Early Gastrointestinal Cancer Research Articles

An artificial intelligence-based system assisted endoscopists to detect early gastric cancer: a case report

Background: The mucosal changes of early gastric cancers (EGC) are slight and difficult to be recognized, leading to a high miss rate. Artificial intelligence (AI) systems have the potential to improve the detection of EGC. Here, we report a case of early gastric cancer discovered by an endoscopist with the assistance of an AI system. Case presentation: A 67-year-old male patient came to our hospital for Esophagogastroduodenoscopy (EGD) due to a routine physical examination. He had previously been healthy but was treated for a Helicobacter pylori infection two years ago. In the process of EGD, the AI system flagged a tiny mucosal lesion that was far away and was not detected by the endoscopist, and this lesion attracted the endoscopist's additional attention. After the close observation of the lesion, the AI system immediately gave a red prompt box, suggesting that the endoscopist further observe it. Under magnifying narrow-band imaging (ME-NBI), the mucosal glands and blood vessels of the lesion were irregular, and AI diagnosed it as a suspicious gastric carcinoma. Biopsy pathology showed that it was high-grade intraepithelial neoplasia, and after endoscopic mucosal dissection (ESD), post-ESD histology confirmed that the lesion was a highly differentiated adenocarcinoma confined to the mucosa, with a lesion range of 1.1cm × 1.0cm. The patient was discharged from the hospital without any postoperative complications. Conclusion: AI has been widely applied in the field of gastrointestinal endoscopy and has the potential to help improve the detection rate of early gastrointestinal cancers. We reported a case of early gastric cancer discovered by the endoscopist with the assistance of AI.

An artificial intelligence-based system assisted endoscopists to detect early gastric cancer: a case report

Background: The mucosal changes of early gastric cancers (EGC) are slight and difficult to be recognized, leading to a high miss rate. Artificial intelligence (AI) systems have the potential to improve the detection rate of EGC. Here, we reported a case of EGC discovered by an endoscopist with the assistance of an AI system. Case presentation: A 67-year-old male patient came to our hospital for Esophagogastroduodenoscopy (EGD) due to a routine physical examination. He had previously been healthy but was treated for a Helicobacter pylori infection two years ago. In the process of EGD, the AI system flagged a tiny mucosal lesion that was far away and was not detected by the endoscopist, and this lesion attracted the endoscopist's additional attention. After the close observation of the lesion, the AI system immediately gave a red prompt box, suggesting that the endoscopist further observe it. Under magnifying endoscopy with narrow-band imaging (ME-NBI), the mucosal glands and blood vessels of the lesion were found to be irregular, and this patient was diagnosed with suspicious gastric carcinoma by AI. Biopsy pathology showed that it was high-grade intraepithelial neoplasia, and after endoscopic mucosal dissection (ESD), post-ESD histology confirmed that the lesion was a highly differentiated adenocarcinoma confined to the mucosa, with a lesion range of 1.1 cm × 1.0 cm. The patient was discharged from the hospital without any postoperative complications. Conclusion: AI has been widely applied in the field of gastrointestinal endoscopy and has the potential to help improve the detection rate of early gastrointestinal cancers. We reported a case of early gastric cancer discovered by the endoscopist with the assistance of AI.

AGA Clinical Practice Update on Surveillance After Pathologically Curative Endoscopic Submucosal Dissection of Early Gastrointestinal Neoplasia in the United States: Commentary

The purpose of this American Gastroenterological Association (AGA) Institute Clinical Practice Update was to review the available evidence and provide expert advice regarding surveillance using endoscopy and other relevant modalities after removal of dysplastic lesions and early gastrointestinal cancers with endoscopic submucosal dissection deemed to be pathologically curative. This Clinical Practice Update was commissioned and approved by the AGA Institute Clinical Practice Updates Committee and the AGA Governing Board to provide timely guidance on a topic of high clinical importance to the AGA membership, and underwent internal peer review by the Clinical Practice Updates Committee and external peer review through standard procedures of Gastroenterology. This expert commentary incorporates important as well as recently published studies in this field, and it reflects the experiences of the authors, who are advanced endoscopists with high-level expertise in performing endoscopic submucosal dissection to treat dysplasia and early cancers in the luminal gastrointestinal tract.

Early gastrointestinal cancer: The application of artificial intelligence

Early gastrointestinal cancer: The application of artificial intelligence

Training Simulators for Gastrointestinal Endoscopy: Current and Future Perspectives.

