Endoscopic submucosal dissection (ESD) is a minimally invasive treatment for early gastric cancer; additional treatment may be recommended for patients in whom resection is not curative per the American Society for Gastrointestinal Endoscopy guidelines. The aim of this study was to assess treatment outcomes of ESD for gastric neoplasia, with a focus on cases of non-curative resection.

This was a retrospective study of all individuals undergoing ESD for the treatment of gastric adenocarcinoma or dysplasia in a high-volume tertiary care center in the United States. Data on patient demographic characteristics, clinical history, lesion characteristics, and procedural and clinical outcomes were collected from the electronic medical record.

Among 82 cases undergoing ESD for the management of gastric neoplasia, 32 cases resulted in non-curative resection. 20 of these non-curative cases did not get additional treatment, among which recurrence occurred in two cases with positive horizontal margins only. These patients did not show lymph node metastasis and underwent further endoscopic or surgical resection. There was no recurrence in 11 cases with undifferentiated carcinomas of ≤2 cm in size.

Although this study was limited by its retrospective design, small sample size, and follow-up duration, our findings suggest that a risk-adapted strategy could be employed for certain patients undergoing non-curative ESD per American Society for Gastrointestinal Endoscopy guidelines, with close follow-up instead of routine surgery in select cases with favorable features. Further studies are needed to refine the criteria for additional treatment after non-curative ESD in Western populations.

Gastric cancer remains a leading cause of cancer-related mortality worldwide. In the United States, gastric cancer incidence and mortality are substantially higher among non-White racial and ethnic groups and new immigrants from high-incidence countries. This is in large part related to the higher prevalence of Helicobacter pylori -associated gastric premalignant changes in these populations. Apart from primary prevention, early detection of gastric cancer is the principal strategy to reduce gastric cancer mortality and improve survival. Extensive evidence in Asian countries has demonstrated the benefits of endoscopic screening in detecting early-stage gastric cancer and reducing gastric cancer-related mortality. By contrast, direct, high-quality US-based data, such as from large clinical trials or observational studies, on important outcomes of gastric cancer screening are still lacking. In this review, we evaluate and summarize the latest global evidence on the epidemiology and predisposing factors of gastric cancer as well as the efficacy, benefits vs. risks, and cost-effectiveness of gastric cancer screening. We further discuss the critical knowledge gaps and challenges in promoting gastric cancer screening in the United States. Dedicated research is urgently needed to enrich the US-based data on gastric cancer primary and secondary prevention to inform clinical practice and reduce gastric cancer-related morbidity and mortality in a cost and resource efficient manner.

Recent advances in endoscopic equipment have improved the diagnosis of gastrointestinal tumors. Image-enhanced endoscopy, including narrow-band imaging, blue light imaging, and linked color imaging, has unified magnifying observation classification methods and significantly improved the qualitative and quantitative diagnostic performance of gastrointestinal epithelial tumors. Endoscopic submucosal dissection (ESD), a minimally invasive treatment for early-stage gastrointestinal cancer, is widely used. The aging population in Japan has been gradually increasing. Despite this, ESD has shown good outcomes in older adults. However, long-term prognostic analyses should take into account the high mortality rate from other illnesses. Prognostic indicators such as the Charlson Comorbidity Index (CCI) and the Prognostic Nutrition Index (PNI) should be used to determine whether ESD should be performed. Even in cases of noncurative resection, follow-up without additional surgical resection is an option if there are other comorbidities that affect the prognosis.

Lymphatic involvement is sometimes detected during routine examination of intramucosal (pT1a) gastric cancer resected endoscopically. However, its clinical significance and association with the risk of metastasis remain unknown.

This was a retrospective cohort study of 6797 consecutive patients with pT1a gastric cancers treated by endoscopic submucosal dissection (ESD) at three institutions in Japan from January 2005 to August 2023. Patients with 49 uncommon-type gastric cancer types were excluded. The risk of metastasis for pT1a cancers with lymphatic involvement was quantified by comparing lymph node metastasis and/or metastatic recurrence in patient groups who underwent additional surgery post-ESD or did not undergo surgery but were followed up for > 3 years.

Among the 6748 pT1a cancers treated by ESD, 41 lesions (0.6%) had histologically confirmed lymphatic involvement. Among the 41 patients, 1 was excluded from the analysis of metastasis risk because the follow-up period after ESD without additional surgery was ≤ 3 years. Metastasis was identified in 1 of 40 patients analyzed (2.5%; 95% confidence interval [CI] 0.4%-12.9%), and was not detected in any of the 25 patients with pure differentiated-type lesions (0.0%; 95% CI 0.0%-13.7%).

The low prevalence of metastasis after ESD for pT1a gastric cancer with lymphatic involvement, particularly in patients with pure differentiated-type lesions, suggests a low risk of metastatic recurrence.

Oligometastatic colorectal cancer (OMCRC) patients can achieve long-term disease control with multidisciplinary treatment. However, the development of extensive metastasis worsens prognosis and restricts treatment options. This study aims to develop a predictive model for extensive metastasis in OMCRC to assist in clinical decision-making.

Clinical and pathological data for OMCRC patients were collected from the Second Affiliated Hospital of Soochow University. Patients were randomly divided into training and testing cohorts. Risk factors for extensive metastasis were identified through LASSO regression analysis and COX regression analysis. Three predictive models were developed in the training cohort and validated in the testing cohort: COX regression analysis, Extreme Gradient Boosting (XGBoost), and Survival Support Vector Machine (SurvSVM). Finally, the optimal model was visualized with the nomogram.

A total of 214 patients with OMCRC were enrolled in the study. Four independent risk factors were identified: whether surgery has been undertaken following oligometastasis (WST), histological type (HT), carcinoembryonic antigen at the last follow-up (CAE at last-FU), and preoperative albumin to globulin ratio (Preop-AGR). In the testing cohort, the COX model (1-year AUC = 0.82, 3-year AUC = 0.72, 5-year AUC = 0.85, mean AUC = 0.80) performed best. Decision curve analysis (DCA) confirmed the net benefit of the Cox model, and the nomogram provided accurate predictions of metastasis risk.

CAE at last-FU, Preop-AGR, HT, and WST are independent risk factors for extensive metastasis in OMCRC. The nomogram model incorporating risk factors can assist clinicians in developing optimal treatment for OMCRC patients.

Although health insurance claims data can address questions that clinical trials cannot answer, the uncertainty of disease names and the absence of stage information hinder their use in gastric cancer (GC) research. This study aimed to develop and validate a claims-based algorithm to identify and determine the progression phases of incident GC cases in Japan.

