Endoscopic ultrasonography-based intratumoral and peritumoral machine learning radiomics analyses for distinguishing insulinomas from non-functional pancreatic neuroendocrine tumors.

Objectives: To develop and validate radiomics models utilizing endoscopic ultrasonography (EUS) images to distinguish insulinomas from non-functional pancreatic neuroendocrine tumors (NF-PNETs). Methods: A total of 106 patients, comprising 61 with insulinomas and 45 with NF-PNETs, were included in this study. The patients were randomly assigned to either the training or test cohort. Radiomics features were extracted from both the intratumoral and peritumoral regions, respectively. Six machine learning algorithms were utilized to train intratumoral prediction models, using only the nonzero coefficient features. The researchers identified the most effective intratumoral radiomics model and subsequently employed it to develop peritumoral and combined radiomics models. Finally, a predictive nomogram for insulinomas was constructed and assessed. Results: A total of 107 radiomics features were extracted based on EUS, and only features with nonzero coefficients were retained. Among the six intratumoral radiomics models, the light gradient boosting machine (LightGBM) model demonstrated superior performance. Furthermore, a peritumoral radiomics model was established and evaluated. The combined model, integrating both the intratumoral and peritumoral radiomics features, exhibited a comparable performance in the training cohort (AUC=0.876) and achieved the highest accuracy in predicting outcomes in the test cohorts (AUC=0.835). The Delong test, calibration curves, and decision curve analysis (DCA) were employed to validate these findings. Insulinomas exhibited a significantly smaller diameter compared to NF-PNETs. Finally, the nomogram, incorporating diameter and radiomics signature, was constructed and assessed, which owned superior performance in both the training (AUC=0.929) and test (AUC=0.913) cohorts. Conclusion: A novel and impactful radiomics model and nomogram were developed and validated for the accurate differentiation of NF-PNETs and insulinomas utilizing EUS images.

Evaluation of a blood miRNA/mRNA signature to follow-up Lu-PRRT therapy for G1/G2 intestinal neuroendocrine tumors.

Background: 177Lu-oxodotreotide peptide receptor therapy (LuPRRT) is an efficient treatment for midgut neuroendocrine tumors (NETs) of variable radiological response. Several clinical, biological, and imaging parameters may be used to establish a relative disease prognosis but none is able to predict early efficacy or toxicities. We investigated expression levels for mRNA and miRNA involved in radiosensitivity and tumor progression searching for correlations related to patient outcome during LuPRRT therapy. Methods: Thirty-five patients received LuPRRT for G1/G2 midgut NETs between May 2019 and September 2021. Peripheral blood samples were collected prior to irradiation, before and 48 h after the second and the fourth LuPRRT, and at 6-month follow-up. Multiple regression analyses and Pearson correlations were performed to identify the miRNA/mRNA signature that will best predict response to LuPRRT. Results: Focusing on four mRNAs and three miRNAs, we identified a miRNA/mRNA signature enabling the early identification of responders to LuPRRT with significant reduced miRNA/mRNA expression after the first LuPRRT administration for patients with progressive disease at 1 year (p < 0.001). The relevance of this signature was reinforced by studying its evolution up to 6 months post-LuPRRT. Moreover, nadir absolute lymphocyte count within the first 2 months after the first LuPRRT administration was significantly related to low miRNA/mRNA expression level (p < 0.05) for patients with progressive disease. Conclusion: We present a pilot study exploring a miRNA/mRNA signature that correlates with early hematologic toxicity and therapeutic response 12 months following LuPRRT. This signature will be tested prospectively in a larger series of patients.

A primary sphenoclival skull base neuroendocrin tumor: A rare case report and literature review.

