• Field cancerization
• Gastric cancer
• Immune
• Sequencing
• Transcriptome
• Whole exome

• Endoscopic submucosal dissection
• Endoscopy
• Gastric cancer
• Prognostic factors

• Cancer screening
• Endoscopic curability C2
• Endoscopic submucosal dissection
• Gastric cancers missed
• Metachronous gastric cancer

• Humans
• Follow-Up Studies
• Stomach Neoplasms/diagnosis
• Stomach Neoplasms/surgery
• Stomach Neoplasms/pathology
• Endoscopic Mucosal Resection
• Retrospective Studies
• Gastric Mucosa/surgery
• Gastric Mucosa/pathology
• Treatment Outcome

The most important consideration in determining treatment strategies for undifferentiated early gastric cancer (UEGC) is the risk of lymph node metastasis (LNM). Therefore, identifying a potential biomarker that predicts LNM is quite useful in determining treatment.

To develop a machine learning (ML)-based integral procedure to construct the LNM gray-level co-occurrence matrix (GLCM) prediction model.

We retrospectively selected 526 cases of UEGC confirmed through pathological examination after radical gastrectomy without endoscopic treatment in four tertiary hospitals between January 2015 to December 2021. We extracted GLCM-based features from grayscale images and applied ML to the classification of candidate predictive variables. The robustness and clinical utility of each model were evaluated based on the following factors: Receiver operating characteristic curve (ROC), decision curve analysis, and clinical impact curve.

GLCM-based feature extraction significantly correlated with LNM. The top 7 GLCM-based factors included inertia value 0° (IV_0), inertia value 45° (IV_45), inverse gap 0° (IG_0), inverse gap 45° (IG_45), inverse gap full angle (IG_all), Haralick 30° (Haralick_30), Haralick full angle (Haralick_all), and Entropy. The areas under the ROC curve (AUCs) of the random forest classifier (RFC) model, support vector machine, eXtreme gradient boosting, artificial neural network, and decision tree ranged from 0.805 [95% confidence interval (CI): 0.258-1.352] to 0.925 (95%CI: 0.378-1.472) in the training set and from 0.794 (95%CI: 0.237-1.351) to 0.912 (95%CI: 0.355-1.469) in the testing set, respectively. The RFC (training set: AUC: 0.925, 95%CI: 0.378-1.472; testing set: AUC: 0.912, 95%CI: 0.355-1.469) model that incorporates Entropy, Haralick_all, Haralick_30, IG_all, IG_45, IG_0, and IV_45 had the highest predictive accuracy.

The evaluation results indicate that the method of selecting radiological and textural features becomes more effective in the LNM discrimination against UEGC patients. Additionally, the ML-based prediction model developed using the RFC can be used to derive treatment options and identify LNM, which can hence improve clinical outcomes.

• Undifferentiated early gastric cancer
• Machine learning
• Lymph node metastasis
• Gray-level co-occurrence matrix
• Feature selection
• Prediction

• Gastrectomy
• Humans
• Lymph Nodes/pathology
• Lymphatic Metastasis/pathology
• Machine Learning
• Retrospective Studies
• Stomach Neoplasms/pathology

• CiteSpace
• Web of Science
• bibliometric analysis
• data visualization
• endoscopic submucosal dissection

• aspirin
• endoscopic mucosal resection
• endoscopic submucosal dissection
• esophagus
• hemorrhage

• Onodera's prognostic nutritional index
• elderly
• endoscopic submucosal dissection
• gastric cancer
• surgery

Total gastrectomy (TG) with lymph node (LN) dissection is recommended for early gastric cancer (EGC) but is not indicated for endoscopic resection (ER). We aimed to identify patients who could avoid TG by establishing a scoring system for predicting lymph node metastasis (LNM) in proximal EGCs.

Between January 2003 and December 2017, a total of 1,025 proximal EGC patients who underwent TG with LN dissection were enrolled. Patients who met the absolute ER criteria based on pathological examination were excluded. The pathological risk factors for LNM were determined using univariate and multivariate logistic regression analyses. A scoring system for predicting LNM was developed and applied to the validation group.

Of the 1,025 cases, 100 (9.8%) showed positive LNM. Multivariate analysis confirmed the following independent risk factors for LNM: tumor size >2 cm, submucosal invasion, lymphovascular invasion (LVI), and perineural invasion (PNI). A scoring system was created using the four aforementioned variables, and the areas under the receiver operating characteristic curves in both the training (0.85) and validation (0.84) groups indicated excellent discrimination. The probability of LNM in mucosal cancers without LVI or PNI, regardless of size, was <2.9%.

