Neuroendocrine Tumors Research Articles

Androgen production, uptake, and conversion (APUC) genes define prostate cancer patients with distinct clinical outcomes.

BACKGROUNDProstate cancer (PC) is driven by aberrant signaling of the androgen receptor (AR) or its ligands, and androgen deprivation therapies (ADTs) are a cornerstone of treatment. ADT responsiveness may be associated with germline changes in genes that regulate androgen production, uptake, and conversion (APUC).METHODSWe analyzed whole-exome sequencing (WES) and whole-transcriptome sequencing (WTS) data from prostate tissues (SU2C/PCF, TCGA, GETx). We also interrogated the Caris Precision Oncology Alliance (POA) DNA (592-gene/whole exome) and RNA (whole transcriptome) next-generation sequencing databases. Algorithm for Linking Activity Networks (ALAN) was used to quantify all pairwise gene-to-gene associations. Real-world overall survival was determined from insurance claims data using Kaplan-Meier estimates.RESULTSSix APUC genes (HSD3B1, HSD3B2, CYP3A43, CYP11A1, CYP11B1, CYP17A1) exhibited coalescent gene behavior in a cohort of metastatic tumors (n = 208). In the Caris POA dataset, the 6 APUC genes (APUC-6) exhibited robust clustering in primary prostate (n = 4,490) and metastatic (n = 2,593) biopsies. Surprisingly, tumors with elevated APUC-6 expression had statically lower expression of AR, AR-V7, and AR signaling scores, suggesting ligand-driven disease biology. APUC-6 genes instead associated with the expression of alternative steroid hormone receptors, ESR1/2 and PGR. We used RNA expression of AR or APUC-6 genes to define 2 subgroups of tumors with differential association with hallmark pathways and cell surface targets.CONCLUSIONSThe APUC-6-high/AR-low tumors represented a subgroup of patients with good clinical outcomes, in contrast with the AR-high or neuroendocrine PCs. Altogether, measuring the aggregate expression of APUC-6 genes in current genomic tests identifies PCs that are ligand (rather than AR) driven and require distinct therapeutic strategies.FUNDINGNCI/NIH 1R37CA288972-01, NCI Cancer Center Support P30 CA077598, DOD W81XWH-22-2-0025, R01 CA249279.

Unmasking Neuroendocrine Prostate Cancer with a Machine Learning-Driven Seven-Gene Stemness Signature That Predicts Progression.

Prostate cancer (PCa) poses a significant global health challenge, particularly due to its progression into aggressive forms like neuroendocrine prostate cancer (NEPC). This study developed and validated a stemness-associated gene signature using advanced machine learning techniques, including Random Forest and Lasso regression, applied to large-scale transcriptomic datasets. The resulting seven-gene signature (KMT5C, DPP4, TYMS, CDC25B, IRF5, MEN1, and DNMT3B) was validated across independent cohorts and patient-derived xenograft (PDX) models. This signature demonstrated strong prognostic value for progression-free, disease-free, relapse-free, metastasis-free, and overall survival. Importantly, the signature not only identified specific NEPC subtypes, such as large-cell neuroendocrine carcinoma, which is associated with very poor outcomes, but also predicted a poor prognosis for PCa cases that exhibit this molecular signature, even when they were not histopathologically classified as NEPC. This dual prognostic and classifier capability makes the seven-gene signature a robust tool for personalized medicine, providing a valuable resource for predicting disease progression and guiding treatment strategies in PCa management.

Robotic Versus Laparoscopic Versus Open Surgery for Non-Metastatic Pancreatic Neuroendocrine Tumors (pNETs): A Systematic Review and Network Meta-Analysis.