The gold standard for validation in this retrospective observational study was medical records of patients with incident GC who underwent specific treatments, defined by the claim codes associated with GC treatment. The algorithm was developed and refined using a cohort from two large tertiary care medical centers (April-September 2017 and April-September 2019) and subsequently validated using two independent cohorts: one from different periods (October 2017-March 2019 and October 2019-March 2021) and the other from a different institution (a community hospital). The algorithm identified incident cases based on a combination of the International Classification of Diseases, 10th Revision diagnosis codes for GC (C160-169), and claim codes for specific treatments, classifying them into endoscopic, surgical, and palliative groups. Positive predictive value (PPV), sensitivity of incident case identification, and diagnostic accuracy of progression phase determination were evaluated.

The developed algorithm achieved PPVs of 90.0% (1119/1244) and 95.9% (94/98), sensitivities of 98.0% (1119/1142) and 98.9% (94/95) for incident case identification, with diagnostic accuracies of 94.1% (1053/1119) and 93.6% (88/94) for progression phase determination in the two validation cohorts, respectively.

This validated claims-based algorithm could advance real-world GC research and assist in decision-making regarding GC treatment.

Background: The association of intravenous prostacyclin therapy, essential for improving prognosis and survival in pulmonary arterial hypertension (PAH), with gastric epithelial neoplasms is uncertain. This study aimed to analyze the clinicopathologic features of gastric neoplasms in patients with PAH undergoing continuous intravenous prostacyclin therapy. Methods: We screened the registry of patients with pulmonary hypertension who visited the NHO Okayama Medical Center. Of the patients with PAH managed between January 2003 and December 2022, those who underwent esophagogastroduodenoscopy (EGD) were assessed for gastric neoplasms. Their clinical, endoscopic, and histopathological data were reviewed. Results: Among the 186 patients with PAH, 56 underwent EGD, revealing 4 patients (aged 37-50 years) with gastric epithelial neoplastic lesions. All four patients received continuous intravenous prostacyclin therapy for a median of 151 months. Of the 98 patients who received prostacyclin, 28 patients underwent EGD; the incidence of gastric epithelial neoplasms was 4.1% (4/98) and the endoscopic detection rate was 14.3% (4/28). All patients had multiple tumors against a background of hypertrophic gastropathy (histologically being foveolar epithelial hyperplasia), with shared features of distal location, elevated morphology, and absent submucosal invasion. However, lymph node metastasis was observed in one lesion. By immunohistochemistry, the tumors exhibited gastric-predominant mucus phenotype and were managed by surgical or endoscopic resection without recurrence. Conclusions: The consistent clinicopathologic features of these cases suggest an association between continuous intravenous prostacyclin therapy and the development of hypertrophic gastropathy with potential progression to gastric epithelial neoplasia. Further prospective clinical trials are warranted to ensure safer prostacyclin use.

Development of a simple, optimized closure method for mucosal defects left by gastric endoscopic submucosal dissection (ESD) is warranted. Herein, we developed a novel and dedicated closure device called FLEXLOOP and aimed to assess feasibility and safety of the closure using FLEXLOOP following gastric ESD.

This multicenter, prospective, observational study enrolled patients clinically diagnosed with gastric neoplasms < 30 mm in size. Following gastric ESD, closure of the mucosal defect was performed using a FLEXLOOP with standard clips. The primary outcome was the complete closure rate. The secondary outcomes were procedure time, number of clips, sustained closure rate on second-look endoscopy on postoperative days (PODs) 5 to 7, and rate of post-ESD bleeding.

Overall, 35 patients were included in this study. The median specimen size was 32 mm. The mucosal defect was completely closed in 31 patients (89%; 95% confidence interval, 73%-99%) and incompletely closed in four patients (11%). Median closure time was 11 minutes and median number of clips was 10. Second-look endoscopy performed on PODs 5 to 7 demonstrated sustained, partially sustained, and unsustained closures in seven (20%), 22 (63%), and six patients (17%), respectively. Post-ESD bleeding and complications related to FLEXLOOP were not observed.

Closure using FLEXLOOP is feasible and safe. Our technique using this new device can be an attractive option for more easily closing mucosal defects. However, further clinical research is warranted to confirm that this technique can prevent delayed complications.

This article provides an overview of recent advances in endoscopic resection techniques. It includes the brief overview of endoscopic submucosal dissection, regional differences in ESD indications, innovation of ESD techniques, and expansion to full-thickness resection. The article covers cold snare polypectomy for small polyps with tips, underwater endoscopic mucosal resection (U-EMR) for sessile lesions with tips and expanding role of U-EMR, and the key assistive techniques for ESD that have improved the safety and efficacy. Furthermore, it discusses the emerging field of endoscopic full-thickness resection including device-assisted and freehand exposure techniques.

Despite advancements in medical care, surgical technologies, and the development of novel treatments over the past decade, the prognosis for patients with gastric cancer (GC) has only modestly improved. This is primarily due to the fact that the majority of patients are diagnosed at advanced stages or present with metastatic disease. Radical resection remains the cornerstone of potentially curative treatment, yet the overall 5-year survival rate remains below 35%. The management of GC varies globally, influenced by factors such as geographical disparities, patient comorbidities and performance status, surgical approaches, and available medical resources. Multidisciplinary collaboration and a multimodal treatment approach are essential for optimizing patient outcomes. Surgeons must stay updated on emerging surgical concepts and make informed decisions regarding patient selection, timing of intervention, and the adoption of appropriate surgical techniques to improve both quality of life and prognosis. This review aims to provide a surgical perspective on the management of GC across all stages, highlighting the importance of a comprehensive treatment approach. Endoscopic resection may be a viable option for early GC in patients with minimal risk of lymph node metastasis, particularly in elderly patients with high surgical risk or severe comorbidities. For advanced GC, neoadjuvant therapy followed by surgery could be a promising strategy to improve patient outcomes. Conversion surgery offers a potential survival benefit for patients who respond to treatment with tumor downstaging. The treatment of peritoneal carcinomatosis remains challenging; however, hyperthermic intraperitoneal chemotherapy combined with complete cytoreductive surgery or pressurized intraperitoneal aerosolized chemotherapy may prolong survival or improve quality of life in highly selected patients.

To analyze the diagnostic efficiency of the four absolute endoscopic submucosal dissection (ESD) indications for lymph node metastasis (LNM) of Chinese patients with early gastric cancer (EGC).

We retrospectively analyzed EGC patients who underwent radical D2 gastrectomy from January 2019 to December 2022. We evaluated the rate of LNM, false-negative rate, and negative predictive value of the four ESD indications.