INTRODUCTION AND IMPORTANCE: Primary intracranial neuroendocrine tumors (NETs) are exceedingly rare, often posing diagnostic challenges, particularly in non-secreting variants. These tumors may initially present with nonspecific symptoms, leading to delayed diagnosis and potential neurological complications. CASE REPORT: We present the case of a 33-year-old male admitted with a one-year history of progressively worsening headache accompanied by acute left ptosis and diplopia. Initial examination revealed left eye ptosis and hypotropia, indicative of third and fourth cranial nerve paralysis. Cavoscopy revealed a mild anterior wall bulge of the sphenoid with normal mucosa. MRI imaging unveiled an expansive clival process extending towards the sellar region and left cavernous sinus, completely occupying the sphenoid sinus and exerting mass effect on the pituitary stalk. Hormonal assays were within reference ranges, ruling out a hormonally-active tumor. Endoscopic endonasal surgery for biopsy revealed a low-grade neuroendocrine tumor positive for cytokeratin AE1/AE2, chromogranin A, synaptophysin, and beta-catenin, with a Ki-67-labeling index <2 %. Somatostatin receptor scintigraphy confirmed intense hyper fixation of the tracer in the sphenoidal tumor, supporting its neuroendocrine origin. The patient declined surgical intervention after informed consent, opting for C1 somatostatin analogs prior to radiotherapy. One-year follow-up demonstrated symptom stability with no tumor progression. CLINICAL DISCUSSION: To this day, no consensus among reports concerning the optimal management of these cases. Imaging assessment is crucial to validate the primary nature of the tumor and to exclude any distant localization. Various therapeutic modalities, such as surgery, radiotherapy, and somatostatin analogs, should be considered based on the specific characteristics and extent of the tumor. CONCLUSION: Our case is a clear reminder that neuroendocrine tumors should be considered as a differential diagnosis for skull base neoplasms.

The Application of 68Ga-Somatostatin Analog and 18F-FDG PET/CT for Bone Metastasis from Neuroendocrine Tumors.

INTRODUCTION: Aims of the study were to assess the differences in the diagnostic efficacy of 68Ga-somatostatin receptor analogs (68Ga-SSAs) and 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) for detecting bone metastases in neuroendocrine neoplasm (NEN) and to analyze the correlation between imaging features and clinical features of BMs. METHODS: We retrospectively analyzed the clinical and imaging data of 213 NEN patients who underwent 68Ga-SSA PET/CT and were finally diagnosed as BMs by pathology or follow-up. Of those, 103 patients underwent 18F-FDG PET/CT within 7 days after 68Ga-SSA PET/CT. RESULT: The BM detection rate of 68Ga-SSA PET/CT was higher than 18F-FDG PET/CT (86.4% vs. 66.0%, p = 0.02) in 103 patients with dual scanning. Meanwhile, the number of positive lesions in 68Ga-SSA PET/CT was significantly more than in 18F-FDG PET/CT (3.37 ± 1.95 vs. 2.23 ± 2.16, t = 4.137, p < 0.001). Most bone metastasis lesions presented as osteogenic change in CT (55.4%, 118/213). Concerning the primary tumor, the most frequent were of pancreatic origin (26.3%, 56/213), followed by rectal origin (22.5%, 48/213), thymic origin in 33 cases (15.5%), pulmonary origin in 29 cases (13.6%), paraganglioma in 20 cases (9.4%). The efficiency of 68Ga-SSA PET/CT to detect BMs was significantly correlated with the primary site (p = 0.02), with thymic carcinoid BMs being the most difficult to detect, and the positive rate was only 60.6% (20/33). However, 18F-FDG PET/CT positive rate was 76.92% (10/13) in thymic carcinoid BMs. In addition, the BMs of 7 patients in this study were detected by 68Ga-SSA PET earlier than CT for 4.57 months (range: 2-10 months). CONCLUSION: 68Ga-SSA PET/CT has higher sensitivity for detecting the BMs of NEN than 18F-FDG and detects the BM earlier than CT. Moreover, 18F-FDG PET/CT should be a complement for diagnosing the BMs of thymic carcinoids.

