Artificial Intelligence-Based Diagnosis of Gastric Mesenchymal Tumors Using Digital Endosonography Image Analysis.

Background/Objectives: Artificial intelligence (AI)-assisted endoscopic ultrasonography (EUS) diagnostic tools have shown excellent performance in diagnosing gastric mesenchymal tumors. This study aimed to assess whether incorporating clinical and endoscopic factors into AI-assisted EUS classification models based on digital image analysis could improve the diagnostic performance of AI-assisted EUS diagnostic tools. Methods: We retrospectively analyzed the data of 464 patients who underwent both EUS and surgical resection of gastric mesenchymal tumors, including 294 gastrointestinal stromal tumors (GISTs), 52 leiomyomas, and 41 schwannomas. AI-assisted classification models for GISTs and non-GIST tumors were developed utilizing clinical and endoscopic factors and digital EUS image analysis. Results: Regarding the baseline EUS classification models, the area under the receiver operating characteristic (AUC) values of the logistic regression, decision tree, random forest, K-nearest neighbor (KNN), and support vector machine (SVM) models were 0.805, 0.673, 0.781, 0.740, and 0.791, respectively. Using the new classification models incorporating clinical and endoscopic factors into the baseline classification models, the AUC values of the logistic regression, decision tree, random forest, KNN, and SVM models increased to 0.853, 0.715, 0.896, 0.825, and 0.794, respectively. In particular, the random forest and KNN models exhibited significant improvement in performance in Delong's test (both p < 0.001). Conclusion: The diagnostic performance of the AI-assisted EUS classification models improved when clinical and endoscopic factors were incorporated. Our results provided direction for developing new AI-assisted EUS models for gastric mesenchymal tumors.

Effective Endoscopic Submucosal Dissection of a Huge Esophageal Liposarcoma: A Case Report.

This case report presents the successful endoscopic submucosal dissection (ESD) of a well-differentiated esophageal liposarcoma in a 51-year-old male with persistent dysphagia. The cause was initially diagnosed as a 10 cm pedunculated lesion extending from the upper esophageal sphincter to the mid-esophagus. An ESD was chosen over traditional surgery because it is less invasive. The procedure involved a precise submucosal injection and excision with special techniques to manage bleeding from a central vessel. Despite the extraction challenges owing to the size of the lesion, it was successfully removed orally. A histopathological examination of the 8.3×4.2×2.3 cm specimen revealed the characteristic features of a well-differentiated liposarcoma, including MDM2 and CDK4 positivity. The follow-up revealed no recurrence, and active surveillance has been performed since. This report highlights the versatility of ESD in treating significant esophageal tumors and provides evidence for its efficacy as a minimally invasive alternative.

A rare case of esophageal mucoepidermoid carcinoma successfully treated via endoscopic submucosal dissection.

Esophageal mucoepidermoid carcinoma (EMEC) is a special subtype of esophageal malignancy, accounting for less than 1% of all cases of primary esophageal carcinoma. Pathologically, it consists of a mixture of adenocarcinoma and squamous cell carcinoma with mucin-secreting cells. Special staining for mucicarmine helps to diagnose EMEC. We present a rare case of EMEC successfully treated via endoscopic submucosal dissection (ESD). A 63-year-old man was referred to our tertiary hospital. On esophagogastroduodenoscopy, a 6-mm-sized subtle reddish depressed lesion was identified in the mid-esophagus. Diagnostic ESD was performed with a high suspicion of carcinoma. Histopathologic findings were consistent with EMEC which was confined to the lamina propria without lymphatic invasion. We plan to do a careful follow-up without administering adjuvant chemotherapy or radiotherapy. Due to the small volume of the lesion, establishing a diagnosis was difficult through forceps biopsy alone. However, by using ESD, we could confirm and successfully treat a rare case of early-stage EMEC.

A Case of Esophageal MALT Lymphoma Mimicking a Subepithelial Tumor.

