assess therapy responsiveness in vivo for targeted therapies, thereby playing a role in personalizing medicine. • To further reduce high miss rates due to human and technical factors, joint application of artificial intelligence and fluorescence molecular endoscopy are likely to generate added value.

Artificial intelligence applicated in gastric cancer: A bibliometric and visual analysis via CiteSpace

Objective

This study aimed to analyze and visualize the current research focus, research frontiers, evolutionary processes, and trends of artificial intelligence (AI) in the field of gastric cancer using a bibliometric analysis.

Methods

The Web of Science Core Collection database was selected as the data source for this study to retrieve and obtain articles and reviews related to AI in gastric cancer. All the information extracted from the articles was imported to CiteSpace to conduct the bibliometric and knowledge map analysis, allowing us to clearly visualize the research hotspots and trends in this field.

Results

A total of 183 articles published between 2017 and 2022 were included, contributed by 201 authors from 33 countries/regions. Among them, China (47.54%), Japan (21.86%), and the USA (13.11%) have made outstanding contributions in this field, accounting fsor 82.51% of the total publications. The primary research institutions were Wuhan University, Tokyo University, and Tada Tomohiro Inst Gastroenterol and Proctol. Tada (n = 12) and Hirasawa (n = 90) were ranked first in the top 10 authors and co-cited authors, respectively. Gastrointestinal Endoscopy (21 publications; IF 2022, 9.189; Q1) was the most published journal, while Gastric Cancer (133 citations; IF 2022, 8.171; Q1) was the most co-cited journal. Nevertheless, the cooperation between different countries and institutions should be further strengthened. The most common keywords were AI, gastric cancer, and convolutional neural network. The "deep-learning algorithm" started to burst in 2020 and continues till now, which indicated that this research topic has attracted continuous attention in recent years and would be the trend of research on AI application in GC.

Conclusions

Research related to AI in gastric cancer is increasing exponentially. Current research hotspots focus on the application of AI in gastric cancer, represented by convolutional neural networks and deep learning, in diagnosis and differential diagnosis and staging. Considering the great potential and clinical application prospects, the related area of AI applications in gastric cancer will remain a research hotspot in the future.

Current Status of Artificial Intelligence-Based Computer-Assisted Diagnosis Systems for Gastric Cancer in Endoscopy

Artificial intelligence (AI) is gradually being utilized in various fields as its performance has been improving with the development of deep learning methods, availability of big data, and the progression of computer processing units. In the field of medicine, AI is mainly implemented in image recognition, such as in radiographic and pathologic diagnoses. In the realm of gastrointestinal endoscopy, although AI-based computer-assisted detection/diagnosis (CAD) systems have been applied in some areas, such as colorectal polyp detection and diagnosis, so far, their implementation in real-world clinical settings is limited. The accurate detection or diagnosis of gastric cancer (GC) is one of the challenges in which performance varies greatly depending on the endoscopist's skill. The diagnosis of early GC is especially challenging, partly because early GC mimics atrophic gastritis in the background mucosa. Therefore, several CAD systems for GC are being actively developed. The development of a CAD system for GC is considered challenging because it requires a large number of GC images. In particular, early stage GC images are rarely available, partly because it is difficult to diagnose gastric cancer during the early stages. Additionally, the training image data should be of a sufficiently high quality to conduct proper CAD training. Recently, several AI systems for GC that exhibit a robust performance, owing to being trained on a large number of high-quality images, have been reported. This review outlines the current status and prospects of AI use in esophagogastroduodenoscopy (EGDS), focusing on the diagnosis of GC.

Application of artificial intelligence in the endoscopic diagnosis of early gastric cancer, atrophic gastritis, and Helicobacter pylori infection

Gastric cancer (GC) is one of the most serious health problems worldwide. Chronic atrophic gastritis (CAG) is most commonly caused by Helicobacter pylori (H. pylori) infection. Currently, endoscopic detection of early gastric cancer (EGC) and CAG remains challenging for endoscopists, and the diagnostic accuracy of H. pylori infection by endoscopy is approximately 70%. Artificial intelligence (AI) can assist endoscopic diagnosis including detection, prediction of depth of invasion, boundary delineation, and anatomical location of EGC, and has achievable diagnostic ability even comparable to experienced endoscopists. In this review we summarized various AI-assisted systems in the diagnosis of EGC, CAG, and H. pylori infection.

Randomized Clinical Trials of Machine Learning Interventions in Health Care: A Systematic Review

IMPORTANCE

Despite the potential of machine learning to improve multiple aspects of patient care, barriers to clinical adoption remain. Randomized clinical trials (RCTs) are often a prerequisite to large-scale clinical adoption of an intervention, and important questions remain regarding how machine learning interventions are being incorporated into clinical trials in health care.

OBJECTIVE

To systematically examine the design, reporting standards, risk of bias, and inclusivity of RCTs for medical machine learning interventions.

EVIDENCE REVIEW

In this systematic review, the Cochrane Library, Google Scholar, Ovid Embase, Ovid MEDLINE, PubMed, Scopus, and Web of Science Core Collection online databases were searched and citation chasing was done to find relevant articles published from the inception of each database to October 15, 2021. Search terms for machine learning, clinical decision-making, and RCTs were used. Exclusion criteria included implementation of a non-RCT design, absence of original data, and evaluation of nonclinical interventions. Data were extracted from published articles. Trial characteristics, including primary intervention, demographics, adherence to the CONSORT-AI reporting guideline, and Cochrane risk of bias were analyzed.