Our scoring system involving four variables can predict the probability of LNM in proximal EGC and might be helpful in determining additional treatment plans after ER, functioning as a good indicator of the adequacy of treatments other than TG in high surgical risk patients.

The landscape of gastrointestinal endoscopy continues to evolve as new technologies and techniques become available. The advent of image-enhanced and magnifying endoscopies has highlighted the step toward perfecting endoscopic screening and diagnosis of gastric lesions. Simultaneously, with the development of convolutional neural network, artificial intelligence (AI) has made unprecedented breakthroughs in medical imaging, including the ongoing trials of computer-aided detection of colorectal polyps and gastrointestinal bleeding. In the past demi-decade, applications of AI systems in gastric cancer have also emerged. With AI’s efficient computational power and learning capacities, endoscopists can improve their diagnostic accuracies and avoid the missing or mischaracterization of gastric neoplastic changes. So far, several AI systems that incorporated both traditional and novel endoscopy technologies have been developed for various purposes, with most systems achieving an accuracy of more than 80%. However, their feasibility, effectiveness, and safety in clinical practice remain to be seen as there have been no clinical trials yet. Nonetheless, AI-assisted endoscopies shed light on more accurate and sensitive ways for early detection, treatment guidance and prognosis prediction of gastric lesions. This review summarizes the current status of various AI applications in gastric cancer and pinpoints directions for future research and clinical practice implementation from a clinical perspective.

• Artificial intelligence
• Diagnostic
• Therapeutic
• Endoscopy
• Gastric cancer
• Gastritis

• Artificial Intelligence
• Early Detection of Cancer
• Endoscopy, Gastrointestinal
• Humans
• Neural Networks, Computer
• Stomach Neoplasms/diagnostic imaging

• Endoscopic submucosal dissection
• Endoscopy
• Hemostasis
• Stomach neoplasms
• endoscopic
• gastrointestinal adverse effects

The number of elderly patients with early gastric cancer (EGC) who meet the indications for endoscopic submucosal dissection (ESD) is increasing. Since elderly patients have more comorbidities, and lower life expectancy than younger patients, special considerations to establish treatment strategies according to prognosis is needed. We investigate overall survival and risk factors related to survival after ESD in these patients. During the follow-up, the 3-, 5-, and 10-year overall survival was 91.2%, 83.5%, and 54.5%, respectively. Smoking, history of cancer of other organs, neutrophil to lymphocyte ratio > 1.6, Charlson comorbidity index ≥ 3, and presence of lymphovascular invasion were independent five risk factors for poor overall survival. The long-term outcome of ESD was poorer in elderly patients with risk factors than in those without. These prognostic factors can also be useful in deciding whether to recommend additive surgery and a close follow-up after non-curative endoscopic treatment in the elderly patients.

Background and Aims: The number of elderly patients with early gastric cancer (EGC) who meet the indications for endoscopic submucosal dissection (ESD) is increasing. We aimed to evaluate the clinical outcomes and prognostic factors of overall survival (OS) in elderly patients undergoing ESD for EGC. Methods: Between January 2006 and December 2018, 439 patients aged ≥75 years who underwent ESD for EGC were analyzed. The clinical outcomes and prognosis were evaluated, and independent risk factors for OS were identified. Results: The mean patient (302 men, 137 women) age was 78.3 (range 75–92) years. En bloc, R0, and curative resections were achieved in 96.8%, 90.7%, and 75.6%, respectively, without severe adverse events. During the follow-up (median 54.2 (range 4.0–159.6) months), 86 patients died (three of gastric cancer). The 3-, 5-, and 10-year OS was 91.2%, 83.5%, and 54.5%, respectively, and the 3-, 5-, and 10-year cancer related survival rate were 99.7%, 99.1% and 97.5%, respectively. In multivariate analysis, smoking, history of cancer of other organs, NLR > 1.6, Charlson comorbidity index ≥ 3, and presence of lymphovascular invasion (hazard ratio = 3.96, 1.78, 1.83, 1.83, and 2.63, respectively, all p < 0.05) were independent five risk factors for poor OS. The high-risk group (≥3 risk factors) showed a significantly lower OS than the low-risk group (<2 risk factors) (p < 0.001). Conclusions: The five factors could be useful in predicting the long-term prognosis of elderly ESD patients or deciding the therapeutic approaches in case of non-curative resection.