Mucosa-associated lymphoid tissue (MALT) lymphoma, also known as extranodal marginal zone lymphoma, is a low-grade B-cell lymphoma that can develop in the mucosal layer of various organs, including the gastrointestinal tract, salivary glands, lungs, and skin. The most common site is the gastrointestinal tract, particularly the stomach. On the other hand, primary esophageal lymphomas are extremely rare. MALT lymphomas can undergo histological transformation into more aggressive B-cell lymphomas, such as diffuse large B-cell lymphoma, resulting in a poor prognosis. This paper reports a rare case of primary esophageal MALT lymphoma mimicking a subepithelial tumor located in the lower esophagus that was treated successfully with radiotherapy. MALT lymphoma should be included in a differential diagnosis when subepithelial tumors are found in the esophagus, particularly if endoscopic ultrasonography reveals the tumor to be located in the deep mucosal and submucosal layers. Following the precise diagnosis, accurate staging and appropriate treatment are crucial. Regular follow-up is necessary to assess the possibility of recurrence or transformation to high-grade lymphoma.

A Gastric Magnetic Foreign Body Incidentally Detected Several Years after Ingestion.

Foreign body ingestion is commonly seen in children. However, occasionally it may also be seen among adults and is often associated with intellectual disability, psychiatric disorders, and alcoholism. Ingestion of a magnetic foreign body may cause complications such as gastrointestinal tract perforation, wherein emergency endoscopic removal of the foreign body is generally required. Here, we report a rare case of a 59-year-old male with an intellectual disability and psychiatric disorder in whom metallic objects in the stomach cavity were accidentally discovered during abdominal CT. Esophagogastroduodenoscopy revealed several metallic objects attached to two magnets, which had been ingested several years before and had remained in the stomach cavity. The magnets and metallic objects were safely removed endoscopically using rat-tooth forceps without complications.

Long-term outcomes of endoscopic resection for duodenal neuroendocrine tumors.

Duodenal neuroendocrine tumors (d-NETs) ≤ 10 mm in size, confined to the submucosal layer, without lymph node or distant metastasis, can be treated safely and effectively by endoscopic management. However, most results are based on limited data and short follow-up outcomes. Herein, we aimed to evaluate the short-term and long-term outcomes of endoscopic resection for d-NETs. We retrospectively analyzed 63 patients with 68 d-NETs who had undergone endoscopic resection at two hospitals between January 2009 and December 2021. En-bloc resection, endoscopically complete resection, and histopathologically complete resection rates were evaluated as short-term outcomes. Furthermore, long-term outcomes were analyzed in 46 patients with 50 d-NETs with a follow-up period of > 1 year. The overall en-bloc, endoscopically complete, and histopathologically complete resection rates were 92.6% (63/68), 100% (68/68), and 69.1% (47/68), respectively. Tumor size (> 5 mm) was the only predictive factor for histopathologically incomplete resection (p = 0.015). The procedure-related bleeding and perforation rates were 0% and 5.9%, respectively. No recurrences were observed in patients with histopathologically complete resection and those with histopathologically incomplete resection at a median follow-up period of 48 months (range 12-132 months). Endoscopic resection for d-NETs ≤ 10 mm in size, limited to the submucosal layer, and without lymph node or distant metastasis provides favorable long-term outcomes when endoscopically complete resection is achieved.

Feasibility of endoscopic resection and impact of endoscopic ultrasound-based surveillance on colorectal subepithelial tumors.