Of enrolled 2722 EGC patients, 388 (14.3%) patients presented LNM. Tumor size > 2 cm, ulceration, submucosal invasion, undifferentiated type, and lymphovascular invasion were independent risk factors of LNM in patients with EGC. 1062 (39%) cases of EGC conformed to the four EDS indications; however, 4% of them had LNM. 451 cases were fully in accord with the fourth ESD indication (undifferentiated intramucosal carcinoma without ulceration and a maximum lesion diameter of ≤ 2 cm), and 35 of them had LNM, with a false-negative rate (FNR) of 9.02% and a negative predictive value (NPV) of 92.24%. There was significant difference among the four indications in terms of the rate of LNM (1.0% vs 1.5% vs 1.3% vs 7.8%, P < 0.001), FNR (1.03% vs 0.52% vs 0.26% vs 9.02%, P < 0.001), and NPV (98.99% vs 98.53% vs 98.75% vs 92.24%, P < 0.001).

Overall, the fourth ESD indication was associated with a high rate of LNM compared to the other three indications. Thus, it might not be safe to classify it as an absolute indication in Chinese patients with EGC.

Endoscopic submucosal dissection (ESD) is effective in treating early gastric cancer (EGC). Its role in patients with comorbidities along with more advanced disease is unknown. We sought to evaluate this in a large Western cohort.

Consecutive patients who underwent ESD for EGC in a single tertiary Western endoscopy center over 10 years were prospectively analyzed. The primary outcomes were long-term overall survival (OS) and disease-free survival (DFS) up to 5 years. Secondary outcomes were efficacy and serious adverse events (SAEs).

ESD for 157 cases of EGC in 149 patients was performed in an elderly and comorbid cohort with a mean age of 73.7 years and age-adjusted Charlson Comorbidity Index of 4.2. Over a median follow-up of 51.6 months, no significant differences were found in 5-year OS (88.9% vs 77.9%, P = .290) and DFS (83.2% vs 75.1%, P = .593) between absolute indication EGC and relative indication (RI) EGC. The absolute indication EGC cohort achieved higher en bloc (96.3% vs 87.5%, P = .069) and R0 resection rates (93.6% vs 62.5%, P < .001) when compared with RI EGC. No significant differences were found in SAEs (7.3% vs 12.5%, P = .363). No mortality or surgical resection ensued from adverse events from ESD.

ESD safely confers DFS in poor surgical candidates with RI EGC in a large Western cohort. Patients who are elderly and/or with comorbidities or who decline surgical resection may benefit from ESD and avoid the risks of surgery and its long-term sequelae. (Clinical trial registration number: NCT02306707.).

Gastric cancer (GC) is the fifth most frequently diagnosed cancer and the fifth most common cause of cancer death in the world. Regarding the age at which the diagnosis was made, GC is divided into early-onset gastric cancer (EOGC-up to 45 years of age) and conventional GC (older than 45). EOGC constitutes approximately 10% of all GCs. Numerous reports indicate that EOGC is more aggressive than conventional GC and is often discovered at an advanced tumor stage, which has an impact on the five-year survival rate. The median survival rate for advanced-stage GC is very poor, amounting to less than 12 months. Risk factors for GC include family history, alcohol consumption, smoking, Helicobacter pylori, and Epstein-Barr virus infection. It has been shown that a proper diet and lifestyle can play a preventive role in GC. However, research indicates that risk factors for conventional GC are less correlated with EOGC. In addition, the unclear etiology of EOGC and the late diagnosis of this disease limit the possibilities of effective treatment. Genetic factors are considered a likely cause of EOGC, as young patients are less exposed to environmental carcinogens. Research characterizing GC in young patients is scarce. This comprehensive study presents all aspects: epidemiology, risk factors, new treatment strategies, and future directions.

Whether the Western pT1acN0M0 gastric cancer (GC) patients who met the Japanese expanded criteria could be the candidates for endoscopic treatment (ET) remains unclear because of unknown long-term survival outcomes.

A retrospective cohort study using data from the Surveillance, Epidemiology, and End Results (SEER) program was performed. The survival differences between pT1acN0M0 gastric adenocarcinoma patients who received ET or gastrectomy treatment (GT) were evaluated using multivariate survival analysis.

A total of 314 pT1acN0M0 gastric adenocarcinoma patients who met the expanded criteria were included, 46 patients received ET and 268 patients received GT. pT1acN0M0 gastric adenocarcinoma patients met the expanded criteria underwent ET experienced a similar hazard of cancer-specific death compared with those underwent GT both in the multivariate Cox survival analysis (adjusted hazard ratio [HR]; 1.18, 95% confidence interval [CI] 0.40-3.49; P = 0.766) and the multivariate competing risk model (subdistribution HR [SHR], 1.12, 95% CI 0.38-3.29; P = 0.845). The result that pT1acN0M0 gastric adenocarcinoma patients met the expanded criteria underwent ET experienced comparable survival outcomes to those who underwent GT did not change even compared with those who underwent GT with > 15 lymph nodes examined (adjusted HR, 1.55, 95% CI 0.44-5.49; P = 0.499; SHR, 1.47, 95% CI 0.44-4.88; P = 0.532).

The ET can be considered in Western pT1acN0M0 gastric adenocarcinoma patients who met the Japanese expanded criteria. However, a prospective study should be warranted.

The purpose of this study was to evaluate the feasibility of a simple method named aspiration and coagulation (AC) for reducing the risk of postoperative bleeding after gastric endoscopic submucosal dissection (ESD).

Data were retrospectively reviewed and collected from the medical records and endoscopic and pathologic reports about consecutive patients who underwent ESD for early gastric cancer or precancerous lesions or gastric submucosal lesions from January 2016 to December 2021 at the Seventh Medical Center of Chinese PLA General Hospital. Enrolled patients who underwent the AC method during ESD were included in the AC group, and the others were included in the control group. Propensity score (PS) matching (1:1 match) was used to compensate for the differences that might affect post-ESD bleeding. Massive hemorrhage and overall delayed bleeding events after gastric ESD were compared between the two groups.

Propensity score matching analysis created 242 matched pairs in the study. Characteristics of the subjects such as age and use of antithrombotic drugs were all similar between the two groups after PS matching. The rate of massive hemorrhage and overall delayed bleeding was both significantly lower in the AC group than in the control (0.4% vs. 3.3% for massive hemorrhage, P = 0.037, and 1.2% vs. 5.0% for overall delayed bleeding, P = 0.032), predominantly in mucosal lesions (0.6% vs. 4.4% for massive hemorrhage, P = 0.032, and 1.2% vs. 5.6% for overall delayed bleeding, P = 0.031).