Screening for carcinoid heart disease: Trends and future Perspectives.

Background: Screening for carcinoid heart disease (CHD), has historically lacked consensus expert guidelines. In 2017, the North American Neuroendocrine Tumor Society (NANETS) released expert recommendations for CHD screening among NET patients to improve CHD detection. The objective of this study is to evaluate CHD screening trends and utility of screening guidelines over more than two decades at a single tertiary care center. Materials and methods: Patients with NETs referred for abdominal surgical evaluation at a single tertiary care center were included, 300 patients from 1999 to 2018 and 34 patients from 2021 to 2022. Lab values for the following NANETS-proposed criteria at any point during their treatments were recorded: NETs with liver metastasis, blood serotonin >5 times upper limit of normal (>1000 ng/mL), NT-ProBNP >260 pg/mL and clinical features suggestive of CHD. Results: 85 % (285/334) of patients included in this study met one or more expert-recommended CHD screening criteria. However, 40 % (132/285) of patients meeting one or more criteria received CHD screening via echocardiogram at some point following NET diagnosis. While rates of screening for patients increased from the first decade to the second decade (32 % vs 40.6 %), the rates were much higher after guideline publication (70 %, 24/34). Furthermore, patients meeting multiple screening criteria were more likely to have evidence of structural valve disease. Conclusions: Results of this study suggest that utilization of these four expert-recommended screening criteria have greatly increased rates of CHD screening via echocardiogram and could assist in improving early CHD detection, especially for patients meeting multiple criteria.

Quantitative SSTR-PET/CT: a potential tool for predicting everolimus response in neuroendoctine tumour patients.

BACKGROUND: This study aimed to assess 68Ga-DOTA-TATE (-TOC) PET/CT quantitative parameters in monitoring and predicting everolimus response in neuroendocrine tumor (NET) patients with hepatic metastases (NELM). PATIENTS AND METHODS: This retrospective analysis included 29 patients with 62 target lesions undergoing everolimus treatment and pre-therapy, and follow-up 68Ga-DOTA-TATE (-TOC) PET/CT scans. Response evaluation utilized progression-free survival (PFS) categorized as responders (R; PFS > 6 months) and non-responders (NR; PFS ≤ 6 months). Lesion size and density, along with maximum and median standardize uptake value (SUV) in target lesions, liver, and spleen were assessed. Tumor-to-spleen (T/S) and tumor-to-liver (T/L) ratios were calculated, including the tumor-to-spleen (T/S) ratio and tumor-to-liver (T/L) ratio (using SUVmax/SUVmax, SUVmax/SUVmean, and SUVmean/SUVmean). RESULTS: PET/CT scans were acquired 19 days (interquartile range [IQR] 69 days) pre-treatment and 127 days (IQR 74 days) post-starting everolimus. The overall median PFS was 264 days (95% CI: 134-394 days). R exhibited significant decreases in Tmax/Lmax and Tmean/Lmax ratios compared to NR (p = 0.01). In univariate Cox regression, Tmean/Lmax ratio was the sole prognostic parameter associated with PFS (HR 0.5, 95% CI 0.28-0.92, p = 0.03). Percentage changes in T/L and T/S ratios were significant predictors of PFS, with the highest area under curve (AUC) for the percentage change of Tmean/Lmax (AUC = 0.73). An optimal threshold of < 2.5% identified patients with longer PFS (p = 0.003). No other imaging or clinical parameters were predictive of PFS. CONCLUSIONS: This study highlights the potential of quantitative SSTR-PET/CT in predicting and monitoring everolimus response in NET patients. Liver metastasis-to-liver parenchyma ratios outperformed size-based criteria, and Tmean/Lmax ratio may serve as a prognostic marker for PFS, warranting larger cohort investigation.

Identification of Prolactinoma in Pituitary Neuroendocrine Tumors Using Radiomics Analysis Based on Multiparameter MRI.