BACKGROUND: Owing to the rising number of screening endoscopies and instrumental advances in endoscopic ultrasound (EUS), colorectal subepithelial tumors (SETs) are being increasingly detected. We aimed to determine the feasibility of endoscopic resection (ER) and the impact of EUS-based surveillance on colorectal SETs. METHODS: The medical records of 984 patients with incidentally detected colorectal SETs between 2010 and 2019 were retrospectively reviewed. Overall, 577 colorectal SETs underwent ER, and 71 colorectal SETs underwent serial colonoscopy for > 12 months. RESULTS: The mean tumor size (± standard deviation) of 577 colorectal SETs for which ER was performed was 7.0 ± 5.7 (median, 55; range, 1-50) mm; 475 tumors were located in the rectum and 102, in the colon. En bloc resection was achieved in 560/577 treated lesions (97.1%), and complete resection was achieved in 516/577 (89.4%). ER-related adverse events occurred in 15/577 (2.6%) patients. SETs originating from the muscularis propria showed a higher risk of ER-related adverse events and perforation than SETs arising from the mucosal or submucosal layer (odds ratio [OR] 19.786, 95% confidence interval [CI] 4.556-85.919; P = 0.002 and OR 141.250, 95% CI 11.596-1720.492; P = 0.046, respectively). Seventy-one patients were followed up after EUS without any treatment for > 12 months, during which three showed progression; eight, regression; and sixty, no changes. CONCLUSIONS: ER for colorectal SETs showed excellent efficacy and safety. Additionally, colorectal SETs without high-risk features in surveillance with colonoscopy showed an excellent prognosis.

Endoscopic Resection for Gastric Adenocarcinoma of the Fundic Gland Type: A Case Series.

The fundic gland type (GA-FG) of gastric adenocarcinoma is a rare variant of gastric cancer recently included in the 5th edition of the World Health Organization's classification of digestive system tumors. Five patients with GA-FG underwent an endoscopic resection at our institution. None of the patients had a Helicobacter pylori infection. Four lesions were located in the upper third of the stomach, and one was in the lower third. Three lesions had a IIa shape, while two resembled a subepithelial tumor. An endoscopic submucosal dissection was performed in four patients and endoscopic mucosal resection in one. Tumor cells were composed of well-differentiated columnar cells mimicking fundic gland cells, and the median tumor size was 10 mm. Three lesions exhibited submucosal invasion. No lymphatic or venous invasion was observed. Tumor cells were positive for MUC6 in all five cases; one case was focally positive for MUC5AC. No recurrence was observed during a median follow-up period of 13 months. An endoscopic resection can be a safe treatment modality for GA-FG, considering its small size and low risk of recurrence or metastasis.

Incidence and adverse clinical events of primary sclerosing cholangitis with ulcerative colitis.

PURPOSE: The aim of this study was to conduct a nationwide population-based study to estimate the incidence of primary sclerosing cholangitis in patients with ulcerative colitis (UC-PSC) and investigate healthcare use, medication use, surgery, cancer, and death as adverse clinical events of UC-PSC. METHODS: We identified incident cases of UC with (UC-PSC) or without PSC (UC-alone) between 2008 and 2018 using health insurance claims data in Korea. Univariate (crude hazard ratio (HR)) and multivariate analyses were performed to compare the risk of adverse clinical events between groups. RESULTS: A total of 14,406 patients with UC using population-based claims data were detected in the cohort. Overall, 3.38% (487/14,406) of patients developed UC-PSC. During a mean follow-up duration of approximately 5.92 years, the incidence of PSC in patients with UC was 185 per 100,000 person-years. The UC-PSC group showed statistically more frequent healthcare use (hospitalization and emergency department visits: HRs, 5.986 and 9.302, respectively; P < .001), higher immunomodulator and biologic use (azathioprine, infliximab, and adalimumab: HRs, 2.061, 3.457, and 3.170, respectively; P < .001), and higher surgery rate (operation for intestinal obstruction, and colectomy: HRs, 9.728 and 2.940, respectively; P < .001) than did the UC-alone group. The UC-PSC group also showed significantly higher colorectal cancer and biliary tract cancer (HRs, 2.799 and 36.343, respectively; P < .001) and mortality (HR, 4.257) rates than did the UC-alone group. CONCLUSION: Patients with UC-PSC have higher risks of colorectal cancer, biliary tract cancer, and death than do patients with UC-alone. Although considered a rare disease, managing this complex and costly disease requires recognition of the impact of increased burden on healthcare services.