Our study demonstrated that the AC method effectively decreased delayed bleeding events after ESD.

We developed three e-learning systems for endoscopists to acquire the necessary skills to improve the diagnosis of early gastric cancer (EGC) and demonstrated their usefulness using randomized controlled trials. The subjects of the three e-learning systems were "detec-tion", "characterization", and "preoperative assessment". The contents of each e-learning system included "technique", "knowledge", and "obtaining experience". All e-learning systems proved useful for endoscopists to learn how to diagnose EGC. Lecture videos describing "the technique" and "the knowledge" can be beneficial. In addition, repeating 100 self-study cases allows learners to gain "experience" and improve their diagnostic skills further. Web-based e-learning systems have more advantages than other teaching methods because the number of participants is unlimited. Histopathological diagnosis is the gold standard for the diagnosis of gastric cancer. Therefore, we developed a comprehensive diagnostic algorithm to standardize the histopathological diagnosis of gastric cancer. Once we have successfully shown that this algorithm is helpful for the accurate histopathological diagnosis of cancer, we will complete a series of e-learning systems designed to assess EGC accurately.

Endoscopy could help detect early gastric cancer (EGC) and improve the prognosis of patients. The aim of this study was to analyze the impact of endoscopy and endoscopic surveillance on the early detection of gastric cancer (GC), GC staging, and treatment selection.

Patients with GC diagnosed at our center from 2010 to 2022 were retrospectively analyzed and allocated to the short-interval group (had received endoscopy within 3 years before diagnosis), the long-interval group (had received endoscopy more than 3 years before diagnosis), and the unchecked group (had not received endoscopy before diagnosis). The differences in GC staging and treatment modalities among the three groups were analyzed, and the differences in the clinical and pathological features of EGC were further analyzed.

One thousand and twenty-five GC patients were included, with 395 cases of EGC and 630 cases of advanced GC. The proportions of EGC in the short-interval, long-interval, and unchecked groups were 98.0%, 84.2%, and 29.8%, respectively (p < 0.001). Among the 387 lesions of 367 EGC patients were resected by endoscopic submucosal dissection (ESD), 341 (88.1%) exhibited curative resection, and 46 (11.9%) involved noncurative resections. Lesions of EGC differed significantly in diameter, depth of invasion, and curative resection rate (p = 0.033, 0.019, and 0.005, respectively). In the short-interval group, 87.8% of the lesions were ≤ 2 cm, 95.6% of the invasion depths were confined to the mucosal layer, and 96.7% of the eCura scores were A or B. Compared with the unchecked group, they had smaller diameters (RR = 0.419, 95% CI 0.234-0.752), shallower invasion depths (RR = 0.286, 95% CI 0.105-0.777), and a higher curative resection rate (RR = 0.215, 95% CI 0.068-0.676).

Endoscopic surveillance at 3-year intervals can help detect EGC, and the EGC lesions found have smaller diameters and shallower depths of invasion, helping improve the curative resection rate of ESD.

A 70-year-old man was diagnosed with early gastric cancer with ulcerative findings. Endoscopic submucosal dissection as an absolute indication was performed, and en bloc resection was achieved. Pathological examination revealed a well-differentiated adenocarcinoma, 3 × 2 mm in size, intramucosal, with an ulcerative scar, no lymphovascular invasion, and a tumor-free margin. We diagnosed it as a curative resection and followed up with annual endoscopy. Sixteen months after endoscopic submucosal dissection, esophagogastroduodenoscopy revealed a singular ulcer scar; however, serum carcinoembryonic antigen level was elevated. Computed tomography scan showed wall thickening of the gastric antrum and an irregular mass on the dorsal side. Additionally, 18F-fluorodeoxyglucose positron emission tomography/coomputed tomography showed 18F-fluorodeoxyglucose uptake in the gastric antrum, irregular mass, and liver. Endoscopic ultrasonography revealed an internally heterogeneous mass in the gastric antrum region extending from the submucosal layer to the muscularis propria layer. Using an endoscopic ultrasonography-guided fine needle biopsy with a 22-gauge needle for the mass, we diagnosed local recurrence with the submucosal tumor-like appearance, lymph node metastasis, and liver metastases. Unfortunately, the patient died of gastric cancer 3 months after the diagnosis. Here, we report a rare case of local recurrence in the submucosal layer, lymph node metastasis, and liver metastases 16 months after curative endoscopic submucosal dissection.

Previous studies have indicated that red dichromatic imaging (RDI) improved the visibility of gastrointestinal bleeding.

To investigate the recognition of bleeding points during endoscopic submucosal dissection (ESD) under RDI compared with that under white light imaging (WLI).

Consecutive patients scheduled to undergo esophageal or gastric ESD at a single center were enrolled. Paired videos of active bleeding during ESD under WLI and RDI were created. Six endoscopists identified the virtual hemostasis point on still images after random video viewing. The distance between virtual hemostasis and actual bleeding points was scored in four levels (0-3 points), and the association with the color value was analyzed in both WLI and RDI.

We evaluated 116 videos for 58 bleeding points. The median visibility score and recognition rate were significantly higher for RDI than for WLI (2.17 vs. 1.42, p < 0.001 and 62.1% vs 27.6%, p < 0.001). Additionally, the recognition rate of trainees in RDI was higher than that of experts in WLI (60.3% vs. 43.1%, p = 0.067). The median color difference of RDI was significantly higher than that of WLI (8.97 vs. 3.69, p < 0.001). Furthermore, the correlation coefficient between the visibility score and color difference was 0.712 (strong correlation).

RDI can provide better recognition of bleeding points than WLI during ESD. Therefore, further studies are warranted to investigate whether RDI improves ESD outcomes.

With an increasing number of patients with gastrointestinal cancer, effective and accurate early diagnostic clinical tools are required provide better health care for patients with gastrointestinal cancer. Recent studies have shown that artificial intelligence (AI) plays an important role in the diagnosis and treatment of patients with gastrointestinal tumors, which not only improves the efficiency of early tumor screening, but also significantly improves the survival rate of patients after treatment. With the aid of efficient learning and judgment abilities of AI, endoscopists can improve the accuracy of diagnosis and treatment through endoscopy and avoid incorrect descriptions or judgments of gastrointestinal lesions. The present article provides an overview of the application status of various artificial intelligence in gastric and colorectal cancers in recent years, and the direction of future research and clinical practice is clarified from a clinical perspective to provide a comprehensive theoretical basis for AI as a promising diagnostic and therapeutic tool for gastrointestinal cancer.