Simple SummaryOver the last decades, visual endoscopy has become a gold standard for the detection and treatment of gastrointestinal cancers. However, mastering endoscopic procedures is complex and requires long hours of practice. In this context, simulation-based training represents a valuable opportunity for acquiring technical and cognitive skills, suiting the different trainees’ learning pace and limiting the risks for the patients. In this regard, the present contribution aims to present a critical and comprehensive review of the current technology for gastrointestinal (GI) endoscopy training, including both commercial products and platforms at a research stage. Not limited to it, the recent revolution played by the technological advancements in the fields of robotics, artificial intelligence, virtual/augmented reality, and computational tools on simulation-based learning is documented and discussed. Finally, considerations on the future trend of this application field are drawn, highlighting the impact of the most recent pandemic and the current demographic trends.Gastrointestinal (GI) endoscopy is the gold standard in the detection and treatment of early and advanced GI cancers. However, conventional endoscopic techniques are technically demanding and require visual-spatial skills and significant hands-on experience. GI endoscopy simulators represent a valid solution to allow doctors to practice in a pre-clinical scenario. From the first endoscopy mannequin, developed in 1969, several simulation platforms have been developed, ranging from purely mechanical systems to more complex mechatronic devices and animal-based models. Considering the recent advancement of technologies (e.g., artificial intelligence, augmented reality, robotics), simulation platforms can now reach high levels of realism, representing a valid and smart alternative to standard trainee/mentor learning programs. This is particularly true nowadays, when the current demographic trend and the most recent pandemic demand, more than ever, the ability to cope with many patients. This review offers a broad view of the technology available for GI endoscopy training, including platforms currently in the market and the relevant advancements in this research and application field. Additionally, new training needs and new emerging technologies are discussed to understand where medical education is heading.

Management of Bleeding in Advanced Endoscopic Procedures

Endoscopic mucosal resection and endoscopic submucosal dissection are used for the treatment of early gastrointestinal tract cancers. Bleeding is one of the most common complications encountered when performing these procedures. It is more common in gastric cases than in esophageal and colorectal cases. It is important to take measures before, during and after the procedure to mitigate the risk of bleeding. Patient history should be carefully questioned for bleeding tendency, the use of medications which may potentiate bleeding and the presence of a condition known to increase the risk of bleeding. In the case of bleeding during the procedure, a knife, coagrasper, hot biopsy forceps or hemoclip may be used. Although bleeding is a common complication in advanced endoscopic procedures, it can be easily managed in experienced hands and effective intervention methods.

Endoscopic Submucosal Dissection in North America: A Large Prospective Multicenter Study

Endoscopic submucosal dissection (ESD) in Asia has been shown to be superior to endoscopic mucosal resection (EMR) and surgery for the management of selected early gastrointestinal cancers. We aimed to evaluate technical outcomes of ESD in North America. We conducted a multicenter prospective study on ESD across 10 centers in the United States and Canada between April 2016 and April 2020. End points included rates of en bloc resection, R0 resection, curative resection, adverse events, factors associated with failed resection, and recurrence post-R0 resection. Six hundred and ninety-two patients (median age, 66 years; 57.8% were men) underwent ESD (median lesion size, 40 mm; interquartile range, 25-52 mm) for lesions in the esophagus (n = 181), stomach (n= 101), duodenum (n= 11), colon (n= 211) and rectum (n= 188). En bloc, R0, and curative resection rates were 91.5%, 84.2%, and 78.3%, respectively. Bleeding and perforation were reported in 2.3% and 2.9% of the cases, respectively. Only 1 patient (0.14%) required surgery for adverse events. On multivariable analysis, severe submucosal fibrosis was associated with failed en bloc, R0, and curative resection and higher risk for adverse events. Overall recurrence was 5.8% (31 of 532) at a mean follow-up of 13.3 months (range, 1-60 months). In this large multicenter prospective North American experience, we demonstrate that ESD can be performed safely, effectively, and is associated with a low recurrence rate. The technical resection outcomes achieved in this study are in line with the current established consensus quality parameters and further support the implementation of ESD for the treatment of select gastrointestinal neoplasms; ClinicalTrials.gov, Number: NCT02989818.

A comprehensive analysis of classification methods in gastrointestinal endoscopy imaging.