Background: This systematic review, using pairwise and network meta-analyses, aimed to compare the intraoperative, short-term, and long-term postoperative outcomes of minimally invasive surgery (MIS) and open surgery (OS) for the management of pancreatic neuroendocrine tumors (pNETs). Methods: Studies reporting on the effects of robotic, laparoscopic, and open surgery on pNETs published before November 2023 on PubMed, Scopus, and CENTRAL were analyzed. Results: Thirty-two studies with 5379 patients were included in this review, encompassing 2251 patients undergoing MIS (1334 laparoscopic, 508 robotic, and 409 unspecified MIS) and 3128 patients undergoing OS for pNETs management. Pairwise meta-analysis revealed that the MIS group had a significantly shorter length of hospital stay ((a low certainty of evidence), MD of -4.87 (-6.19 to -3.56)); less intraoperative blood loss ((a low certainty of evidence), MD of -108.47 (-177.47 to -39.47)); and decreased tumor recurrence ((a high certainty of evidence), RR of 0.46, 95% CI (0.33 to 0.63)). Subgroup analysis indicated a higher R0 resection rate and prolonged operative time for laparoscopic surgery than for OS. The network meta-analysis ranked the robotic approach as superior in terms of the length of hospital stay, followed by the laparoscopic and OS arms. Furthermore, it favored both MIS approaches over OS in terms of the R0 resection rate. No significant differences were found in severe postoperative complications, postoperative fistula formation, mortality, readmission, reoperation, or conversion rates. Conclusions: This review supports the safety of MIS for the treatment of pNETs. However, the varying certainty of evidence emphasizes the need for higher-quality studies.

Hepatic Recurrence of Neuroendocrine Tumor Component in Gallbladder Cancer.

A 60-year-old man underwent an extended cholecystectomy with regional lymphadenectomy for T2N0M0 gallbladder cancer (GBC), which showed significant FDG uptake (SUVmax = 6.5). However, CT scan at 24 months postsurgery revealed multiple hepatic masses. Unlike the primary GBC, the hepatic masses showed limited FDG uptake (SUVmax = 3.7). A tumor biopsy revealed the diagnosis of a grade 3 neuroendocrine tumor. Furthermore, the hepatic masses showed significant uptake on somatostatin receptor scintigraphy. Upon reevaluation, the primary resected specimen was found to include approximately 10% of neuroendocrine tumor components. This case suggests that different FDG uptake between primary and metastatic cancer may necessitate differential diagnosis.

Demographic Characteristics and Survival in Young-Onset Colorectal Neuroendocrine Neoplasms.

Recent epidemiological studies have revealed an upward trend in young-onset colorectal cancer (YOCRC) overall, whereas specific data on young-onset colorectal neuroendocrine neoplasms (YONEN) remain limited. This study investigated the demographic characteristics and survival trends in YONEN and compared these with those of young-onset colorectal adenocarcinoma (YOADC), the most common histologic subtype of YOCRC. A retrospective analysis was conducted from 2000 to 2019 using the Surveillance, Epidemiology, and End Results (SEER) database. Survival outcomes were assessed using univariate and multivariable Cox proportional models, with demographic differences evaluated via Wilcoxon rank sum and Chi-square tests. Out of 61,705 patients aged 20-49 with colorectal cancer, 8% had NEN, and 92% had adenocarcinoma. The YONEN cohort had a higher proportion of Black patients and a lower proportion of White patients than the YOADC cohort (21% vs. 13% and 44% vs. 57%, respectively). NEN was more commonly found in the rectum (79%), and adenocarcinoma was mostly colonic (57%) in origin. YONEN patients had better survival than YOADC patients. Multivariate analysis in YONEN patients revealed that Hispanic patients had better overall survival compared to White patients (HR 0.67, 95% CI 0.47-0.95, p = 0.024). Racial disparities should be investigated further to aid in policymaking and targeted interventions.

The prognostic and therapeutic value of the tumor microenvironment and immune checkpoints in pancreatic neuroendocrine neoplasms