FINDINGS

Literature search yielded 19 737 articles, of which 41 RCTs involved a median of 294 participants (range, 17-2488 participants). A total of 16 RCTS (39%) were published in 2021, 21 (51%) were conducted at single sites, and 15 (37%) involved endoscopy. No trials adhered to all CONSORT-AI standards. Common reasons for nonadherence were not assessing poor-quality or unavailable input data (38 trials [93%]), not analyzing performance errors (38 [93%]), and not including a statement regarding code or algorithm availability (37 [90%]). Overall risk of bias was high in 7 trials (17%). Of 11 trials (27%) that reported race and ethnicity data, the median proportion of participants from underrepresented minority groups was 21% (range, 0%-51%).

CONCLUSIONS AND RELEVANCE

This systematic review found that despite the large number of medical machine learning-based algorithms in development, few RCTs for these technologies have been conducted. Among published RCTs, there was high variability in adherence to reporting standards and risk of bias and a lack of participants from underrepresented minority groups. These findings merit attention and should be considered in future RCT design and reporting.

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.

The Feasibility of Applying Artificial Intelligence to Gastrointestinal Endoscopy to Improve the Detection Rate of Early Gastric Cancer Screening

Convolutional neural networks in the field of artificial intelligence show great potential in image recognition. It assisted endoscopy to improve the detection rate of early gastric cancer. The 5-year survival rate for advanced gastric cancer is less than 30%, while the 5-year survival rate for early gastric cancer is more than 90%. Therefore, earlier screening for gastric cancer can lead to a better prognosis. However, the detection rate of early gastric cancer in China has been extremely low due to many factors, such as the presence of gastric cancer without obvious symptoms, difficulty identifying lesions by the naked eye, and a lack of experience among endoscopists. The introduction of artificial intelligence can help mitigate these shortcomings and greatly improve the accuracy of screening. According to relevant reports, the sensitivity and accuracy of artificial intelligence trained on deep cirrocumulus neural networks are better than those of endoscopists, and evaluations also take less time, which can greatly reduce the burden on endoscopists. In addition, artificial intelligence can also perform real-time detection and feedback on the inspection process of the endoscopist to standardize the operation of the endoscopist. AI has also shown great potential in training novice endoscopists. With the maturity of AI technology, AI has the ability to improve the detection rate of early gastric cancer in China and reduce the death rate of gastric cancer related diseases in China.

Implementation of artificial intelligence in upper gastrointestinal endoscopy

The application of artificial intelligence (AI) using deep learning has significantly expanded in the field of esophagogastric endoscopy. Recent studies have shown promising results in detecting and differentiating early gastric cancer using AI tools built using white light, magnified, or image-enhanced endoscopic images. Some studies have reported the use of AI tools to predict the depth of early gastric cancer based on endoscopic images. Similarly, studies based on using AI for detecting early esophageal cancer have also been reported, with an accuracy comparable to that of endoscopy specialists. Moreover, an AI system, developed to diagnose pharyngeal cancer, has shown promising performance with high sensitivity. These reports suggest that, if introduced for regular use in clinical settings, AI systems can significantly reduce the burden on physicians. This review summarizes the current status of AI applications in the upper gastrointestinal tract and presents directions for clinical practice implementation and future research.

Artificial Intelligence and Deep Learning for Upper Gastrointestinal Neoplasia

Upper gastrointestinal (GI) neoplasia account for 35% of GI cancers and 1.5 million cancer-related deaths every year. Despite its efficacy in preventing cancer mortality, diagnostic upper GI endoscopy is affected by a substantial miss rate of neoplastic lesions due to failure to recognize a visible lesion or imperfect navigation. This may be offset by the real-time application of artificial intelligence (AI) for detection (computer-aided detection [CADe]) and characterization (computer-aided diagnosis [CADx]) of upper GI neoplasia. Stand-alone performance of CADe for esophageal squamous cell neoplasia, Barrett's esophagus-related neoplasia, and gastric cancer showed promising accuracy, sensitivity ranging between 83% and 93%. However, incorporation of CADe/CADx in clinical practice depends on several factors, such as possible bias in the training or validation phases of these algorithms, its interaction with human endoscopists, and clinical implications of false-positive results. The aim of this review is to guide the clinician across the multiple steps of AI development in clinical practice.

Application and prospect of artificial intelligence in digestive endoscopy

INTRODUCTION

With the progress of science and technology, artificial intelligence represented by deep learning has gradually begun to be applied in the medical field. Artificial intelligence has been applied to benign gastrointestinal lesions, tumors, early cancer, inflammatory bowel disease, gallbladder, pancreas, and other diseases. This review summarizes the latest research results on artificial intelligence in digestive endoscopy and discusses the prospect of artificial intelligence in digestive system diseases.

AREAS COVERED

We retrieved relevant documents on artificial intelligence in digestive tract diseases from PubMed and Medline. This review elaborates on the knowledge of computer-aided diagnosis in digestive endoscopy.

EXPERT OPINION

Artificial intelligence significantly improves diagnostic accuracy, reduces physicians' workload, and provides a shred of evidence for clinical diagnosis and treatment. Shortly, artificial intelligence will have high application value in the field of medicine.