Prevalence, natural progression, and clinical practices of upper gastrointestinal subepithelial lesions in Korea: a multicenter study

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.

A 65-Year-Old Man Presenting to the Emergency Department with Gastric Hemorrhage Caused by a Glomus Tumor

BACKGROUND Glomus tumor is a benign but rapidly growing mesenchymal tumor that is a rare in the gastrointestinal tract, can be locally invasive due to its rapid growth, and can result in perforation of a viscus. We report a 65-year-old man presenting as an emergency with gastric hemorrhage and gastric glomus tumor. CASE REPORT A 65-year-old man came to our hospital for a life-threatening upper digestive hemorrhage. The preoperative examinations (digestive endoscopy without sampling of biopsy fragments and contrast-enhanced computer tomography) led to the presumptive diagnosis of gastrointestinal stromal tumor. Wedge resection of the gastric wall was performed. The histopathological examinations revealed a proliferation of round-oval cells of medium size with a solid disposition and in nests. This proliferation dissected the muscular tunic and caused ulceration of the gastric mucosa. Immunohistochemical tests confirmed the diagnosis of glomus tumor and excluded other diagnoses (neuroendocrine tumor or gastrointestinal stromal tumor). The postoperative evolution was favorable, and at the time of discharge, the biochemical test values normalized. CONCLUSIONS Pathologists are faced with a challenging task due to the deceptive appearance that can be presented by such a rare tumor. Histopathological and immunohistochemical examinations are essential in achieving a precise diagnosis and assessing the biological potential of the glomus tumor. Even if it is a benign tumor, the clinical picture it causes can still be a major risk to the patient's life. Consequently, ensuring effective case management becomes crucial, as it requires a thorough comprehension of all conditions encompassed in the differential diagnosis.