To retrospectively develop and validate an interpretable deep learning model and nomogram utilizing endoscopic ultrasound (EUS) images to predict pancreatic neuroendocrine tumors (PNETs). Following confirmation via pathological examination, a retrospective analysis was performed on a cohort of 266 patients, comprising 115 individuals diagnosed with PNETs and 151 with pancreatic cancer. These patients were randomly assigned to the training or test group in a 7:3 ratio. The least absolute shrinkage and selection operator algorithm was employed to reduce the dimensionality of deep learning (DL) features extracted from pre-standardized EUS images. The retained nonzero coefficient features were subsequently applied to develop predictive eight DL models based on distinct machine learning algorithms. The optimal DL model was identified and used to establish a clinical signature, which subsequently informed the construction and evaluation of a nomogram. Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP) were implemented to interpret and visualize the model outputs. A total of 2048 DL features were initially extracted, from which only 27 features with coefficients greater than zero were retained. The support vector machine (SVM) DL model demonstrated exceptional performance, achieving area under the curve (AUC) values of 0.948 and 0.795 in the training and test groups, respectively. Additionally, a nomogram was developed, incorporating both DL and clinical signatures, and was visually represented for practical application. Finally, the calibration curves, decision curve analysis (DCA) plots, and clinical impact curves (CIC) exhibited by the DL model and nomogram indicated high accuracy. The application of Grad-CAM and SHAP enhanced the interpretability of these models. These methodologies contributed substantial net benefits to clinical decision-making processes. A novel interpretable DL model and nomogram were developed and validated using EUS images, cooperating with machine learning algorithms. This approach demonstrates significant potential for enhancing the clinical applicability of EUS in predicting PNETs from pancreatic cancer, thereby offering valuable insights for future research and implementation.

Endoscopic ultrasound-guided local ablation therapy is one of the most important approaches for treating insulinomas that arise from neuroendocrine islet cell tumors located within the pancreas. This study aimed to evaluate the efficacy of various ablative treatments including anhydrous ethanol, lauromacrogol, polidocanol, and paclitaxel as local ablative agents on subcutaneous insulinoma tumors in mice models using tumor necrosis and drug distribution. For this purpose, mice were modeled for insulinoma tumors by subcutaneous injection of Ins-1 and Min-6 cell lines in 4-6 weeks-old nude female mice. The tumors became visible 1 to 2 weeks after the transplantation of cells, reaching a treatment-appropriate volume of 2030mm3 within 2 to 3 weeks, as confirmed by the insulinoma-like characteristics observed during histopathological analysis. The results indicated that the insulinoma animal models exhibited an early onset of hypoglycemia and significantly elevated serum insulin levels during starvation tests, compared to the control group further confirmed by expression of chromogranin A (CgA), synaptophysin (Syn), and insulinoma-associated protein 1 (Insm1) in the tumor cells during immunohistochemical staining. Following treatment, necrosis percentages in insulinoma tumors were significantly higher in the paclitaxel (93.2%) and ethanol (86.5%) groups compared to saline, polidocanol, and polyglactin groups. Similarly, tumor drug distribution was tracked using methylene blue, with paclitaxel demonstrating the fastest diffusion, followed by ethanol, polidocanol, and polyglactin. These findings suggest that both paclitaxel and polidocanol have significant potential as local ablative agents in inducing tumor necrosis, with paclitaxel offering the fastest drug dispersion. These results highlight the potential for further optimization of ablation therapies in insulinoma treatment.

BACKGROUND:Artesunate (ART) has been recognized to induce ferroptosis in various tumor phenotypes, including neuroendocrine tumors. We aimed to investigate the effects of ART on insulinoma and the underlying mechanisms by focusing on the process of ferroptosis.METHODS:The CCK8 and colony formation assays were conducted to assess the effectiveness of ART. Lipid peroxidation, glutathione, and intracellular iron content were determined to validate the process of ferroptosis, while ferrostatin-1 (Fer-1) was employed as the inhibitor of ferroptosis. Subcutaneous tumor models were established and treated with ART. The ferroptosis-associated proteins were determined by western blot and immunohistochemistry assays. Pathological structures of the liver were examined by hematoxylin-eosin staining.RESULTS:ART suppressed the growth of insulinoma both in vitro and in vivo. Insulinoma cells treated by ART revealed signs of ferroptosis, including increased lipid peroxidation, diminished glutathione levels, and ascending intracellular iron. Notably, ART-treated insulinoma cells exhibited a decline in the expressions of catalytic component solute carrier family 7 member 11 (SLC7A11) and glutathione peroxidase 4 (GPX4). These alterations were negated by Fer-1. Moreover, no hepatotoxicity was observed upon the therapeutic dose of ART.CONCLUSION:Artesunate might regulate ferroptosis of insulinoma cells through the SLC7A11/GPX4 pathway.

