Convolutional neural networks (CNNs) have received increased attention in endoscopic images due to their outstanding advantages. Clinically, some gastric polyps are related to gastric cancer, and accurate identification and timely removal are critical. CNN-based semantic segmentation can delineate each polyp region precisely, which is beneficial to endoscopists in the diagnosis and treatment of gastric polyps. At present, just a few studies have used CNN to automatically diagnose gastric polyps, and studies on their semantic segmentation are lacking. Therefore, we contribute pioneering research on gastric polyp segmentation in endoscopic images based on CNN. Seven classical semantic segmentation models, including U-Net, UNet++, DeepLabv3, DeepLabv3+, Pyramid Attention Network (PAN), LinkNet, and Muti-scale Attention Net (MA-Net), with the encoders of ResNet50, MobineNetV2, or EfficientNet-B1, are constructed and compared based on the collected dataset. The integrated evaluation approach to ascertaining the optimal CNN model combining both subjective considerations and objective information is proposed since the selection from several CNN models is difficult in a complex problem with conflicting multiple criteria. UNet++ with the MobineNet v2 encoder obtains the best scores in the proposed integrated evaluation method and is selected to build the automated polyp-segmentation system. This study discovered that the semantic segmentation model has a high clinical value in the diagnosis of gastric polyps, and the integrated evaluation approach can provide an impartial and objective tool for the selection of numerous models. Our study can further advance the development of endoscopic gastrointestinal disease identification techniques, and the proposed evaluation technique has implications for mathematical model-based selection methods for clinical technologies.

Automatic and accurate segmentation and classification of esophageal lesions are two essential tasks to assist endoscopists in Upper Gastrointestinal Endoscopy. However, there is no intelligent system that can diagnose more lesion types, handle multiple tasks simultaneously, and be more accurate in clinical work. Therefore, we present an innovative Multi-Task deep learning architecture named Attention Gating Pyramid Vision Transformer (AGPVT), which provides a solution for the accurate classification and precise segmentation of lesion types and regions simultaneously. The proposed AGPVT combines the benefits of cutting-edge deep learning model designs with Multi-Task Learning (MTL) in order to advance the field. Furthermore, a patch-wise multi-head attention gating method alongside a hybrid design MTL decoder, is employed as the core driving architecture of the AGPVT. Comprehensive experiments are conducted on a multicenter dataset which contains esophageal cancer, Barrett's esophagus, esophageal protruded lesions, esophagitis, and normal esophagus. Experimental results show that the proposed AGPVT achieves a classification accuracy of 96.84%, an IoU score of 85.61%, and a Dice score of 90.75%, outperforming existing methods and demonstrating its effectiveness in this domain.

Background/Aims: The present study seeks to appraise the therapeutic outcomes of cystic lesion management and the diagnostic performance of endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) in characterizing pelvic space-occupying lesions. Materials and Methods: EUS-FNA was performed transrectally on 83 patients with pelvic space-occupying lesions identified using ultrasonography, computed tomography, or magnetic resonance imaging (MRI) from January 2016 to December 2024. Tissue was obtained for pathological analysis and smear cytology using a 19 G or 22 G puncture needle. Cytological samples are collected, and drainage is executed for pelvic cystic lesions. In the presence of an abscess, metronidazole solution was routinely provided for irrigation. Postoperatively, additional clinical monitoring was performed on patients to assess their prognosis, including the evaluation of clinical symptoms and laboratory indicators during follow-up. Results: After pathological and/or cytological evaluation of 83 patients, 67 instances of solid masses were identified, comprising 41 adenocarcinomas, 6 malignant mesenchymal tumors, 7 inflammatory masses, 3 lymphomas, 2 dermoid cysts, and 8 other cases. Sixteen instances of cystic masses were recorded, comprising 3 plasma cystadenomas, alongside 13 occurrences of perirectal abscesses, of which 11 patients with perirectal abscess were drained of pus and treated with metronidazole injection. The comparison of 19G and 22G puncture needles revealed no statistically significant variation in the percentage of punctures amenable to immunohistochemistry (P > .05). Thirteen patients with perirectal abscesses exhibited differing degrees of pain during EUS-FNA. Except for 1 patient who exhibited hematochezia attributable to a pelvic lesion in the prostate, none of the other patients encountered postoperative complications, including fever or hematochezia. Conclusion: The EUS-FNA is a direct, secure, and minimally invasive method with therapeutic promise for clarifying the characteristics of pelvic space-occupying lesions. Cite this article as: Fan X, Wang C, Wang W, Gao S. Diagnostic value of ultrasound guided fine-needle aspiration for pelvic space-occupying lesions via rectal endoscopic ultrasound. Turk J Gastroenterol. Published online January 26, 2026. doi:10.5152/tjg.2026.25487.