Pancreatic neuroendocrine neoplasms (Pan-NEN) represent a group of highly heterogeneous cancers, characterized by complex and diverse biological behavior. The objective of this study was to systematically investigate the immunological features of the tumor microenvironment (TME) in Pan-NEN, aiming to identify prognostic biomarkers and explore the therapeutic potential of immunotherapy for Pan-NEN. Tumor and adjacent normal tissues were collected from 56 patients with Pan-NEN. Immunohistochemical analysis was conducted on tumor tissues using a panel of monoclonal antibodies targeting key immune markers. The expression levels of these markers were quantitatively assessed and correlated with clinicopathological features and overall survival. Low expression of CD3, CD8, CD4, CD68, CD163, Foxp3, CD56, CD69, GZMB, HLA-1, HLA-II, PD-1, and PD-L1 were observed in the majority of Pan-NEN patient samples. PD-1 expression was positively correlated with CD4 and Foxp3 expression, while PD-L1 expression was positively correlated with CD68, CD163, and Foxp3 expression; HLA-II expression was positively correlated with GZMB expression. Infiltration of lymphocytes (CD3 + or CD8+) and macrophages (CD68 + or CD163+) and expression of PD-1/PD-L1 were more pronounced in poorly differentiated neuroendocrine carcinoma (Pan-NEC) compared to well-differentiated neuroendocrine tumors (Pan-NET), while CD68 and PD-L1 correlated with advanced disease stage. Conversely, HLA-I antigen expression was commonly downregulated in Pan-NEC. Univariate Cox proportional hazard analysis demonstrated that tumor grade, stage; CD4+, CD68+, and CD163 + cell count; and expression of PD-1 and PD-L1 were significantly associated with poor survival outcomes, while the positive expression of HLA-I was correlated with a more favorable survival prognosis. Furthermore, multivariate Cox proportional hazard analyses revealed that tumor grade, stage, and PD-1 expression are independent prognostic factors. The immunological landscape of Pan-NEN offers potential prognostic value and therapeutic targets. The findings suggest that immunotherapy, particularly targeting the PD-1/PD-L1 pathway, may serve as a promising strategy for the treatment of Pan-NEN, especially for Pan-NEC patients.

Hepatic Encephalopathy Without Hyperammonemia in the Setting of Liver Metastases by a Pancreatic Neuroendocrine Tumor

Hepatic Encephalopathy Without Hyperammonemia in the Setting of Liver Metastases by a Pancreatic Neuroendocrine Tumor

Treatment and survival of non-metastatic small cell carcinoma of the bladder from multiple centers in China

Small cell carcinoma of the bladder (SCCB) is a rare, highly malignant neuroendocrine tumor. This study attempted to analyze tumor characteristics, treatments and clinical outcomes in China. We conducted a retrospective analysis of patients diagnosed with non-metastatic SCCB at multi-institutions between January 2007 and January 2022. The Kaplan-Meier method was used to calculate survival. A total of 20 patients were included. 10 had localized disease (T1-2N0), and 10 had locally advanced disease (≥ T3 or N+). 13 received local treatment (partial cystectomy or transurethral resection of the bladder tumor) and 7 received radical treatment (radical cystectomy or radiotherapy). A total of 18 patients (90%) received chemotherapy (CT), either neoadjuvant CT (n = 5) or adjuvant CT (n = 13). The median OS for the receiving local treatment was 65.3 months (95% CI 0 to 138 months) and the corresponding 1-year, 2-year, and 3-year OS was 77%, 54%, and 54%, respectively. The median OS for the receiving radical treatment was not reached and the corresponding 1-year, 2-year, and 3-year OS was 100%, 100%, and 75%, respectively. The median PFS for receiving local treatment was 13.8 months (95% CI 9.3 to 18.3 months) and the corresponding 1-year, 2-year, and 3-year PFS was 46%, 31%, and 31%, respectively. The median PFS for the receiving radical treatment was not reached and the corresponding 1-year, 2-year, and 3-year PFS was 83%, 56%, and 56%, respectively. This study reported the largest cohort of non-metastatic SCCB among Chinese population. Given its metastatic potential, CT remained an essential part of the treatment. The survival outcomes of radical cystectomy and RT in non-metastatic SCCB were encouraging.

Immunohistochemical expression of ephrin receptors in neuroendocrine neoplasms: a case-series of gastroenteropancreatic neuroendocrine neoplasms and a systematic review of the literature.