Introduction: 5-Iodotubercidin, a type of purine derivative, has attracted increasing attention in tumor chemotherapy because of its potential as an antitumor agent in recent years. In this study, we confirmed the effects on apoptosis in insulinoma cell lines induced by 5-iodotubercidin and tried to illuminate the underlying mechanisms. Methods: We used 5-iodotubercidin in the treatment of insulinoma cells and the cell proliferation was examined using CCK-8 assay, colony-forming assays, and insulinoma animal models. Cell apoptosis was examined using TUNEL assays and Western blotting. Cellular DNA damage was shown by comet assay and immunofluorescence. The expression of apoptosis-regulating proteins and DNA damage biomarker was investigated by Western blotting. Subcutaneous inoculation of the insulinoma cells into nude mice was to measure blood glucose, insulin levels, and tumor growth. ATM siRNA and p53 siRNA were used as loss-of-function targets to evaluate 5-iodotubercidin treatment. Results: 5-Iodotubercidin inhibited the proliferation of insulinoma cells and induced DNA damage and cell apoptosis. Moreover, 5-iodotubercidin induced ATM and p53 activated. In vivo, 5-iodotubercidin inhibited the growth of Ins-1 and Min-6 cells xenografts in nude mice. Conclusion: 5-Iodotubercidin induces DNA damage leading to insulinoma cells apoptosis by activating ATM/p53 pathway. Therefore, this is a potential strategy for treating insulinoma.

Background Endoscopic ultrasound-guided local ablation therapy stands as one of the most important approach for the treatment of insulinomas. We aimed to compare the effects of four drugs (anhydrous ethanol, lauromacrogol, polidocanol, and paclitaxel) as local ablative agents on subcutaneous insulinomas in nude mice. Additionally, we aimed to determine the diffusion rate of these drugs within tumors by utilizing methylene blue as a tracer. Methods Insulinoma cells were inoculated subcutaneously into nude mice, and the successful construction of an animal model of insulinoma was confirmed by testing blood glucose, insulin levels, and transplantation tumor pathology. The tumor-forming nude mice were ablated with different doses of saline, anhydrous ethanol, lauromacrogol, polidocanol and paclitaxel. The tumor necrosis percentages were determined to assess the therapeutic efficacy. Methylene blue was added to the ablative drug solution at a concentration of 10% to follow ablation treatments, and the diffusion rates in tumors were estimated by calculating the diffusion area of the drug. Results The tumor necrosis percentages in each group were paclitaxel: 93.20%, ethanol: 86.51%, polidocanol: 70.48%, lauromacrogol: 34.26%, and saline: 3.29%. The paclitaxel and ethanol group percentages were significantly higher than the rest of the groups, but there was no significant difference between them. In tumors, paclitaxel was the fastest to disperse, followed by ethanol and polidocanol, while lauromacrogol was the slowest. Conclusions Paclitaxel and polidocanol may potentially serve as local ablative agents for the treatment of insulinomas.

Almost 50% of esophageal adenocarcinoma (EAC) patients progressed from Barrett's esophagus (BE). EAC is often diagnosed at late stages and is related to dismal prognosis. However, there are still no effective methods for stratification and therapy in BE and EAC. Two public datasets (GSE26886 and GSE37200) were analyzed to identify differentially expressed genes (DEGs) between BE and EAC. Then, a series of bioinformatics analyses were performed to explore potential biomarkers associated with BE-EAC. 27 up- and 104 down-regulated genes were observed between GSE26886 and GSE37200. The GO and KEGG enrichment analysis indicated that the DEGs were highly involved in tumorigenesis. Subsequently, Weighted Gene Co-Expression Network Analysis (WGCNA) were performed to explore the potential genes related to BE-EAC, which were validated in The Cancer Genome Atlas (TCGA) database, and 5 up-regulated genes (MYO1A, ACE2, COL1A1, LGALS4, and ADRA2A) and 3 down-regulated genes (AADAC, RAB27A, and P2RY14) were found in EAC. Meanwhile, ADRA2A and AADAC could contribute to EAC pathogenesis and progression. MYO1A, ACE2, COL1A1, LGALS4, ADRA2A, AADAC, RAB27A, and P2RY14 could be potential novel diagnostic and prognostic biomarkers in BE-EAC.

Rationale:Small intestinal hemangioma is a rare condition and very difficult to diagnose preoperatively. It can occur in all segments of the small intestine, but jejunum is common. Its common symptoms are gastrointestinal bleeding and chronic anemia, while intussusception, intestinal obstruction and perforation are rare. In recent years, the popularization and application of capsule endoscopy, computed tomographic enterography and double-balloon enteroscopy play vital roles in the diagnosis and management of small bowel bleeding. We report a case of gastrointestinal hemorrhage caused by of the small intestine hemangioma. Patient concerns:A 56-year-old male complaint of hematochezia for 1 day with dizziness, fatigue, and vomiting of gastric contents. Diagnosis:Based on the clinical, laboratory, imaging tests, endoscopy, laparoscopic approach and pathological examination, the patient was diagnosed with small intestinal hemangioma. Interventions:Segmental resection was performed for the small intestinal hemangioma by a laparoscopic approach. Outcomes:The patient was discharged without operation complications, and his hemoglobin increased to 130 g/L at the second month after the operation. Lessons:Small intestinal hemangioma is a rare condition without specific symptoms and can cause gastrointestinal bleeding. The possibility of small intestinal hemangioma should be considered with unexplained gastrointestinal bleeding. Surgical resection is the preferred treatment option for symptomatic hemangiomas. Furthermore, double-balloon enteroscopy can increase the diagnostic yield. Applying endoscopic titanium clip combined with Indian ink marking can obtain an accurate positioning before surgery.