This study aims to investigate the feasibility of preoperatively predicting histological subtypes of pituitary neuroendocrine tumors (PitNETs) using machine learning and radiomics based on multiparameter MRI. Patients with PitNETs from January 2016 to May 2022 were retrospectively enrolled from four medical centers. A cfVB-Net network was used to automatically segment PitNET multiparameter MRI. Radiomics features were extracted from the MRI, and the radiomics score (Radscore) of each patient was calculated. To predict histological subtypes, the Gaussian process (GP) machine learning classifier based on radiomics features was performed. Multi-classification (six-class histological subtype) and binary classification (PRL vs. non-PRL) GP model was constructed. Then, a clinical-radiomics nomogram combining clinical factors and Radscores was constructed using the multivariate logistic regression analysis. The performance of the models was evaluated using receiver operating characteristic (ROC) curves. The PitNET auto-segmentation model eventually achieved the mean Dice similarity coefficient of 0.888 in 1206 patients (mean age 49.3 ± SD years, 52% female). In the multi-classification model, the GP of T2WI got the best area under the ROC curve (AUC), with 0.791, 0.801, and 0.711 in the training, validation, and external testing set, respectively. In the binary classification model, the GP of T2WI combined with CE T1WI demonstrated good performance, with AUC of 0.936, 0.882, and 0.791 in training, validation, and external testing sets, respectively. In the clinical-radiomics nomogram, Radscores and Hardy' grade were identified as predictors for PRL expression. Machine learning and radiomics analysis based on multiparameter MRI exhibited high efficiency and clinical application value in predicting the PitNET histological subtypes.

Well-differentiated G1 and G2 pancreatic neuroendocrine tumors: a meta-analysis of published expanded DNA sequencing data.

Introduction: Well-differentiated pancreatic neuroendocrine tumors (PNETs) can be non-functional or functional, e.g. insulinoma and glucagonoma. The majority of PNETs are sporadic, but PNETs also occur in hereditary syndromes, primarily multiple endocrine neoplasia type 1 (MEN1). The Knudson hypothesis stated a second, somatic hit in MEN1 as the cause of PNETs of MEN1 syndrome. In the recent years, reports on genetic somatic events in both sporadic and hereditary PNETs have emerged, providing a basis for a more detailed molecular understanding of the pathophysiology. In this systematic review and meta-analysis, we made a collation and statistical analysis of aggregated frequent genetic alterations and potential driver events in human grade G1/G2 PNETs. Methods: A systematic search was performed in concordance with the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) reporting guidelines of 2020. A search in Pubmed for published studies using whole exome, whole genome, or targeted gene panel (+400 genes) sequencing of human G1/G2 PNETs was conducted at the 25th of September 2023. Fourteen datasets from published studies were included with data on 221 patients and 225 G1/G2 PNETs, which were divided into sporadic tumors, and hereditary tumors with pre-disposing germline variants, and tumors with unknown germline status. Further, non-functioning and functioning PNETs were distinguished into two groups for pathway evaluation. The collated genetical analyses were conducted using the 'maftools' R-package. Results: Sporadic PNETs accounted 72.0% (162/225), hereditary PNETs 13.3% (30/225), unknown germline status 14.7% (33/225). The most frequently altered gene was MEN1, with somatic variants and copy number variations in overall 42% (95/225); hereditary PNETs (germline variations in MEN1, VHL, CHEK2, BRCA2, PTEN, CDKN1B, and/or MUTYH) 57% (16/30); sporadic PNETs 36% (58/162); unknown germline status 64% (21/33). The MEN1 point mutations/indels were distributed throughout MEN1. Overall, DAXX (16%, 37/225) and ATRX-variants (12%, 27/225) were also abundant with missense mutations clustered in mutational hotspots associated with histone binding, and translocase activity, respectively. DAXX mutations occurred more frequently in PNETs with MEN1 mutations, p<0.05. While functioning PNETs shared few variated genes, non-functioning PNETs had more recurrent variations in genes associated with the Phosphoinositide 3-kinase, Wnt, NOTCH, and Receptor Tyrosine Kinase-Ras signaling onco-pathways. Discussion: The somatic genetic alterations in G1/G2 PNETs are diverse, but with distinct differences between sporadic vs. hereditary, and functional vs. non-functional PNETs. Increased understanding of the genetic alterations may lead to identification of more drivers and driver hotspots in the tumorigenesis in well-differentiated PNETs, potentially giving a basis for the identification of new drug targets. (Funded by Novo Nordisk Foundation, grant number NNF19OC0057915).