Magnifying Endoscopy with Narrow-Band Imaging for Duodenal Neuroendocrine Tumors.

Duodenal neuroendocrine tumors (NETs) are rare subepithelial tumors that arise from the neuroendocrine cells beneath the epithelial layer. However, an accurate histopathological diagnosis is difficult when tissue samples are obtained using conventional endoscopic forceps biopsy alone. This study aimed to evaluate the magnifying endoscopy with narrow-band imaging (ME-NBI) findings of duodenal NETs. We retrospectively analyzed a database of 22 duodenal NETs from 21 patients who underwent ME-NBI between January 2011 and June 2022. The ME-NBI, endosonographic, and histopathologic findings of duodenal NETs were analyzed. Nineteen lesions were located in the bulb, two were located in the superior duodenal angle, and one was located in the second portion of the duodenum. Eighteen lesions (82%) had IIa morphology, and nine (41%) had central depression on the surface. On endoscopic ultrasonography, almost all lesions (20/22, 91%) were located in the second and/or third layers, and the median tumor size was 6 mm. During ME-NBI, the microsurface pattern was regular in 18 lesions (82%) and absent in 4 (18%). The microvascular pattern was regular in 17 lesions (77%), irregular in 4 (18%), and absent in 1 (5%). Thickened subepithelial vessels were observed in 15 (68%) lesions. There was no difference in tumor size according to the presence or absence of thickened subepithelial vessels (6.1 ± 1.8 mm vs. 5.9 ± 3.8 mm, p = 0.860). In conclusion, the characteristic ME-NBI findings of duodenal NETs were regular microsurface and microvascular patterns and the presence of thickened subepithelial vessels. These ME-NBI features may be useful for differentiating duodenal NETs from other duodenal subepithelial lesions.

Incidence, Morbidity, and Mortality of Achalasia: A Nationwide, Population-Based Cohort Study in South Korea.

Background/Aims: Although an association between achalasia and esophageal cancer has been reported, whether achalasia confers a substantial increase in mortality is unknown. Moreover, the causes of death related to achalasia have not been investigated. We performed this nationwide, population-based cohort study on achalasia because no such study has been performed since the introduction of high-resolution manometry in 2008. Methods: This study was performed using data extracted from the Korean National Health Insurance Service database, covering a 9-year period from 2009 to 2017. Control participants without a diagnostic code for achalasia were randomly selected and matched by sex and birth year at a case-to-control ratio of 1:4. Data on the cause of death from Statistics Korea were also analyzed. Results: The overall incidence of achalasia was 0.68 per 100,000 person-years, and the prevalence was 6.46 per 100,000 population. Patients with achalasia (n=3,063) had significantly higher adjusted hazard ratio (aHR) for esophageal cancer (aHR, 3.40; 95% confidence interval [CI], 1.25 to 9.22; p=0.017), pneumonia (aHR, 2.30; 95% CI, 1.89 to 2.81; p<0.001), aspiration pneumonia (aHR, 3.92; 95% CI, 2.38 to 6.48; p<0.001), and mortality (aHR, 1.68; 95% CI, 1.44 to 1.94; p<0.001). Esophageal cancer carried the highest mortality risk (aHR, 8.82; 95% CI, 2.35 to 33.16; p=0.001), while pneumonia had the highest non-cancer mortality risk (aHR, 2.28; 95% CI, 1.31 to 3.96; p=0.004). Conclusions: In this nationwide study, achalasia was associated with increased risk of mortality. Esophageal cancer and pneumonia were the most common comorbidities and the major causes of death in patients with achalasia.

Exosomal MicroRNA Analyses in Esophageal Squamous Cell Carcinoma Cell Lines.