Erythropoietin-producing hepatocellular (EPH) receptors are the largest known family of tyrosine kinases receptors (TKR) in humans, implicated in cell proliferation, adhesion, migration, tumor angiogenesis, invasion and metastasis. The aim of the present study is to assess the expression of EPHs in neuroendocrine neoplasms (NENs). Immunohistochemical staining of specimens of 30 patients with gastroenteropancreatic and lung NENs was performed for EPH-A1, EPH-A2, EPH-A4, EPH-A5 protein expression, in addition to ki-67 multiplication index and programmed death-ligand 1. Additionally, we performed a systematic review of the available literature in three different databases reporting on the expression of EPH in all neuroendocrine neoplasms. Positive expression was seen in 16/19 (84%) specimens for EPH-A1, 15/23 (65%) for EPH-A2, 21/24 (88%) for EPH-A4, 24/26 (92%) for EPH-A5. EPH-A1 was expressed in 9/9 pancreatic, 3/4 small intestine, but not in one lung NEN, EPH-A2 in 5/10 pancreatic, 3/4 small intestine and lung, and in one of each of gastric, appendix, colorectal, and cervical NENs, respectively. EPH-A4 showed positive expression in 9/11 pancreatic, 4/4 small intestine, 3/3 lung specimens and EPH-A5 in 10/11, 4/4 and 4/4, respectively. Data retrieved from the systematic review of the literature in combination with the data from the present study are suggestive of a frequent EPH expression in pituitary, thyroid, lung and gastroenteropancreatic NENs, yet, with varying expressions of the single receptor subtypes. EPHs may have a role in NEN tumorigenesis, prognosis as well as a role in the evolving molecular-targeted therapies.

Whole genome sequencing elucidates etiological differences in MCPyV-negative Merkel cell carcinoma

Merkel cell carcinoma (MCC) is an aggressive neuroendocrine neoplasm of the skin. Immunosuppression, ultraviolet radiation and the integration of Merkel cell polyomavirus (MCPyV) have all been shown to be involved in the pathogenesis of this malignancy. We performed whole genome sequencing on two MCPyV-negative cases of MCC that demonstrated very different clinical presentations and outcomes, and mutational profiles. The first case exhibited a highly aggressive clinical course, absence of UV-signature mutations and a low tumor mutational burden. A rearrangement in the tumor suppressor gene SUFU was identified, a likely driver and potential target of the Hedgehog signaling pathway. Meanwhile, the second case exhibited a less aggressive behavior, harbored UV-signature mutations, and a high mutational burden including mutations in TP53 and RB1.

Clinicopathological correlations in 38 cases of gastroenteropancreatic high-grade neuroendocrine neoplasms.

Diagnosis and treatment of gastroenteropancreatic high-grade neuroendocrine neoplasms (GEP-HG-NENs), particularly G3 well-differentiated neuroendocrine tumours (NETs) and poorly differentiated neuroendocrine carcinomas (NECs) relies on histopathological morphology, immunohistochemistry, and molecular biological markers, which are lacking especially in cases with ambiguous histomorphology. In this study to contribute to the development of more targeted treatment strategies, we examined various immunohistochemical and molecular biological markers and their association with clinicopathological features in GEP-HG-NENs. We included 38 patients with GEP-HG-NENs in this study, with their retrospective follow-up data. The expression of tumour protein p53 (TP53), RB transcriptional corepressor 1 (RB1), somatostatin receptor 2 (SSTR2), clusterin (CLU), and marker of proliferation Ki-67 (MKI67) was immunohistochemically analysed. KRAS proto-oncogene, GTPase (KRAS) and B-Raf proto-oncogene, serine/threonine kinase (BRAF) V600E expression was evaluated using quantitative real-time polymerase chain reaction (qRT-PCR). The relationships between immunohistochemical and molecular biological markers and clinicopathological characteristics were examined using a Cox risk regression model, receiver operating characteristic (ROC) curve, and Kaplan-Meier survival analyses. SSTR2, RB, TP53, and CLU expression differed between NET G3 and NECs, with variations among the NET G3 and small- and large-cell NEC (SCNEC and LCNEC, respectively) groups (p < 0.05). The median MKI67 proliferative index was approximately 40% and 70% in G3 NETs and NECs, respectively. The NET G3 group exhibited a median survival of 25 months, indicating a relatively better prognosis than that of the NECs group (median survival, 11 months). Both Kaplan-Meier survival analysis and the Cox risk regression model indicated a statistical correlation among treatment methods, CLU expression, and prognosis (p < 0.05). The BRAF V600E mutation rate was 32.4% in G3 NETs and SCNEC, demonstrating a significant difference between both types (p = 0.0086). Furthermore, ROC curve analysis highlighted the diagnostic significance of the positive expression of the immunohistochemical markers CLU, SSTR2, and RB in identifying NET G3. To guide more suitable treatment strategies, it is essential to develop and apply valuable and more targeted immunohistochemical and molecular pathological markers for a comprehensive analysis.