[Characteristics of gastric neuroendocrine tumors and the PDX-1 transcription factor expression]. / Kharakteristika neiroendokrinnykh opukholei zheludka i ekspressiya v nikh transkriptsionnogo faktora PDX-1.

OBJECTIVE: To study the features of gastric neuroendocrine tumors (NETs) and the diagnostic and prognostic significance of PDX-1 expression in them. MATERIAL AND METHODS: 207 NETs identified in 56 men and 115 women (59 had multiple NETs), and 94 cases of gastric cancer (comparison group) were studied morphologically and immunohistochemically. RESULTS: In more than half of the cases (54.93%), NETs were localized in the body of the stomach; the cardiac and antral parts of the stomach accounted for 8.64% and 11.73%, respectively. NETs of the cardiac region predominated in men, and of the body and antrum - in women. NETs of the cardiac region predominated in men, and of the body and antrum - in women. The vast majority of NETs were highly differentiated (89.20%), of which Grade 1, 2 and 3 were 55.41%, 40.76% and 3.82%, respectively. Neuroendocrine carcinomas (NEC) accounted for 10.80% of all NET cases. NECs were more often localized in the cardiac part of the stomach and accounted for 35.71% of all NETs in the cardiac part. The share of NEC among all NETs of the antrum was 15.79%, of the body of the stomach - only 3.37%. Metastases were found in 17.90% of NETs. Expression of PDX-1 was detected in 44.73% of NETs, 70% of NECs and 74.50% of gastric cancers. CONCLUSION: PDX-1 is involved in the mechanisms of precancerous and cancerous lesions of the stomach and its overexpression is detected in the majority of the most malignant NETs and gastric cancers.

Update on thymic epithelial tumors: a narrative review.

Background and Objective: Thymoma, thymic carcinoma and thymic neuroendocrine tumors originate from the epithelial cells of the thymus and account for the thymic epithelial tumors (TETs). Although TETs are uncommon, they are the most frequent tumor type in the anterior mediastinum. Multidisciplinary approach is essential for their correct management. The aim of the present review is to summarize the update management for TETs. Methods: For this review, we searched in Excerpta Medica database (EMBASE) and MEDLINE until 6 September 2023. The terms used in the search included thymoma, thymic carcinoma, thymic epithelial tumors, management, immunotherapy, multiple tyrosine kinases inhibitors. Key Content and Findings: The therapeutic approach is based on histology and tumor stage and may involve surgery with or without neoadjuvant or adjuvant treatment. In the metastatic setting, platinum-based chemotherapy is the standard of care and patients who do not respond to first-line treatment have limited treatment options mainly because of the poor efficacy shown in subsequent lines of therapy. Conclusions: Future research should focus on identifying predictive biomarkers for patients with TETs, and should implement multicenter collaborations and appropriate clinical trials tailored for rare tumor types. Immune check point inhibitors, mammalian target of rapamycin (mTOR) and antiangiogenic multikinase inhibitors have also been studied in this clinical setting.

Role of Nutrition in the Management of Patients with Multiple Endocrine Neoplasia Type 1.