• early gastric cancer
• elderly
• endoscopic submucosal dissection
• prognostic factor

• gastroscopy
• lymph nodes
• neoplasm invasiveness
• stomach neoplasms

• Adult
• Aged
• China/epidemiology
• Early Detection of Cancer/methods
• Female
• Gastrectomy/methods
• Gastric Mucosa/pathology
• Humans
• Lymph Nodes/pathology
• Lymphatic Metastasis
• Male
• Middle Aged
• Multivariate Analysis
• Neoplasm Invasiveness/pathology
• Odds Ratio
• Retrospective Studies
• Risk Factors
• Stomach Neoplasms/epidemiology
• Stomach Neoplasms/metabolism
• Stomach Neoplasms/pathology

• 5-aminolevulinic acid
• Photodynamic diagnosis
• gastric adenoma
• gastric cancer

• Artificial intelligence
• Convolutional neural networks
• Early gastric cancer
• Endoscopy
• Invasion depth

• Early gastric cancer
• gastric cancer
• lymph node metastasis

In early gastric cancer (EGC), tumor invasion depth is an important factor for determining the treatment method. However, as endoscopic ultrasonography has limitations when measuring the exact depth in a clinical setting as endoscopists often depend on gross findings and personal experience. The present study aimed to develop a model optimized for EGC detection and depth prediction, and we investigated factors affecting artificial intelligence (AI) diagnosis. We employed a visual geometry group(VGG)-16 model for the classification of endoscopic images as EGC (T1a or T1b) or non-EGC. To induce the model to activate EGC regions during training, we proposed a novel loss function that simultaneously measured classification and localization errors. We experimented with 11,539 endoscopic images (896 T1a-EGC, 809 T1b-EGC, and 9834 non-EGC). The areas under the curves of receiver operating characteristic curves for EGC detection and depth prediction were 0.981 and 0.851, respectively. Among the factors affecting AI prediction of tumor depth, only histologic differentiation was significantly associated, where undifferentiated-type histology exhibited a lower AI accuracy. Thus, the lesion-based model is an appropriate training method for AI in EGC. However, further improvements and validation are required, especially for undifferentiated-type histology.

• artificial intelligence
• convolutional neural networks
• early gastric cancer
• endoscopy

• Endoscopic Submucosal Dissection
• Lymphovascular Invasion
• Non–Gastroesophageal Junction Early Gastric Cancer
• Submucosal Invasion

• Argon plasma coagulation
• Endoscopic resection
• Gastrectomy
• Neoplasms
• Stomach

• American Society of Anesthesiologists Physical Status
• Early gastric cancer
• Endoscopic submucosal dissection
• Long-term outcome
• Propensity score analysis

A 78-year-old man underwent endoscopic submucosal dissection (ESD) of early gastric cancer (EGC) (type 0-IIa) in the anterior wall of the antrum. En bloc resection was achieved. The histopathological examination revealed very well-differentiated tubular adenocarcinoma (tub1) of 30 × 22 mm in size, confined to the mucosa. No lymphovascular invasion or ulceration was observed, and there was no undifferentiated-type component and the margins were tumor-free. Therefore, this lesion fulfilled the eCuraA criteria. Two years after ESD, esophagogastroduodenoscopy revealed an irregular, slightly-depressed lesion within the post-ESD scar. Tubular adenocarcinoma was suspected based on histopathological examination of a biopsy specimen. The tumor was resected by ESD. A histopathological examination revealed well-differentiated tubular adenocarcinoma (tub1) of 6 × 4 mm in size, confined to the mucosa. No lymphovascular invasion was detected and the margins were tumor-free. These findings indicated a curative resection. Recurrence following a curative ESD of an intramucosal differentiated-type EGC which fulfilled the eCuraA criteria is rare. Careful endoscopic observation using magnifying narrow band imaging (NBI) is needed after ESD, even when curative resection is achieved.

• Early gastric cancer
• Endoscopic submucosal dissection
• eCuraA

• Early gastric cancer
• Endoscopic mucosal resection
• Undifferentiated

To investigate the feasibility and safety of secondary endoscopic submucosal dissection (ESD) for residual or locally recurrent gastric tumors.

Between 2010 and 2017, 1623 consecutive patients underwent ESD for gastric neoplasms at a single tertiary referral center. Among these, 28 patients underwent secondary ESD for a residual or locally recurrent tumor. Our analysis compared clinicopathologic factors between primary ESD and secondary ESD groups.

The en bloc resection and curative rate of resection of secondary ESD were 92.9% and 89.3%, respectively. The average procedure time of secondary ESD was significantly longer than primary ESD (78.2 min vs 55.1 min, P = 0.004), and the adverse events rate was not significantly different but trended slightly higher in the secondary ESD group compared to the primary ESD group (10.7% vs 3.8%, P = 0.095). Patients who received secondary ESD had favorable outcomes without severe adverse events. During a mean follow-up period, no local recurrence occurred in patients who received secondary ESD.