N-linked fucosylated glycans are biomarkers for prostate cancer with a neuroendocrine and metastatic phenotype.

Prostate cancer (PCa) is a heterogeneous disease with a spectrum of pathology and outcomes ranging from indolent to lethal. Although there have been recent advancements in prognostic tissue biomarkers, limitations still exist. We leveraged Matrix Assisted Laser Desorption Ionization (MALDI) imaging of formalin-fixed, paraffin embedded (FFPE) prostate cancer specimens to determine if N-linked glycans expressed in the extracellular matrix of lethal neuroendocrine prostate cancer were also expressed in conventional prostate adenocarcinomas that were associated with poor outcomes. We found that N-glycan fucosylation was abundant in neuroendocrine prostate cancer as well as adenocarcinomas at time of prostatectomy that eventually developed recurrent metastatic disease. Analysis of patient derived xenografts revealed that this fucosylation signature was enriched differently across metastatic disease organ sites, with the highest abundance in liver metastases. These data suggest that N-linked fucosylated glycans could be an early tissue biomarker for poor PCa outcomes. Implications: These studies identify that hyper-fucosylated N-linked glycans are enriched in neuroendocrine prostate cancer and conventional prostate adenocarcinomas that progress to metastatic disease, thus advancing biomarker discovery and providing insights into mechanisms underlying metastatic disease.

Adverse Events of Radioligand Therapy in Patients with Progressive Neuroendocrine Neoplasms: The Biggest Eastern European Prospective Study.

Neuroendocrine neoplasms (NENs) are neoplastic tumors developing in every part of the body, mainly in the gastrointestinal tract and pancreas. Their treatment involves the surgical removal of the tumor and its metastasis, long-acting somatostatin analogs, chemotherapy, targeted therapy, and radioligand therapy (RLT). A total of 127 patients with progressive neuroendocrine neoplasms underwent RLT-4 courses, administered every 10 weeks-with the use of 7.4 GBq [177Lu]Lu-DOTA-TATE or tandem therapy with 1.85 GBq [177Lu]Lu-DOTA-TATE and 1.85 GBq [90Y]Y-DOTA-TATE. Assessment of short- and long-term complications, as well as the calculation of progression-free survival (PFS) and overall survival (OS) were performed. RLT caused a statistically but not clinically significant decrease in blood morphology parameters during both short- and long-term observations. Glomerular filtration rate (GFR) significantly decreased only in a long-term observation after RLT; however, it was clinically acceptable. Computed predictions of progression-free survival (PFS) and overall survival (OS) indicated that five years post-RLT, there is a 74% chance of patients surviving, with only a 58.5% likelihood of disease progression. Computed predictions of PFS and OS confirmed treatment efficiency and good patient survival. RLT should be considered a safe and reliable line of treatment for patients with progressive NENs as it causes only a low number of low-grade adverse events.