Because endoscopic submucosal dissection (ESD) for early gastric cancer (EGC) preserves the entire stomach, missed gastric cancers (MGCs) are often found in the remaining gastric mucosa. However, the endoscopic causes of MGCs remain unclear. Therefore, we aimed to elucidate the endoscopic causes and characteristics of MGCs after ESD.

From January 2009 to December 2018, all patients undergoing ESD for initially detected EGC were enrolled. According to a review of EGD images before ESD, we identified the endoscopic causes (perceptual, exposure, sampling errors, and inadequate preparation) and characteristics of MGC in each endoscopic cause.

Of 2208 patients who underwent ESD for initial EGC, 82 patients (3.7%) had 100 MGCs. The breakdown of endoscopic causes of MGCs was as follows: 69 (69%) perceptual errors, 23 (23%) exposure errors, 7 (7%) sampling errors, and 1 (1%) inadequate preparation. Logistic regression analysis showed that the risk factors for perceptual error were male sex (odds ratio [OR], 2.45; 95% confidence interval [CI], 1.16-5.18), isochromatic coloration (OR, 3.17; 95% CI, 1.47-6.84), greater curvature (OR, 2.31; 95% CI, 1.121-4.40), and lesion size ≤12 mm (OR, 1.74; 95% CI, 1.07-2.84). The sites of exposure errors were around the incisura angularis (11 [48%]), posterior wall of the gastric body (6 [26%]), and antrum (5 [21%]).

We identified MGCs in 4 categories and clarified their characteristics. Quality improvements in EGD observation, with attention to the risks of perceptual and site of exposure errors, can potentially prevent missing EGCs.

This study aimed to determine long-term outcomes of gastric endoscopic submucosal dissection (ESD) in Western settings based on the latest Japanese indication criteria, and to examine predictors of outcomes and complications.

Data were collected from consecutive patients undergoing gastric ESD at four participating centers from 2009 to 2021. Retrospective analysis using logistic regression and survival analysis was performed.

415 patients were included (mean age 71.7 years; 56.4 % male). Absolute indication criteria (2018 guideline) were met in 75.3 % of patients. Median follow-up was 52 months. Post-resection histology was adenocarcinoma, high grade dysplasia, and low grade dysplasia in 49.9 %, 22.7 %, and 17.1 %, respectively. Perforation, early and delayed bleeding occurred in 2.4 %, 4.3 %, and 3.4 %, respectively. Rates of en bloc and R0 resection, and recurrence on first endoscopic follow-up were 94.7 %, 83.4 %, and 2.7 %, respectively. Relative indication (2018 guideline) for ESD was associated with R1 outcome (P = 0.02). Distal location (P = 0.002) and increased procedure time (P = 0.04) were associated with bleeding, and scarring (P = 0.009) and increased procedure duration (P = 0.003) were associated with perforation. Recurrence-free survival at 2 and 5 years was 94 % and 83 %, respectively.

This is the largest Western multicenter cohort and suggests that gastric ESD is safe and effective in the Western setting. A quarter of patients fell outside the new absolute indications for ESD, suggesting that Western practice involves more advanced lesions. We identified the predictors of complications, which should help to inform future Western practice and research.

Several studies have reported the metachronous gastric cancers (MGCs) with possible lymph node metastasis (LNM) after endoscopic submucosal dissection (ESD) and Helicobacter pylori (H. pylori) eradication in which a curative ESD had not been achieved. There have been no published reports of evaluations of the features of patients with MGC with possible LNM after ESD and H. pylori eradication.

We identified 264 patients with 369 MGCs after H. pylori eradication among the 4354 patients with 5059 early gastric cancers (EGCs) who underwent ESD between 1999 and 2017 and divided them into two groups: patients with MGCs with possible LNM (Group I) and patients with MGCs undergone curative ESD (Group II). We retrospectively compared the features of patients with MGCs and patients with EGCs at index ESD in the two groups.

Group I consisted of 20 patients with 21 MGCs, and Group II consisted of 244 patients with 348 MGCs. Group I lesions were significantly more common in the posterior wall than in the lesser curvature (odds ratio [OR] = 3.97; 95% confidence intervals [CI] 1.20-13.10). Development of Group I was significantly more common in patients with a body mass index (BMI) < 19.0 kg/m2 than in patients with a BMI ≥ 19.0 kg/m2 at index ESD (OR = 4.44; 95% CI 1.30-15.20).

During surveillance endoscopy after gastric ESD and H. pylori eradication, the posterior wall should be carefully examined to detect MGCs early. Lower BMI may be associated with the development of MGCs with possible LNM.

Endoscopic submucosal dissection (ESD) is the standard treatment for early gastric cancer in Japan. Pathological evaluation of ESD specimens is considered essential to determine if additional gastrectomy is necessary. Usually, specimens resected by ESD are sliced into 2-3 mm wide sections, and each section is examined for depth of tumor and lymphovascular invasion. Nevertheless, in most cases of additional gastrectomy, lymph node metastasis is not present. Given that there are few-studies on how clinical-decisions based on the pathologic-evaluation-method, in particular the specimen cut-width, influence patient outcomes, we retrospectively evaluated whether reducing the number of cuts to one-half or one-third would result in underestimation of the real need for additional surgery. The effect of the actual cut-width on recommended treatment (referral to operation) and patient-outcomes was also assessed.

Pathological records of 498 lesions from 439 patients were reviewed and re-evaluated. All pathological descriptions are based on the gastric cancer classification system of the Japanese Gastric Cancer Association, 15th edition.

In 5.8% and 8.5% of the total specimens, underdiagnosis of tumor-depth and lymphovascular invasion occurred when the number of sections was reduced to one-half and one-third, respectively. Significantly more submucosal invasions were found in the group in which the cut-with was between 3 and 4 mm than in the group in which the cut width was less than 3 mm.

Evaluation of the appropriate cut-width is important and should be discussed from the standpoint of labor costs and lost opportunities to search for molecular markers in ESD materials.

Although endoscopic submucosal dissection (ESD) is becoming more common for early gastric cancer, it requires more advanced techniques and a longer treatment duration than endoscopic mucosal resection. Hybrid ESD using a multifunctional snare (SOUTEN) has been reported to be effective for colorectal lesions, as it can reduce treatment duration. Endoscopic suturing of post-ESD mucosal defects has been reported to reduce the incidence of ESD-related complications.