Exosomal miRNAs have been studied in various cancers as minimally invasive biomarkers. This study aimed to investigate the potential of exosomal microRNAs (miRNAs) as biomarkers for esophageal squamous cell carcinoma (ESCC). Exosomes were isolated from cultures of esophageal epithelial cell and ESCC cell lines using ExoDisc, and exosomal miRNAs were detected via miRNA sequencing. Of the differentially expressed 14 miRNAs, the top 2 up-regulated miRNAs (miR-205-5p and miR-429) and top 2 down-regulated miRNAs (miR-375-3p and miR-483-3p) were selected as ESCC target miRNAs. Four selected exosomal miRNAs were validated in the plasma of 20 healthy controls (HCs) and 40 ESCC patients via quantitative reverse transcription-polymerase chain reaction. The expression of plasma exosomal miR-205-5p and miR-429 significantly increased, while that of plasma exosomal miR-375-3p was significantly reduced in ESCC patients compared to that in HCs. At cut-off values of 5.04, 2.564, and 0.136, the sensitivity and specificity for the diagnosis of ESCC were 72.5% and 70.0% for miR-205-5p, 60.0% and 60.0% for miR-429, and 65.0% and 65.0% for miR-375-3p, respectively. Based on the exosomal miRNAs identified in ESCC cell lines, our study demonstrated that plasma exosomal miR-205-5p, miR-429, and miR-375-3p could serve as potential biomarkers for ESCC diagnosis.

MicroRNA Expression in Plasma of Esophageal Squamous Cell Carcinoma Patients.

BACKGROUND: Patients with esophageal squamous cell carcinoma (ESCC) have a poor prognosis and there are no effective clinical biomarkers. Recently, stable microRNAs detected in the blood have been suggested as potential biomarkers in various cancers. Therefore, we investigated whether plasma microRNAs could be feasible biomarkers for ESCC. METHODS: Peripheral blood samples were obtained from 16 healthy volunteers and 66 ESCC patients before treatment between May 2016 and April 2021. Plasma miR-18b, miR-21, miR-31, and miR-375 expression levels were measured using reverse transcription-quantitative polymerase chain reaction. RESULTS: Compared with those in healthy controls, the expression levels of plasma miR-21 were significantly higher (P = 0.022) and those of plasma miR-31 and miR-375 were significantly lower in ESCC patients (both P < 0.001). Plasma miR-18b expression levels increased in ESCC patients, but the difference was not significant (P = 0.164). The sensitivities and specificities of miR-21, miR-31, and miR-375 for differentiating ESCC patients from healthy controls were 87.5% and 61.9%, 87.5% and 98.4%, and 87.5% and 100%, respectively. There was no difference in expression levels of plasma miR-21, miR-31, and miR-375 according to clinicopathological characteristics of sex, age, tumor size and location, histologic grade, and tumor-node-metastasis stage. CONCLUSION: Our study demonstrated that plasma miR-21, miR-31, and miR-375 could be potential biomarkers for the diagnosis of ESCC. Particularly, plasma miR-31 and miR-375 showed high sensitivity and specificity for differentiating ESCC patients from healthy controls.

Diagnostic performance of endoscopic ultrasonography-guided fine-needle biopsy in upper gastrointestinal subepithelial tumors measuring 2-5 cm in size.