Multiple endocrine neoplasia type 1 (MEN1) is a rare syndrome caused by inactivating mutations in the MEN1 tumor suppressor gene. The three main clinical manifestations of MEN1 are primary hyperparathyroidism (PHPT), duodenal-pancreatic neuroendocrine tumors (DP-NETs) and anterior pituitary tumors. Endocrine tumors in patients with MEN1 differ from sporadic tumors because of their younger age at onset, common multiple presentations and the different clinical course. MEN1 is characterized by a complex clinical phenotype; thus, patients should be followed by a multidisciplinary team of experts that includes an endocrinologist, a surgeon, a oncologist, a radiotherapist, and not least, a nutritionist. It is important to remember the fundamental role that diet plays as a primary prevention tool, together with a healthy and active lifestyle in preventing osteoporosis/osteopenia and reducing the risk of developing kidney stones due to hypercalciuria, two frequent clinical complications in MEN1 patients. Is very important for MEN1 patients to have an adequate intake of calcium, vitamin D, magnesium and phosphate to maintain good bone health. The intake of foods containing oxalates must also be kept under control because in combination with calcium they concur to form calcium oxalate crystals, increasing the risk of nephrolithiasis. Another aspect to consider is the management of patients with pancreatic neuroendocrine tumors undergoing major surgical resections of the pancreas that can lead to alterations in digestion and absorption mechanisms due to partial or total reduction in pancreatic enzymes such as amylase, lipase, and protease, resulting in malabsorption and malnutrition. Therefore, the nutritionist's aim should be to devise a dietary plan that takes into consideration each single patient, educating them about a healthy and active lifestyle, and accompanying them through various life stages by implementing strategies that can enhance their quality of life.

Serum ß-hCG as a Biomarker in Pancreatic Neuroendocrine Tumors: Rethinking Single-Analyte Approach.

Despite recent advances, neuroendocrine tumors (NETs) remain a challenging topic, due to their diversity and the lack of suitable biomarkers. Multianalyte assays and the shift to an omics-based approach improve on the conventional single-analyte strategy, albeit with their own drawbacks. We explored the potential of serum ß-hCG as a biomarker for NETs and discussed its role in disease monitoring. We recruited 40 patients with non-functioning pancreatic NETs, all with liver metastases. Serum ß-hCG concentrations were measured at 3-month intervals over 48 months. We performed a comparative and a repeated measures analysis of ß-hCG depending on WHO grade (G1, G2), liver tumor burden (LTB; below 10%, 10-25%), and RECIST 1.1. (stable disease, progressive disease). Patients with progressive disease (p < 0.001), 10-25% LTB (p < 0.001) and WHO Grade 2 (p < 0.001) displayed higher ß-hCG concentrations. Throughout the study, ß-hCG concentrations consistently increased across the entire cohort. Delta ß-hCG during the study period was greater in patients with 10-25% LTB (p < 0.001), progressive disease (p < 0.001), and G2 (p = 0.003). Serum ß-hCG correlates with established indicators of malignancy and disease progression in metastatic NETs, supporting further studies as a monitoring and prognostic biomarker. Despite promising results from novel biomarkers, there is still a place for single-analyte assays in NETs.

Hereditary Syndromes Associated with Pancreatic and Lung Neuroendocrine Tumors.

Pancreatic neuroendocrine tumors (PanNETs) and lung NETs (LNETs) represent a rare but clinically significant subgroup of neoplasms. While the majority is sporadic, approximately 17% of PanNETs and a subset of LNETs develop in the context of monogenic familial tumor syndromes, especially multiple endocrine neoplasia type 1 (MEN1) syndrome. Other inherited syndromes associated with PanNETs include MEN4, von Hippel-Lindau (VHL) syndrome, neurofibromatosis type 1 (NF1), and tuberous sclerosis complex (TSC). These syndromes are highly penetrant and their clinical manifestations may vary even among members of the same family. They are attributed to genetic mutations involving key molecular pathways regulating cell growth, differentiation, and angiogenesis. Pancreatic NETs in hereditary syndromes are often multiple, develop at a younger age compared to sporadic tumors, and are associated with endocrine and nonendocrine tumors derived from multiple organs. Lung NETs are not as common as PanNETs and are mostly encountered in MEN1 syndrome and include typical and atypical lung carcinoids. Early detection of PanNETs and LNETs related to inherited syndromes is crucial, and specific follow-up protocols need to be employed to optimize diagnosis and management. Genetic screening is recommended in childhood, and diagnostic screening starts often in adolescence, even in asymptomatic mutation carriers. Optimal management and therapeutic decisions should be made in the context of a multidisciplinary team in specialized centers, whereas specific biomarkers aiming to identify patients denoted to follow a more aggressive course need to be developed.