Secondary ESD of residual or locally recurrent gastric tumors appears to be a feasible and curative treatment though it requires greater technical efficiency and longer procedure time.

• Secondary endoscopic submucosal dissection
• Endoscopic submucosal dissection
• Gastric neoplasms
• Residual tumors
• Recurrent tumors

• Aged
• Endoscopic Mucosal Resection/adverse effects
• Endoscopic Mucosal Resection/methods
• Feasibility Studies
• Female
• Follow-Up Studies
• Gastric Mucosa/pathology
• Gastric Mucosa/surgery
• Gastroscopy/adverse effects
• Gastroscopy/methods
• Humans
• Male
• Middle Aged
• Neoplasm Recurrence, Local/epidemiology
• Neoplasm Recurrence, Local/surgery
• Neoplasm, Residual
• Reoperation/adverse effects
• Reoperation/methods
• Retrospective Studies
• Stomach Neoplasms/epidemiology
• Stomach Neoplasms/pathology
• Stomach Neoplasms/surgery
• Treatment Outcome

• obesity
• sleeve gastrectomy
• quality of life
• bariatric surgery
• obesidade
• gastrectomia vertical
• qualidade de vida
• cirurgia bariátrica

• Feasibility Studies
• Gastrectomy/methods
• Gastrostomy
• Humans
• Laparoscopy
• Obesity, Morbid/surgery
• Surgical Staplers

• Curative resection
• En bloc resection
• Perforation
• R0 resection

• Endoscopic Mucosal Resection/adverse effects
• Esophageal Mucosa/pathology
• Esophageal Mucosa/surgery
• Gastric Mucosa/pathology
• Gastric Mucosa/surgery
• Gastrointestinal Neoplasms/pathology
• Gastrointestinal Neoplasms/surgery
• Humans
• Intestinal Mucosa/pathology
• Intestinal Mucosa/surgery
• Neoplasm Recurrence, Local/epidemiology
• Neoplasm Recurrence, Local/prevention & control
• Operative Time
• Postoperative Complications/epidemiology
• Postoperative Complications/etiology
• Treatment Outcome

• Cancer staging
• Early detection of cancer
• Endoscopic submucosal dissection
• Healthcare costs
• Stomach neoplasms

To investigate the relationship between histological mixed-type of early gastric cancer (EGC) in the mucosa and submucosa and lymph node metastasis (LNM).

This study included 298 patients who underwent gastrectomy for EGC between 2005 and 2012. Enrolled lesions were divided into groups of pure differentiated (pure D), pure undifferentiated (pure U), and mixed-type according to the proportion of the differentiated and undifferentiated components observed under a microscope. We reviewed the clinicopathological features, including age, sex, location, size, gross type, lymphovascular invasion, ulceration, and LNM, among the three groups. Furthermore, we evaluated the predictors of LNM in the mucosa-confined EGC.

Of the 298 patients, 165 (55.4%) had mucosa-confined EGC and 133 (44.6%) had submucosa-invasive EGC. Only 13 (7.9%) cases of mucosa-confined EGC and 30 (22.6%) cases of submucosa-invasive EGC were observed to have LNM. The submucosal invasion (OR = 4.58, 95%CI: 1.23-16.97, P = 0.023), pure U type (OR = 4.97, 95%CI: 1.21-20.39, P = 0.026), and mixed-type (OR = 5.84, 95%CI: 1.05-32.61, P = 0.044) were independent risk factors for LNM in EGC. The rate of LNM in mucosa-confined EGC was higher in the mixed-type group (P = 0.012) and pure U group (P = 0.010) than in the pure D group, but no significant difference was found between the mixed-type group and pure U group (P = 0.739). Similarly, the rate of LNM in the submucosa-invasive EGC was higher in the mixed-type (P = 0.012) and pure U group (P = 0.009) than in the pure D group but was not significantly different between the mixed-type and pure U group (P = 0.375). Multivariate logistic analysis showed that only female sex (OR = 5.83, 95%CI: 1.64-20.70, P = 0.028) and presence of lymphovascular invasion (OR = 13.18, 95%CI: 1.39-125.30, P = 0.020) were independent risk factors for LNM in mucosa-confined EGC, while histological type was not an independent risk factor for LNM in mucosa-confined EGC (P = 0.106).

For mucosal EGC, histological mixed-type is not an independent risk factor for LNM and could be managed in the same way as the undifferentiated type.