BACKGROUND: Subepithelial tumors (SETs) in the upper gastrointestinal (GI) tract are frequently discovered during upper endoscopy, and their management is determined based on size and histopathological diagnosis. We aimed to evaluate the diagnostic performance of endoscopic ultrasonography-guided fine-needle biopsy (EUS-FNB) in upper GI SETs of 2-5 cm in size. METHODS: We included 63 patients who underwent EUS-FNB for upper GI SETs of 2-5 cm in size between January 2013 and February 2020. The diagnostic yield of EUS-FNB, ability of EUS-FNB in discriminating malignant from non-malignant lesions, and histopathological concordance between EUS-FNB specimens and resected specimens were evaluated. RESULTS: Successful acquisition of macroscopic tissue cores was possible in all 63 cases, and the diagnostic yield of EUS-FNB was 92.1% (58/63). The sensitivity, specificity, and accuracy of EUS-FNB in discriminating malignant from non-malignant lesions were 100% (95% confidence interval [CI] 85.3-100%), 87.8% (95% CI 79.9-87.8%), and 92.1% (95% CI 81.8-92.1%), respectively. Of the 26 SETs that were endoscopically or surgically resected after EUS-FNB, the histopathological concordance rate between the EUS-FNB specimens and resected specimens was 100% (24/24), except in two cases of inadequate results with EUS-FNB specimens. CONCLUSION: EUS-FNB provides high diagnostic yield and high capability in discriminating malignant from non-malignant lesions in upper GI SETs of 2-5 cm in size.

Randomized Controlled Trial Comparing the Efficacy of Sustained-Release Formula of Mosapride-Plus-Esomeprazole Combination Therapy to Esomeprazole Monotherapy in Patients with Gastroesophageal Reflux Disease.

We aimed to evaluate whether adding a sustained-release (SR) formula of mosapride to proton-pump inhibitors (PPIs) would be more effective in controlling symptoms than PPI alone in patients with gastroesophageal reflux disease (GERD). Sixty patients with heartburn and/or regurgitation were randomly assigned to two groups: mosapride SR 15 mg combined with esomeprazole 20 mg once daily (ME group) and esomeprazole 20 mg once daily alone (E group). The primary endpoint was the complete-resolution rate of GERD symptoms after eight-week medication, and the secondary endpoints were the complete-resolution rate of GERD symptoms after four-week medication, symptom-improvement rates ≥ 50% after four- and eight-week medication, and change in reflux-disease-questionnaire (RDQ) and GERD-health-related quality-of-life (GERD-HRQL) scores from baseline at four- and eight-week medication. No significant differences in complete-symptom-resolution rates at eight weeks and four weeks or in the changes in RDQ and GERD-HRQL scores from baseline at four- and eight-week medication were observed between the ME and E groups. The symptom-improvement rate of ≥50% after four and eight weeks was comparable between both groups. Adding mosapride SR to esomeprazole in patients with GERD provides no additional benefits in controlling GERD symptoms.

Prediction model for curative endoscopic submucosal dissection of undifferentiated-type early gastric cancer.

BACKGROUND: Endoscopic submucosal dissection (ESD) is an effective treatment for early gastric cancer (EGC); however, its curative resection rate is low for undifferentiated-type EGC. We developed and externally validated a prediction model for curative ESD of undifferentiated-type EGC. METHODS: In this cross-sectional study, we included 448 patients who underwent ESD for undifferentiated-type EGC at 18 hospitals in Korea between 2005 and 2015 in the development cohort and 1342 patients who underwent surgery at two hospitals in the validation cohort. A prediction model was developed using the logistic regression model. RESULTS: Endoscopic tumor size 1-2 cm (odds ratio [OR], 2.40; 95% confidence interval [CI] 1.54-3.73), tumor size > 2 cm (OR, 14.00; 95% CI 6.81-28.77), and proximal tumor location from the lower to upper third of the stomach (OR, 1.45; 95% CI 1.03-2.04) were independent predictors of non-curative ESD. A six-score prediction model was developed by assigning points to endoscopic tumor size > 2 cm (five points), tumor size 1-2 cm (two points), upper third location (two points), and middle third location (one point). The rate of curative ESD ranged from 70.6% (score 0) to 11.6% (score 5) with an area under the receiver operating characteristic curve (AUC) of 0.720 (95% CI 0.673-0.766). The model also showed good performance in the validation cohort (AUC, 0.775; 95% CI 0.748-0.803). CONCLUSIONS: This six-score prediction model may help in predicting curative ESD and making informed decisions about the treatment selection between ESD and surgery for undifferentiated-type EGC.