Successful liver transplantation as rescue therapy in a patient with metastases from a vasoactive intestinal peptide producing neuroendocrine tumor.

This case report presents a 40-year-old patient with a vasoactive intestinal peptide (VIP) secreting high grade (Ki-67 39%) neuroendocrine tumor (NET) from the pancreas, for whom successful liver transplantation (LT) was carried out 8 years after resection of the primary tumor due to massive liver metastases. The transplantation was done as rescue therapy due to rapid progression and a devastating clinical condition requiring intravenous supplementation for 20 hours daily. The latest imaging carried out 18 months after transplantation is without signs of recurrence, and the patient is in good health with undetectable levels of VIP. According to the guidelines, LT is only recommended if Ki-67 is <20% and if there has been tumor control for more than 6 months prior to transplantation. Our case illustrates that LT is an option that should be considered for selected NET patients without extrahepatic involvement regardless of tumor grade and clinical condition.

Carcinoid Heart Syndrome With Metastatic Low-Grade Neuroendocrine Tumor of the Liver: A Rare Case.

We present a rare and complex case of a 76-year-old male patient with a history of low-grade neuroendocrine tumor (NET) of the small intestine, status post resection, who presented with recurrence of the tumor in the liver and subsequent carcinoid heart syndrome (CHS). The recurrent liver tumor caused severe tricuspid regurgitation and CHS, highlighting the rare association between NETs and CHS, particularly in the elderly population. This case underscores the importance of multidisciplinary care and close monitoring for patients with recurrent NETs and potential cardiac complications.

Construction and validation of an endoscopic ultrasonography-based ultrasomics nomogram for differentiating pancreatic neuroendocrine tumors from pancreatic cancer.

Objectives: To develop and validate various ultrasomics models based on endoscopic ultrasonography (EUS) for retrospective differentiating pancreatic neuroendocrine tumors (PNET) from pancreatic cancer. Methods: A total of 231 patients, comprising 127 with pancreatic cancer and 104 with PNET, were retrospectively enrolled. These patients were randomly divided into either a training or test cohort at a ratio of 7:3. Ultrasomics features were extracted from conventional EUS images, focusing on delineating the region of interest (ROI) for pancreatic lesions. Subsequently, dimensionality reduction of the ultrasomics features was performed by applying the Mann-Whitney test and least absolute shrinkage and selection operator (LASSO) algorithm. Eight machine learning algorithms, namely logistic regression (LR), light gradient boosting machine (LightGBM), multilayer perceptron (MLP), random forest (RF), extra trees, k nearest neighbors (KNN), support vector machine (SVM), and extreme gradient boosting (XGBoost), were employed to train prediction models using nonzero coefficient features. The optimal ultrasomics model was determined using a ROC curve and utilized for subsequent analysis. Clinical-ultrasonic features were assessed using both univariate and multivariate logistic regression. An ultrasomics nomogram model, integrating both ultrasomics and clinical-ultrasonic features, was developed. Results: A total of 107 EUS-based ultrasomics features were extracted, and 6 features with nonzero coefficients were ultimately retained. Among the eight ultrasomics models based on machine learning algorithms, the RF model exhibited superior performance with an AUC= 0.999 (95% CI 0.9977 - 1.0000) in the training cohort and an AUC= 0.649 (95% CI 0.5215 - 0.7760) in the test cohort. A clinical-ultrasonic model was established and evaluated, yielding an AUC of 0.999 (95% CI 0.9961 - 1.0000) in the training cohort and 0.847 (95% CI 0.7543 - 0.9391) in the test cohort. Subsequently, the ultrasomics nomogram demonstrated a significant improvement in prediction accuracy in the test cohort, as evidenced by an AUC of 0.884 (95% CI 0.8047 - 0.9635) and confirmed by the Delong test. The calibration curve and decision curve analysis (DCA) depicted this ultrasomics nomogram demonstrated superior accuracy. They also yielded the highest net benefit for clinical decision-making compared to alternative models. Conclusions: A novel ultrasomics nomogram was proposed and validated, that integrated clinical-ultrasonic and ultrasomics features obtained through EUS, aiming to accurately and efficiently identify pancreatic cancer and PNET.