Gastric glomus tumor with a rare presentation: a case report and review of the literature

Introduction and Importance: Gastric glomus tumors (GGT) are rare soft tissue tumors of the gastrointestinal tracts (GIT). It is somewhat challenging to establish the diagnosis of GGT and differentiate it from the more common submucosal neoplasms. Case Presentation: A 34-year-old female patient presented with upper gastrointestinal bleeding. Extensive workup including endoscopic ultrasonography (EUS) revealed a well-circumscribed isoechoic mass arising from the muscularis propria. Based on fine needle biopsy (FNB) findings, with H&amp;E stains performed only initially, the mass was considered a neuroendocrine tumor (NET). Antrectomy with Billroth II anastomosis was performed. A microscopic and immunohistochemical studies of the resected specimen showed the cells to be positive for smooth muscle actin (SMA) making GGT the final diagnosis. Clinical Discussion: Of the 116 patients included in our analysis, 56.9% (n=66) were females and age group was between 41-64 years old in 63.8% (n=74) of the patients. About 55 cases (47.4%) had abdominal or epigastric pain or discomfort, which was the most frequent clinical symptom. In immunohistochemistry, SMA staining is present in 68.1% of the cases, underscoring its diagnostic significance. Laparotomy with wedge or partial gastrectomy was employed in 46.1% of the recorded cases. Due to malignant potential, long-term follow-up and monitoring are usually recommended. Conclusion: Despite the rarity of GGT, they should be included in the differential diagnosis of gastric submucosal tumors, with immunohistochemistry studies playing a major role in the diagnosis. Furthermore, a comprehensive evaluation of the literature in the past eight years was presented in a table.

Large-cell Basaloid Adenocarcinoma of the Lung: A Clinicopathologic Study of 12 Cases of a Distinctive Form of Lung Cancer Often Mistaken for Large-cell Neuroendocrine Carcinoma.

A distinctive form of lung adenocarcinoma that closely mimics large-cell neuroendocrine carcinoma is described. The tumors arose in 6 women and 6 men aged 46-86 years (mean=58.4). They presented as peripheral subpleural masses measuring 2-12cm (mean=6.5cm). Histologically they were characterized by islands or anastomosing and serpiginous strands of large, atypical cells showing striking peripheral palisading of nuclei, with high mitotic activity and prominent comedo-like areas of necrosis. Because of the striking resemblance to neuroendocrine tumors, some of the cases were initially diagnosed as large-cell neuroendocrine carcinoma despite the absence of neuroendocrine markers. Immunohistochemistry showed positivity of the tumor cells for TTF1 and napsin-A, and negative staining for p40. The tumors were also uniformly negative for multiple neuroendocrine markers, including chromogranin, synaptophysin, CD56, and INSM1. Electron microscopy performed in 2 cases was negative for membrane-bound dense core neurosecretory granules. Pathogenic alterations were detected in 5 of 8 tumors tested by next-generation sequencing. Point mutations in KRAS and TP53 were identified in 5 patients. Low-level amplification of GNAS, KIT, and FGFR1 was present in 2 patients. No RB1 mutations were identified. Clinical follow-up in 10 cases showed that 2 patients died of their tumors, 2 experienced distant metastases, and 6 were alive and well from 1 to 13 years after diagnosis (median=7.1y). Large-cell basaloid adenocarcinoma is an unusual variant of lung cancer that is easily confused with large-cell neuroendocrine carcinoma. Awareness of this unusual variant of lung adenocarcinoma is important for treatment and prognosis and for avoiding misdiagnosis.

Should We Rest on a Rest? A Well-Differentiated Neuroendocrine Tumor Arising From Pancreatic Heterotopia.

Should We Rest on a Rest? A Well-Differentiated Neuroendocrine Tumor Arising From Pancreatic Heterotopia.

Personalized oncology in pheochromocytomas and paragangliomas: integrating genetic analysis with machine learning.

Pheochromocytomas and paragangliomas (PCCs/PGLs) are uncommon neuroendocrine tumors with a significant genetic tendency. Approximately 35-40% of these tumors are associated with genetic factors. The present study performed a thorough analysis using publicly accessible genetic and clinical data from the Cancer Genome Atlas (TCGA) to examine the involvement of six genes, namely GBP1, KIF13B, GPT, CSDE1, CEP164, and CLCA1, in the development of PCCs/PGLs. By employing multi-omics data, this study investigates the relationship between mutational patterns and the prognosis of tumors, focusing on the possibility of tailoring treatment methods to individual patients. The study utilizes Mutect2 to detect somatic mutations with high confidence in whole-exome sequencing data from PCCG samples. The study uncovers mild effects on protein function caused by particular mutations, including GBP1 (p.Cys12Tyr), KIF13B (p.Arg847Gly), and GPT (p.Gln50Arg). A random forest classifier uses mutational profiles to predict potential drug recommendations, proposing a focused therapy strategy. This study thoroughly analyzes the genetic mutations found in PCCs/PGLs, highlighting the significance of precision medicine in developing specific treatments for these uncommon types of cancer. This study aims to improve the understanding of the development of tumors and identify personalized treatment approaches by combining genetic data with machine learning analyses.