Gastrointestinal (GI) endoscopy has been an active field of research motivated by the large number of highly lethal GI cancers. Early GI cancer precursors are often missed during the endoscopic surveillance. The high missed rate of such abnormalities during endoscopy is thus a critical bottleneck. Lack of attentiveness due to tiring procedures, and requirement of training are few contributing factors. An automatic GI disease classification system can help reduce such risks by flagging suspicious frames and lesions. GI endoscopy consists of several multi-organ surveillance, therefore, there is need to develop methods that can generalize to various endoscopic findings. In this realm, we present a comprehensive analysis of the Medico GI challenges: Medical Multimedia Task at MediaEval 2017, Medico Multimedia Task at MediaEval 2018, and BioMedia ACM MM Grand Challenge 2019. These challenges are initiative to set-up a benchmark for different computer vision methods applied to the multi-class endoscopic images and promote to build new approaches that could reliably be used in clinics. We report the performance of 21 participating teams over a period of three consecutive years and provide a detailed analysis of the methods used by the participants, highlighting the challenges and shortcomings of the current approaches and dissect their credibility for the use in clinical settings. Our analysis revealed that the participants achieved an improvement on maximum Mathew correlation coefficient (MCC) from 82.68% in 2017 to 93.98% in 2018 and 95.20% in 2019 challenges, and a significant increase in computational speed over consecutive years.

Artificial intelligence for cancer detection of the upper gastrointestinal tract.

In recent years, artificial intelligence (AI) has been found to be useful to physicians in the field of image recognition due to three elements: deep learning (that is, CNN, convolutional neural network), a high-performance computer, and a large amount of digitized data. In the field of gastrointestinal endoscopy, Japanese endoscopists have produced the world's first achievements of CNN-based AI system for detecting gastric and esophageal cancers. This study reviews papers on CNN-based AI for gastrointestinal cancers, and discusses the future of this technology in clinical practice. Employing AI-based endoscopes would enable early cancer detection. The better diagnostic abilities of AI technology may be beneficial in early gastrointestinal cancers in which endoscopists have variable diagnostic abilities and accuracy. AI coupled with the expertise of endoscopists would increase the accuracy of endoscopic diagnosis.

Recent advances in third space or intramural endoscopy

Third space endoscopy or intramural endoscopy is based on the principle that the deeper layers of the gastrointestinal tract can be accessed by tunneling in the submucosal space and maintaining the integrity of the overlying mucosa. The era of third space endoscopy started with peroral endoscopic myotomy (POEM) for treatment of achalasia and has expanded to treat various other gastrointestinal disorders. The technique is also currently used for treatment of refractory gastroparesis, Zenker’s diverticulum (ZD), resection of subepithelial tumors and early cancers of the gastrointestinal tract and Hirschsprung’s disease (HD). These procedures are rapidly emerging as minimally invasive alternatives to conventional surgery. They are safe and effective with excellent outcomes. This review focuses on the evolution and current applications of third space endoscopy in various gastrointestinal disorders. Key points: (1) Third space or intramural endoscopy initially started with the POEM procedure for treatment of achalasia; (2) Advancements in procedural techniques have expanded its application to treat other gastrointestinal disorders such as refractory gastroparesis, ZD, HD, resection of subepithelial tumors and early gastrointestinal cancers; (3) These procedures are highly effective with excellent outcomes and low complication rates; and (4) Third space endoscopic procedures are rapidly emerging as minimally invasive alternatives to conventional surgery.

Clinical practice guideline for endoscopic resection of early gastrointestinal cancer.

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by en bloc fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.

Viscosity: An important factor in predicting the performance of submucosal injection materials

Viscous submucosal injection materials (SIMs) that are clinically used in endoscopic treatments for early gastrointestinal cancer and polyps contribute to the treatment effects. However, the relationship between SIM characteristics [such as injection pressure (IP) and submucosal elevation height (SEH)] and viscosity has not been evaluated. The aim of this study was to analyze this relationship and elucidate whether it is possible to predict the SIM characteristics by viscosity measurements. Viscosity, IP, and SEH of conventional and developing SIMs were measured, and the correlation between these values was evaluated. A newly developed measurement model accurately measured IP. The magnitude of IP increased as the endoscopic injection needle gauge, injection speed, and concentration of SIM were increased. The strongest correlations were observed between viscosity at a shear rate of 103 s−1 and IP (correlation coefficient > 0.9, p < .01) and between viscosity at a shear rate of 100 s−1 and the SEH (correlation coefficient > 0.9, p < .01). This study defined the viscosities that represent the SIM characteristics. These findings will contribute to the design and accelerate the development of suitable high-performance SIMs by eliminating complex characterization methods.