This study reports outpatient hybrid ESD for early gastric cancer using SOUTEN, followed by endoscopic suturing of post-ESD mucosal defects in an 86-year-old man. On referral for ESD, a 10-mm flat, depressed lesion was found on the posterior wall of the gastric antrum, the depth of which was expected to be mucosal. Given his history of delirium, we performed outpatient endoscopic treatment. The procedure used was hybrid ESD using SOUTEN to reduce the duration of treatment and endoscopic suturing of post-ESD mucosal ESD defects to reduce complications. The procedure time was 62 min and the lesion was completely resected based on histopathological examination, with no reported postoperative complications.

This safe and useful procedure may be especially important for outpatient endoscopic treatment.

Early gastric cancer comprises gastric malignancies that are confined to the mucosa or submucosa, irrespective of lymph node metastasis. Endoscopic resection is currently pivotal for the management of such early lesions, and it is the recommended treatment for tumors presenting a very low risk of lymph node metastasis. In general, these lesions consist of two groups of differentiated mucosal adenocarcinomas: non-ulcerated lesions (regardless of their size) and small ulcerated lesions. Endoscopic submucosal dissection is the technique of choice in most cases. This procedure has high rates of complete histological resection while maintaining gastric anatomy and its functions, resulting in fewer adverse events than surgery and having a lesser impact on patient-reported quality of life. Nonetheless, approximately 20% of resected lesions do not fulfill curative criteria and demand further treatment, highlighting the importance of patient selection. Additionally, the preservation of the stomach results in a moderate risk of metachronous lesions, which underlines the need for surveillance. We review the current evidence regarding the endoscopic treatment of early gastric cancer, including the short-and long-term results and management after resection.

This study aimed to identify the predictive factors of lymph node metastasis (LNM) in patients with early gastric cancer (EGC) and to evaluate the applicability of the Japanese treatment guidelines for endoscopic resection in the western population.

Five hundred-one patients with pathological diagnoses of EGC were included. Univariate and multivariate analyses were conducted to identify the predictive factors of LNM. EGC patients were distributed according to the indications for endoscopic resection of the Eastern guidelines. The incidence of LNM was evaluated in each group.

From 501 patients with EGC, 96 (19.2%) presented LNM. In 279 patients with tumors with submucosal infiltration (T1b), 83 (30%) patients had LNM. Among 219 patients who presented tumors > 3 cm, 63 (29%) patients had LNM. Thirty-one percent of patients with ulcerated tumors presented LMN (33 out of 105). In 76 patients and 24 patients with lymphovascular and perineural invasion, the percentage of LMN was 84% and 87%, respectively. In the multivariate analysis, a tumor diameter >3 cm, submucosal invasion, lymphovascular, and perineural invasion were independent predictors of LMN in EGC. No patient with differentiated, non-ulcerated mucosal tumors presented LNM regardless of tumor size. Three of 17 patients (18%) with differentiated, ulcerated mucosal tumors and ≤ 3 cm presented LNM. No LNM was evidenced in patients with undifferentiated mucosal tumors and ≤ 2 cm.

The presence of LNM in Western EGC patients was independently related to larger tumors (>3 cm), submucosal invasion, lymphovascular and perineural invasion. The Japanese absolute indications for EMR are safe in the Western population. Likewise, Western patients with differentiated, non-ulcerated mucosal tumors, and larger than 2 cm are susceptible to endoscopic resection. Patients with undifferentiated mucosal tumors smaller than 2 cm presented encouraging results and ESD could be recommended only for selected cases.

To evaluate the pathological characteristics of endoscopic submucosal dissection (ESD) specimens for early gastric cancer and precancerous lesions, accumulating experience for clinical management and pathological analysis.

A total of 411 cases of early gastric cancer or precancerous lesions underwent ESD. According to the Japanese guidelines for ESD treatment of early gastric cancer and classification of gastric carcinoma, the clinicopathological data, pathologic evaluation, concordance rate of pathological diagnosis between preoperative endoscopic forceps biopsies and their ESD specimens (in 400 cases), as well as the risk factors of non-curative resection of early gastric cancer, were analyzed retrospectively.

23.4% (96/411) of the 411 cases were adenoma/low-grade dysplasia and 76.6% (315/411) were early gastric cancer. The latter included 28.0% (115/411) non-invasive carcinoma/high-grade dysplasia and 48.7% (200/411) invasive carcinoma. The concordance rate of pathological diagnosis between endoscopic forceps biopsies and ESD specimens was 66.0% (264/400), correlating with pathological diagnosis and lesion location (P < 0.01). The rate of upgraded diagnosis and downgraded diagnosis after ESD was 29.8% (119/400) and 4.2% (17/400), respectively. Among the 315 cases of early gastric cancer, there were 277 cases (87.9%) of differentiated type and 38 cases (12.1%) of undifferentiated type. In the study, 262 cases (83.2%) met with absolute indication, while 53 cases (16.8%) met relative indication. En bloc and curative resection rates were 98.1% and 82.9%, respectively. Risk factors for non-curative resection included a long diameter >20 mm (OR=3.631, 95%CI: 1.170-11.270, P=0.026), tumor infiltration into submucosa (OR=69.761, 95%CI: 21.033-231.376, P < 0.001)and undifferentiated tumor histology (OR=16.950, 95%CI: 4.585-62.664, P < 0.001).

Several subjective and objective factors, such as the limitations of biopsy samples, the characteristics and distribution of the lesions, different pathological understanding, and the endoscopic sampling and observation, can lead to the differences between the preoperative and postoperative pathological diagnosis of ESD. In particular, the pathological upgrade of postoperative diagnosis was more significant and should receive more attention by endoscopists and pathologists. The curative resection rate of early gastric cancer in ESD was high. Non-curative resection was related to the long diameter, the depth of tumor invasion and histological classification. ESD can also be performed in undifferentiated early gastric cancer if meeting the indication criteria. The comprehensive and standardized pathological analysis of ESD specimens is clinically important to evaluate the curative effect of ESD operation and patient outcomes.

Local excision (LE) for early-stage gastric cancer has expanded in the United States over recent years, however, national outcomes are unknown. The objective of the study was to evaluate national survival outcomes following LE for early-stage gastric cancer.

Patients with resectable gastric adenocarcinoma between 2010 and 2016 were identified from the National Cancer Database then classified by LE curability into eCuraA (high) and eCuraC (low) according to Japanese Gastric Cancer Association guidelines. Demographics, clinical/provider descriptors, and perioperative/survival outcomes were extracted. Propensity-weighted cox proportional hazards regression assessed factors associated with overall survival.

Patients were stratified into eCuraA (N = 1167) and eCuraC (N = 13,905) subgroups. Postoperative 30-day mortality (0% vs 2.8%, p < 0.001) and readmission (2.3% vs 7.8%, p = 0.005) favored LE. Local excision was not associated with survival on propensity-weighted analyses. However, among eCuraC patients, LE was associated with higher likelihood of positive margins (27.1% vs 7.0%, p < 0.001), which was the strongest predictor of poor survival (HR 2.0, p < 0.001).