• Early gastric carcinoma
• Mixed-type
• Lymph node metastasis
• Mucosa
• Lymphovascular invasion

• Adolescent
• Adult
• Aged
• Aged, 80 and over
• Carcinoma/secondary
• Carcinoma/surgery
• Cell Differentiation
• Chi-Square Distribution
• Female
• Gastrectomy
• Gastric Mucosa/pathology
• Gastric Mucosa/surgery
• Humans
• Logistic Models
• Lymphatic Metastasis
• Male
• Middle Aged
• Multivariate Analysis
• Neoplasm Invasiveness
• Neoplasm Staging
• Neoplasms, Complex and Mixed/secondary
• Neoplasms, Complex and Mixed/surgery
• Odds Ratio
• Retrospective Studies
• Risk Factors
• Stomach Neoplasms/pathology
• Stomach Neoplasms/surgery
• Young Adult

This review article summarizes knowledge about metachronous gastric cancer (MGC) occurring after curative endoscopic resection (ER) of early gastric cancer (EGC), treatment outcomes of patients who developed MGC, and efficacy of Helicobacter pylori eradication to prevent MGC. The incidence of MGC following curative ER increases over time and is higher than in patients undergoing gastrectomy. Increasing age and multifocal EGC are independent risk factors for developing MGC. An MGC following curative ER is usually a small (<20 mm) and differentiated intramucosal cancer. Most MGC lesions are found at an early stage on semiannual or annual surveillance endoscopy and are successfully treated by further ER, with excellent long-term outcomes. Eradication of H. pylori may reduce the risk of MGC following ER of EGC, but further prospective studies with long-term outcomes are required. Surveillance endoscopy following gastric ER should be continued indefinitely, due to the risk of MGC even after successful H. pylori eradication. Risk stratification and tailored endoscopic surveillance schedules need to be developed.

• Endoscopic mucosal resection
• Endoscopic resection
• Surveillance endoscopy
• Helicobacter pylori
• Metachronous gastric cancer

• 5-year disease-specific survival rate
• 5-year survival rate
• Early gastric cancer
• Nationwide registry

To investigate predictive markers for metachronous and synchronous gastric cancer (GC), which can develop after endoscopic submucosal dissection (ESD).

A total of 352 patients underwent ESD for early GC at NTT West Osaka Hospital between June 2006 and February 2016. Exclusion criteria were as follows: Remnant stomach, unknown Helicobacter pylori status, and endoscopic observation of the whole stomach outside our hospital. We analyzed data from 192 patients comprising 109 patients with solitary GC (Group A) and 83 with metachronous and synchronous GC (Group B). We retrospectively investigated the clinicopathological and endoscopic characteristics, and endoscopic risk score as predictive markers for GC.

The median age of Group B [72 years (interquartile range 63-78)] was significantly higher than that of Group A [66 years (interquartile range 61-74), respectively, P = 0.0009]. The prevalence of intestinal metaplasia in Group B tended to be higher than that in Group A (57.8% vs 45.0%, P = 0.08). The prevalence of gastric xanthoma (GX) in Group B was significantly higher than that in Group A (54.2% vs 32.1%, P = 0.003). The atrophy score in Group B was significantly higher than that in Group A (P = 0.005). Multivariate analysis revealed that higher age and the presence of GX were independently related to metachronous and synchronous GC [OR = 1.04 (1.01-1.08), P = 0.02; and OR = 2.11 (1.14-3.99), P = 0.02, respectively].

The presence of GX is a useful predictive marker for metachronous and synchronous GC.

• Gastric cancer
• Metachronous neoplasms
• Synchronous neoplasms
• Xanthoma
• Biomarker

• Endoscopy
• Outcome assess
• Prospective studies
• Stomach neoplasms
• gastrointestinal

• early gastric cancer
• endoscopic submucosal dissection
• gastrectomy
• treatment outcome

• Adenocarcinoma/epidemiology
• Adenocarcinoma/surgery
• Aged
• Disease-Free Survival
• Endoscopic Mucosal Resection/adverse effects
• Female
• Follow-Up Studies
• Gastrectomy
• Humans
• Incidence
• Kaplan-Meier Estimate
• Lymph Node Excision
• Male
• Middle Aged
• Neoplasm Recurrence, Local/epidemiology
• Neoplasm Recurrence, Local/pathology
• Neoplasms, Second Primary/epidemiology
• Retrospective Studies
• Stomach Neoplasms/epidemiology
• Stomach Neoplasms/pathology
• Stomach Neoplasms/surgery
• Time Factors
• Treatment Outcome