A new reliable acoustic respiratory monitoring technology during upper gastrointestinal tract therapeutic endoscopy with CO2 insufflation.

Previous studies documented the effectiveness and benefits of capnography monitoring during propofol-based sedation for colonoscopy to reduce the incidence of hypoxemia. However, the performance of capnography during longer duration endoscopic therapy of upper gastrointestinal tract cancers under CO2 insufflation it is not well known. In this study, we compare a new device with acoustic monitoring technology to standard capnography monitoring. We retrospectively analyzed 49 patients who underwent endoscopic resection of early upper gastrointestinal tract cancer between December 2013 and October 2014. All 49 patients were monitored using both acoustic monitoring technology and standard capnography. We investigated the duration of the periods with unmeasurable respiratory rate during the overall procedure. When comparing standard capnography monitoring to the new acoustic monitoring technology, the ratio of the unmeasurable time was significantly lower in RRa (36.9% vs. 21.6%, p < 0.01). The ratio of unmeasurable respiratory rate by capnography was strongly correlated to the ratio of unmeasurable PETCO2 level by capnography (R2 = 0.847). There were no severe events or adverse events (grade 2 or more) during all 49 procedures. The acoustic monitoring technology provides a more reliable respiratory monitoring when compared to standard capnography during endoscopic resection of upper gastrointestinal tract cancers under CO2 insufflation, even if the procedures were prolonged and complex.

Semi-supervised WCE image classification with adaptive aggregated attention.

Accurate abnormality classification in Wireless Capsule Endoscopy (WCE) images is crucial for early gastrointestinal (GI) tract cancer diagnosis and treatment, while it remains challenging due to the limited annotated dataset, the huge intra-class variances and the high degree of inter-class similarities. To tackle these dilemmas, we propose a novel semi-supervised learning method with Adaptive Aggregated Attention (AAA) module for automatic WCE image classification. Firstly, a novel deformation field based image preprocessing strategy is proposed to remove the black background and circular boundaries in WCE images. Then we propose a synergic network to learn discriminative image features, consisting of two branches: an abnormal regions estimator (the first branch) and an abnormal information distiller (the second branch). The first branch utilizes the proposed AAA module to capture global dependencies and incorporate context information to highlight the most meaningful regions, while the second branch mainly focuses on these calculated attention regions for accurate and robust abnormality classification. Finally, these two branches are jointly optimized by minimizing the proposed discriminative angular (DA) loss and Jensen-Shannon divergence (JS) loss with labeled data as well as unlabeled data. Comprehensive experiments have been conducted on the public CAD-CAP WCE dataset. The proposed method achieves 93.17% overall accuracy in a fourfold cross-validation, verifying its effectiveness for WCE image classification. The source code is available at https://github.com/Guo-Xiaoqing/SSL_WCE.

Clinical Practice Guideline for Endoscopic Resection of Early Gastrointestinal Cancer

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by en bloc fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.

Standardizing the pathological diagnosis of early gastrointestinal cancers

早期发现、早期诊断和早期规范化治疗对降低消化道癌症病死率、改善患者预后具有重要意义。规范化病理学检查是判断内镜下治疗效果的重要环节。但目前国内缺乏一套完整的消化道早癌病理诊断标准及流程，导致病理与临床内镜诊断出现不一致的情况。消化道早癌规范化病理学检查及诊断需要内镜和病理医师的密切配合。.

Safety and usefulness of endoscopic submucosal dissection for early esophageal cancers in elderly patients aged 80years or older.