Although early morbidity is low, oncologic outcomes following LE are compromised for eCuraC patients. These findings support careful patient selection and treatment centralization in the early adoption phase of LE for gastric cancer.

Gastric cancer is the fifth most common cancer and in 2018, it was the third most common cause of cancer-related deaths worldwide. Endoscopic advances continue to be made for the diagnosis and management of both early gastric cancer and premalignant gastric conditions. In this review, we discuss the epidemiology and risk factors of gastric cancer and emphasize the differences in early vs late-stage gastric cancer outcomes. We then discuss endoscopic advances in the diagnosis of early gastric cancer and premalignant gastric lesions. This includes the implementation of different imaging modalities such as narrow-band imaging, chromoendoscopy, confocal laser endomicroscopy, and other experimental techniques. We also discuss the use of endoscopic ultrasound in the diagnosis and staging of early gastric cancer. We then discuss the endoscopic advances made in the treatment of these conditions, including endoscopic mucosal resection, endoscopic submucosal dissection, and hybrid techniques such as laparoscopic endoscopic cooperative surgery. Finally, we comment on the current suggested recommendations for surveillance of both gastric cancer and its premalignant conditions.

Superficial epithelial gastric neoplasms can be divided into adenomas and early carcinomas. Histological diagnosis by endoscopic forceps biopsy is crucial for the diagnosis and management of gastric neoplasms. It is difficult to distinguish features of gastric neoplasms in small biopsy specimens; hence, gastric carcinomas can be underdiagnosed as adenomas. Recent developments in image-enhanced endoscopy have improved the ability to differentiate between carcinomatous and non-carcinomatous lesions. To investigate the prevalence of gastric carcinoma in lesions initially diagnosed as adenomas by forceps biopsy and assess the usefulness of image-enhanced endoscopy in distinguishing carcinomas. A total of 142 lesions of gastric adenomas, diagnosed by biopsy and resected endoscopically between January 2010 and May 2020, were retrospectively evaluated. Images were captured by white-light endoscopy (WLE), magnifying endoscopy with narrow-band imaging (M-NBI), and magnifying endoscopy with acetic acid and narrow-band imaging (M-AANBI); they were analyzed and compared with histopathological results. The diagnostic performance of M-AANBI was compared with that of M-NBI. Of the 142 lesions, 58 (40.8%) were pathologically diagnosed as adenocarcinomas. On WLE images, a depressed macroscopic type and size ≥20 mm were significant predictors of carcinoma (P < .001); however, they displayed low sensitivities (32.8% and 41.4%, respectively). M-AANBI displayed significantly higher sensitivity, specificity, and accuracy for distinguishing carcinomas than M-NBI (94.8% vs 74.1%, 81.0% vs 72.6%, and 86.6% vs 73.2%, P < .05). In conclusion, carcinoma was prevalent in 40.8% of gastric lesions initially diagnosed as adenomas by forceps biopsy. M-AANBI may be more useful than M-NBI and WLE in distinguishing gastric carcinomas from adenomas.

We aimed to clarify the long-term outcomes of endoscopic resection (ER) for early gastric cancers (EGCs) based on pathological curability in a multicenter prospective cohort study.

We analyzed the long-term outcomes of 9054 patients with 10,021 EGCs undergoing ER between July 2010 and June 2012. Primary endpoint was the 5-year overall survival (OS). The hazard ratio for all-cause mortality was calculated using the Cox proportional hazards model. We also compared the 5-year OS with the expected one calculated for the surgically resected patients with EGC. If the lower limit of the 95% confidence interval (CI) of the 5-year OS exceeded the expected 5-year OS minus a margin of 5% (threshold 5-year OS), ER was considered to be effective. Pathological curability was categorized into en bloc resection, negative margins, and negative lymphovascular invasion: differentiated-type, pT1a, ulcer negative, ≤2 cm (Category A1); differentiated-type, pT1a, ulcer negative, >2 cm or ulcer positive, ≤3 cm (Category A2); undifferentiated-type, pT1a, ulcer negative, ≤2 cm (Category A3); differentiated-type, pT1b (SM1), ≤3 cm (Category B); or noncurative resections (Category C).

Overall, the 5-year OS was 89.0% (95% CI, 88.3%-89.6%). In a multivariate analysis, no significant differences were observed when the hazard ratio of Categories A2, A3, and B were compared with that of A1. In all the pathological curability categories, the lower limit of the 95% CI for the 5-year OS exceeded the threshold 5-year OS.

ER can be recommended as a standard treatment for patients with EGCs fulfilling Category A2, A3, and B, as well as A1 (UMIN Clinical Trial Registry, UMIN000005871).

Endoscopic resection (ER) is widely performed for early gastric cancer (EGC) with a negligible risk of lymph node metastasis (LNM) in Eastern Asian countries. In particular, endoscopic submucosal dissection (ESD) leads to a high en bloc resection rate, enabling accurate pathological evaluation. As undifferentiated EGC (UD-EGC) is known to result in a higher incidence of LNM and infiltrative growth than differentiated EGC (D-EGC), the indications for ER are limited compared with those for D-EGC. Previously, clinical staging as intramucosal UD-EGC ≤2 cm, without ulceration, was presented as 'weakly recommended' or 'expanded indications' for ER in the guidelines of the United States, Europe, Korea, and Japan. Based on promising long-term outcomes from a prospective multicenter study by the Japan Clinical Oncology Group (JCOG) 1009/1010, the status of this indication has expanded and is now considered 'absolute indications' in the latest Japanese guidelines published in 2021. In this study, which comprised 275 patients with UD-EGC (cT1a, ≤2 cm, without ulceration) treated with ESD, the 5-year overall survival (OS) was 99.3% (95% confidence interval, 97.1%-99.8%), which was higher than the threshold 5-year OS (89.9%). Currently, the levels of evidence grades and recommendations for ER of UD-EGC differ among Japan, Korea, and Western countries. Therefore, a further discussion is warranted to generalize the indications for ER of UD-EGC in countries besides Japan.

endoscopic submucosal dissection (ESD) is the standard treatment for differentiated early gastric cancer (EGC). However, its expanded indication for undifferentiated EGC is controversial. In this study, the efficacy and safety of ESD versus surgery in patients with undifferentiated EGC were compared.