A case of early-stage type 3 gastric neuroendocrine tumor in the upper body of the stomach: is endoscopic resection feasible?

Although gastric neuroendocrine tumors (NETs) are uncommon compared with gastric carcinomas, the incidence of NETs has been recently increasing. Gastric NETs are classified into three subgroups, and among these, gastrin-independent sporadic type 3 gastric NETs have a poor prognosis because of frequent lymph node or distant metastasis. We experienced a case of an early-stage type 3 gastric NET associated with lymphovascular and submucosal invasion. In a 54 year-old woman, esophagogastroduodenoscopy performed during a health screening identified an elevated lesion of the upper body of the stomach. The results of immunohistochemical analyses of endoscopic biopsy specimens obtained from the lesion were positive for chromogranin A and synaptophysin, indicating an NET. Because the patient's serum gastrin level was normal and she had no predisposing conditions for NET development, the tumor was diagnosed as a type 3 gastric NET. The patient underwent local resection of the tumor and regional lymph node dissection. The resected specimen indicated a diagnosis of type 3 gastric NET with invasion into the submucosa and lymphatic duct. This is an extremely rare case of an early-stage type 3 gastric NET. Our discussion provides insight into the pathogenesis and development of these tumors and the appropriate therapeutic strategy.

[Paragangliomas of the head and neck]. / Paragangliome im Kopf-Hals-Bereich.

Paragangliomas represent a heterogeneous group of rare neuroendocrine tumors with marked variability in symptoms and disease course. Due to the close proximity to neurovascular structures, paragangliomas of the head and neck region can cause a variety of symptoms. To this day, there are no reliable prognostic factors that can predict a potentially malignant course. All patients with newly diagnosed paragangliomas should undergo an early diagnostic workup and regular follow-up examinations in specialized centers. While radical resection was previously regarded as standard treatment for paragangliomas, radiotherapy and active surveillance (watch-and-scan strategy) have become equally important over the years. Low-threshold techniques for molecular pathology analysis of the mutation-specific behavior of paragangliomas are nowadays available.

A rare case of small cell neuroendocrine carcinoma of gallbladder origin.

Neuroendocrine carcinomas (NECs) of the gallbladder are very rare and aggressive tumors with poor prognosis. Most of them are poorly differentiated and belong to the small cell type. We report a case of a 59-year-old woman who presented with abdominal pain and distension. Contrast-enhanced computed tomography revealed a large heterogeneous mass in the liver, adjacent to the gallbladder, and omental nodules. CA 19-9 level was elevated and ascitic fluid cytology was suspicious for malignancy. Percutaneous biopsy of the liver mass confirmed the diagnosis of small cell NEC of the gallbladder. The patient was considered inoperable and planned for chemotherapy, but she died 20 days after admission. This case illustrates the diagnostic challenges and the dismal outcome of small cell NEC of the gallbladder. Early detection and multimodal treatment are essential for improving the survival of these patients.