Endoscopic submucosal dissection (ESD) for early gastrointestinal (GI) cancers is widely performed as a standard treatment in Japan. Given the increasing life expectancy worldwide, it is naturally regarded that the rate of elderly patients diagnosed with early GI cancer has increased. Available guidelines do not specifically outline how to manage endoscopic therapy for the elderly. The aim of this study was to assess the safety and usefulness of ESD for superficial esophageal squamous cell carcinoma (SESCC) in elderly patients. We retrospectively investigated 393 consecutive patients, who underwent 426 ESD for 444 SESCCs from January 2011 to August 2016 at our institution. For this study, patients were divided into 2 groups based on their age; ≥ 80years (Group aged ≥ 80years, n = 42) and < 80years (group aged < 80years, n = 351). Patient demographics, sedation methods, technical outcomes, adverse events, sedatives, dosages given, overall survival, and disease-specific survival were then examined. The ESD procedure time was significantly longer for group aged ≥ 80years than for group aged < 80years (110min [range 29-260] vs 85min [24-504], p = 0.006); however, there was no significant differences between other technical items and adverse events. The 3-year overall survival and disease-specific survival were favorable in both groups. Esophageal ESD for elderly patients aged ≥ 80years can be safely performed. Mid-term outcome was favorable. Our study suggests that esophageal ESD might be a useful treatment for SESCCs.

Clinical Practice Guideline for Endoscopic Resection of Early Gastrointestinal Cancer

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by en bloc fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.

Novel potential tumor biomarkers: Circular RNAs and exosomal circular RNAs in gastrointestinal malignancies.

BackgroundCircular RNAs (circRNAs) are structural ubiquitous RNA molecules. Accumulating evidences have elucidated that circRNAs play essential roles in the pathogenesis of diseases including cancers. Exosomal circRNAs are those circRNAs stably existing in exosomes and having high clinical values as novel potential diagnostic biomarkers of many diseases. Gastrointestinal (GI) malignancies, including pancreatic cancer, colorectal cancer, hepatocellular carcinoma (HCC), and gastric cancer, are leading causes of mortality worldwide and a major global health burden. However, no ideal tumor biomarkers of screening early GI cancers are currently available.MethodsWe collected data through Web of Science. The search terms used were as follows: circular RNA, circRNA, exosomes, exosomal circRNAs, biomarkers, gastrointestinal malignancies, pancreatic cancer, hepatocellular carcinoma, HCC, gastric cancer, colorectal cancer, physiological functions, biogenesis, molecular mechanism. Only articles published in English were included.ResultsWe found that several circRNAs and exosomal circRNAs have been used as potential biomarkers to screen GI cancers including pancreatic cancer (hsa_circ_0001649, circ_0007534, circ_0030235, circRHOT1, circZMYM2, circ‐LDLRAD3, chr14:101402109‐101464448C, chr4:52729603‐52780244C, circ‐IARS, and circ‐PDE8A), HCC (circSETD3, circADAMTS13, hsa_circ_0007874, hsa_circ_104135, circFBLIM1, cSMARCA5, circRNA‐100338, and circPTGR1), colorectal cancer (hsa_circ_0001178, hsa_circ_0000826, hsa_circ_0004771, circDDX17, circITGA7, and circHIPK3), and gastric cancer (hsa_circ_0074362, circNRIP1, circAKT3, circ‐DONSON, circPSMC3, circ‐KIAA1244, circPVRL3, circPVT1, hsa_circ_0000096, ciRS‐133, hsa_circ_0001017, and hsa_circ_0061276).ConclusionCircRNAs and exosomal circRNAs have the potential high clinical diagnostic values for GI malignancies.

Clinical Practice Guideline for Endoscopic Resection of Early Gastrointestinal Cancer.

Although surgery was the standard treatment for early gastrointestinal cancers, endoscopic resection is now a standard treatment for early gastrointestinal cancers without regional lymph node metastasis. High-definition white light endoscopy, chromoendoscopy, and image-enhanced endoscopy such as narrow band imaging are performed to assess the edge and depth of early gastrointestinal cancers for delineation of resection boundaries and prediction of the possibility of lymph node metastasis before the decision of endoscopic resection. Endoscopic mucosal resection and/or endoscopic submucosal dissection can be performed to remove early gastrointestinal cancers completely by <i>en bloc</i> fashion. Histopathological evaluation should be carefully made to investigate the presence of risk factors for lymph node metastasis such as depth of cancer invasion and lymphovascular invasion. Additional treatment such as radical surgery with regional lymphadenectomy should be considered if the endoscopically resected specimen shows risk factors for lymph node metastasis. This is the first Korean clinical practice guideline for endoscopic resection of early gastrointestinal cancer. This guideline was developed by using mainly de novo methods and encompasses endoscopic management of superficial esophageal squamous cell carcinoma, early gastric cancer, and early colorectal cancer. This guideline will be revised as new data on early gastrointestinal cancer are collected.