Long-term outcomes of endoscopic resection followed by additional surgery after non-curative resection in undifferentiated-type early gastric cancer: a nationwide multi-center study.

BACKGROUND: Undifferentiated-type early gastric cancer (UD EGC) shows lower curative resection rates after endoscopic submucosal dissection (ESD). Additional surgery is recommended after non-curative resection. We evaluated the long-term outcomes of ESD followed by additional surgery after non-curative resection in UD EGC compared to those for surgery as initial treatment. METHODS: We reviewed 1139 UD EGC patients who underwent ESD at 18 hospitals and 1956 patients who underwent surgery at two hospitals between February 2005 and May 2015. We enrolled 636 patients with non-curative ESD and 1429 surgery subjects beyond the curative ESD criteria. Among them, 133 patients with additional surgery after ESD (ESD + OP group) and 252 patients without additional surgery (ESD-only group) were matched 1:1 using propensity scores to patients with surgery as initial treatment (surgery group). Overall survival (OS) and recurrence-free survival (RFS) were compared. RESULTS: Signet ring cell carcinoma and poorly differentiated adenocarcinoma (PDA) were observed in 939 and 1126 cases, respectively. OS was significantly longer in the surgery group than in the ESD + OP group, especially for PDA. However, RFS was shorter in the ESD-only group than those in the ESD + OP and surgery groups. RFS did not differ significantly between the ESD + OP and surgery groups. Compared to the surgery group, the ESD-only and ESD + OP groups had an overall hazard ratio for RFS of 3.58 (95% confidence interval 1.44-8.88) and 0.46 (0.10-2.20), respectively. CONCLUSIONS: ESD followed by additional surgery after non-curative resection showed comparable cancer-specific outcomes to initial surgery in UD EGC.

Association between mucin phenotype and lesion border detection using acetic acid-indigo carmine chromoendoscopy in early gastric cancers.

BACKGROUND: For successful treatment of early gastric cancers (EGCs), it is crucial to define the horizontal border of the lesion with high accuracy. Acetic acid-indigo carmine (AI) chromoendoscopy has been used to determine the horizontal border in EGCs, but this technique is less potent in certain situations. Mucin phenotype in gastric cancers refers to biological differences in precursor lesions and differences in histopathologic findings, and it might affect AI chromoendoscopy findings. We aimed to investigate the association between mucin phenotype and AI chromoendoscopy findings in EGCs. METHODS: We prospectively evaluated 126 lesions in 126 patients with endoscopically diagnosed EGCs. Conventional endoscopy and AI chromoendoscopy findings of these lesions before treatment were prospectively analyzed. The border distinction between the lesion and surrounding mucosa was classified as distinct or indistinct on conventional endoscopy and AI chromoendoscopy, respectively. Mucin phenotypes were classified as gastric, intestinal, gastrointestinal, or null type by immunohistochemistry. RESULTS: The lesion borders were distinct in 46.8% (59/126) of the lesions assessed using conventional endoscopy and in 73.0% (92/126) of those assessed with AI chromoendoscopy (p < 0.001). The border distinction rate of differentiated-type cancers on AI chromoendoscopy was significantly higher than that on conventional endoscopy (66/71 [93.0%] vs. 34/71 [47.9%], p < 0.001), but the border distinction rate of undifferentiated-type cancers on AI chromoendoscopy was not different from that on conventional endoscopy (26/55 [47.3%] vs. 25/55 [45.5%], p = 0.848). Compared with conventional endoscopy, AI chromoendoscopy identified borders in a significantly higher percentage of gastric, intestinal, and gastrointestinal mucin types; however, there was no difference in AI chromoendoscopy findings according to the mucin phenotype (p = 0.271). CONCLUSION: AI chromoendoscopy was effective in horizontal border delineation in differentiated-type EGCs, but not in undifferentiated-type EGCs. Mucin phenotype had no effect on border distinction using AI chromoendoscopy.