four databases were searched until February 24, 2022, for studies assessing patients with undifferentiated EGC that met an expanded indication for endoscopic resection and who were treated with ESD or surgery. Primary outcomes were all-cause mortality and any recurrence. Secondary outcomes were complete histological resection, local recurrence, metachronous recurrence, synchronous recurrence, distant metastasis, overall complication, and bleeding. All meta-analyses were performed using a random-effects models. Unadjusted (risk ratio [RR]) and adjusted (aRR and hazard ratio [aHR]) estimates with 95 % confidence interval (CI) were calculated.

seven cohort studies were included (n = 2637). The use of ESD was significantly associated with higher all-cause mortality compared to surgery (RR, 2.17; 95 % CI, 1.24-3.81); adjusted all-cause mortality effects were not significant (aRR, 2.28; 95 % CI, 0.95-5.47 and aHR, 1.97; 95 % CI, 0.85-4.53). ESD was associated with a higher risk of any recurrence using unadjusted (RR, 5.24; 95 % CI, 1.49-18.46) and adjusted (aRR, 7.89; 95 % CI, 1.52-40.95 and aHR, 3.73; 95 % CI, 1.17-11.90) estimates. The risk of local recurrence, synchronous recurrence and bleeding were significantly higher for ESD versus surgery. No significant differences were found for other secondary outcomes.

although ESD is associated with a higher risk of any recurrence, adjusted all-cause mortality is similar during follow-up. Overall complications were similar between ESD and surgery.

The sixth edition of the Japanese Gastric Cancer Treatment Guidelines was completed in July 2021, incorporating new evidence that emerged after publication of the previous edition. It consists of a text-based "Treatments" part and a "Clinical Questions" part including recommendations and explanations for clinical questions. The treatments parts include a comprehensive description regarding surgery, endoscopic resection and chemotherapy for gastric cancer. The clinical question part is based on the literature search and evaluation by an independent systematic review team. Consequently, not only evidence for each therapeutic recommendation was clearly shown, but it also identified the research fields that require further evaluation to provide appropriate recommendations.

Endoscopic submucosal dissection (ESD) remains an investigational issue for early gastric cancer (EGC) with expanded indications owing to the risk of lymph node metastasis. In this study, we aimed to evaluate the clinical outcomes and safety of ESD versus surgical resection (SR) for EGC with expanded indications.

The systematic review selected studies from PubMed, Embase, Cochrane and Web of Science databases from 2010 to 2020, and compared survival and clinical safety data of ESD with those of surgical resection for EGC with expanded indications. The fixed-effects or random-effects model was used to calculate the differences between the two groups. To assess the validity of the eligible studies, risk of bias was measured using the Newcastle-Ottawa Quality Assessment Scale.

Nine retrospective studies were used to calculate the differences in survival and clinical safety data between the two groups for EGC with expanded indications. Differences were not significant between the groups in terms of age, sex, tumour size, tumour histology or lesion morphology. Regarding tumour site, tumours located in the L area (the lower third of the stomach) were more likely to be found in the ESD group. With regard to metachronous and synchronous carcinomas, there was a significant difference favouring SR treatment (metachronous: OR=0.12, 95% CI=0.05 to 0.25, p<0.00001; synchronous: OR=0.11, 95% CI=0.02 to 0.46, p=0.003). Adverse event data were identified in six studies showing a significant difference favouring ESD treatment (ESD vs SR, OR=0.49, 95% CI=0.34 to 0.72. p=0.002). Additionally, six studies evaluating 5-year overall survival showed no significant differences between the two groups (HR=1.22, 95% CI=0.66 to 2.25, p=0.53). With regard to 5-year disease-free survival, patients with expanded indication EGC undergoing SR showed better survival (ESD vs SR, HR=3.29, 95% CI=1.60 to 6.76, p=0.001).

ESD provided favourable results for patients with EGC with expanded indications regarding clinical outcomes and safety in retrospective studies. Further, to detect synchronous or metachronous lesions, endoscopic surveillance should be performed following ESD. However, the included studies were observational, some did not have adequate adjustment for confounding factors and their results lacked generalisability due to their origin. Thus, further related randomised controlled trials are urgently encouraged.

CRD42021251068.

Early gastric cancer (EGC) is defined as a lesion restricted to the mucosa or submucosa, independent of size or evidence of regional lymph node metastases. Although computed tomography (CT) is the main technique for determining the stage of gastric cancer (GC), the accuracy of CT for determining tumor invasion of EGC was still unsatisfactory by radiologists. In this research, we attempted to construct an AI model to discriminate EGC in portal venous phase CT images.

We retrospectively collected 658 GC patients from the first affiliated hospital of Nanchang university, and divided them into training and internal validation cohorts with a ratio of 8:2. As the external validation cohort, 93 GC patients were recruited from the second affiliated hospital of Soochow university. We developed several prediction models based on various convolutional neural networks, and compared their predictive performance.

The deep learning model based on the ResNet101 neural network represented sufficient discrimination of EGC. In two validation cohorts, the areas under the curves (AUCs) for the receiver operating characteristic (ROC) curves were 0.993 (95% CI: 0.984-1.000) and 0.968 (95% CI: 0.935-1.000), respectively, and the accuracy was 0.946 and 0.914. Additionally, the deep learning model can also differentiate between mucosa and submucosa tumors of EGC.

These results suggested that deep learning classifiers have the potential to be used as a screening tool for EGC, which is crucial in the individualized treatment of EGC patients.

As the indications for endoscopic submucosal dissection (ESD) for early gastric cancer have been revised, diagnostic ESD has increased. However, despite the technical difficulty of ESD for large lesions, the degree to which curative resection can be achieved has not been clarified. This study investigated the feasibility and safety of ESD for gastric lesions larger than 5 cm.

This retrospective multicenter study included 3474 gastric lesions treated by ESD from April 2012 to December 2021. We compared clinicopathological characteristics and treatment outcomes between lesions ≥ 5 cm and lesions < 5 cm.

There were 128 lesions in the ≥ 5 cm group and 3282 lesions in the < 5 cm group. In the ≥ 5 cm group, upper location and fibrosis during ESD were more common, with a lower rate of 0-IIc type. Both en bloc resection rate and R0 resection rate were comparable, but there was a difference in curative resection rate (65.6% in the ≥ 5 cm group and 91.5% in the < 5 cm group). The frequency of adverse events (post-ESD bleeding, perforation, or stenosis) was almost similar, but delayed perforation was significantly more common (1.6% in the ≥ 5 cm group vs. 0.1% in the < 5 cm group).

About two-thirds of curative resections were obtained with ESD for early gastric lesions larger than 5 cm, but delayed complications should be noted (Number: UMIN000047725).