The current status of somatostatin analogs in the treatment of neuroendocrine tumors and future perspectives.

Somatostatin analogs (SSAs) were developed as antisecretory agents to palliate hormonal symptoms in patients with functioning neuroendocrine tumors (NETs). Their antiproliferative activity has been established in the phase 3 PROMID and CLARINET trials. SSAs currently represent the standard first-line therapy for the majority of well-differentiated G1/G2 gastroenteropancreatic NETs as well as for pulmonary NETs. An update on the clinical applications of established SSAs for the treatment of NETs is provided. Perspectives on emerging nonpeptide SSAs such as paltusotine and innovative formulations of octreotide (CAM2029) are included. SSAs represent the cornerstone of treatment for both functioning and nonfunctioning NETs. While standard-dose SSAs have a defined place in the therapeutic algorithm of well-differentiated NETs, uncertainties remain on how to best integrate above-label doses of SSAs in the treatment sequence, particularly when tumor control is the goal. Octreotide and lanreotide appear to be clinically interchangeable, and no signs of superiority of one agent over the other has been observed so far. Whether SSAs may be exploited in the maintenance setting following more aggressive treatments, whether continuing SSAs beyond-progression after first-line therapy could be an effective treatment strategy, and whether new-generation SSAs such as pasireotide could overcome resistance to established SSAs are key areas of investigation.

A convolutional neural network-based system for identifying neuroendocrine neoplasm and multiple types of lesions in the pancreas via endoscopic ultrasound (with videos)

Background and aimsEndoscopic ultrasound (EUS) is sensitive in detecting pancreatic neuroendocrine neoplasm (pNEN). However, the endoscopic diagnosis of pNEN is operator-dependent and time-consuming since pNEN mimics normal pancreas and other pancreatic lesions. We intended to develop a convolutional neural network (CNN)-based system named iEUS for identifying pNEN and multiple types of pancreatic lesions via EUS. MethodsRetrospective data of 12,200 EUS images obtained from pNEN and non-pNEN pancreatic lesions, including pancreatic ductal adenocarcinoma (PDAC), autoimmune pancreatitis (AIP), and pancreatic cystic neoplasm (PCN), were used to develop iEUS. It was composed of a two-category (pNEN/ non-pNEN pancreatic lesion) classification model (CNN1) and a four-category (pNEN/ PDAC/ AIP/ PCN) classification model (CNN2). Videos from consecutive patients were prospectively collected for a human-iEUS contest to evaluate the performance of iEUS. ResultsA total of 573 patients were enrolled in this study. In the human-iEUS contest containing 203 videos, CNN1 and CNN2 showed an accuracy of 84.2% and 88.2% for diagnosing pNEN, respectively, which were significantly higher than that of novices (75.4%) and comparable with intermediate endosonographers (85.5%) and experts (85.5%). In addition, CNN2 showed an accuracy of 86.2%, 97.0%, and 97.0% for diagnosing PDAC, AIP, and PCN, respectively. With the assistance of iEUS, the sensitivity of endosonographers at all three levels in diagnosing pNEN has significantly improved (64.6% vs. 44.8%, 87.5% vs. 71.9%, 74.0% vs. 57.6%, respectively). ConclusionsThe iEUS precisely diagnosed pNEN and other confusing pancreatic lesions, thus could assist endosonographers in achieving more accessible and accurate endoscopic diagnoses via EUS.

“Pregnancy and neuroendocrine neoplasms: what we know and do not know?”

“Pregnancy and neuroendocrine neoplasms: what we know and do not know?”