Pancreatic neuroendocrine tumours: Grade is superior to T, N, or M status in predicting outcome and selecting patients for chemotherapy:A retrospective cohort study in the SEER database

Machine Learning Methods Based on CT Features Differentiate G1/G2 From G3 Pancreatic Neuroendocrine Tumors

RATIONALE AND OBJECTIVES

To identify CT features for distinguishing grade 1 (G1)/grade 2 (G2) from grade 3 (G3) pancreatic neuroendocrine tumors (PNETs) using different machine learning (ML) methods.

MATERIALS AND METHODS

A total of 147 patients with 155 lesions confirmed by pathology were retrospectively included. Clinical-demographic and radiological CT features was collected. The entire cohort was separated into training and validation groups at a 7:3 ratio. Least absolute shrinkage and selection operator (LASSO) algorithm and principal component analysis (PCA) were used to select features. Three ML methods, namely logistic regression (LR), support vector machine (SVM), and K-nearest neighbor (KNN) were used to build a differential model. Receiver operating characteristic (ROC) curves and precision-recall curves for each ML method were generated. The area under the curve (AUC), accuracy rate, sensitivity, and specificity were calculated.

RESULTS

G3 PNETs were more likely to present with invasive behaviors and lower enhancement than G1/G2 PNETs. The LR classifier yielded the highest AUC of 0.964 (95% confidence interval [CI]: 0.930, 0.972), with 95.4% accuracy rate, 95.7% sensitivity, and 92.9% specificity, followed by SVM (AUC: 0.957) and KNN (AUC: 0.893) in the training group. In the validation group, the SVM classier reached the highest AUC of 0.952 (95% CI: 0.860, 0.981), with 91.5% accuracy rate, 97.3% sensitivity, and 70% specificity, followed by LR (AUC: 0.949) and KNN (AUC: 0.923).

CONCLUSIONS

The LR and SVM classifiers had the best performance in the training group and validation group, respectively. ML method could be helpful in differentiating between G1/G2 and G3 PNETs.

The clinical implication and translational research of OSCC differentiation

BACKGROUND

The clinical value and molecular characteristics of tumor differentiation in oral squamous cell carcinoma (OSCC) remain unclear. There is a lack of a related molecular classification prediction system based on pathological images for precision medicine.

METHODS

Integration of epidemiology, genomics, experiments, and deep learning to clarify the clinical value and molecular characteristics, and develop a novel OSCC molecular classification prediction system.

RESULTS

Large-scale epidemiology data (n = 118,817) demonstrated OSCC differentiation was a significant prognosis indicator (p < 0.001), and well-differentiated OSCC was more chemo-resistant than poorly differentiated OSCC. These results were confirmed in the TCGA database and in vitro. Furthermore, we found chemo-resistant related pathways and cell cycle-related pathways were up-regulated in well- and poorly differentiated OSCC, respectively. Based on the characteristics of OSCC differentiation, a molecular grade of OSCC was obtained and combined with pathological images to establish a novel prediction system through deep learning, named ShuffleNetV2-based Molecular Grade of OSCC (SMGO). Importantly, our independent multi-center cohort of OSCC (n = 340) confirmed the high accuracy of SMGO.

CONCLUSIONS

OSCC differentiation was a significant indicator of prognosis and chemotherapy selection. Importantly, SMGO could be an indispensable reference for OSCC differentiation and assist the decision-making of chemotherapy.

ALKBH5 enhances lipid metabolism reprogramming by increasing stability of FABP5 to promote pancreatic neuroendocrine neoplasms progression in an m6A-IGF2BP2-dependent manner

The process of post-transcriptional regulation has been recognized to be significantly impacted by the presence of N6-methyladenosine (m6A) modification. As an m6A demethylase, ALKBH5 has been shown to contribute to the progression of different cancers by increasing expression of several oncogenes. Hence, a better understanding of the key targets of ALKBH5 in cancer cells could potentially lead to the development of new therapeutic targets. However, the specific role of ALKBH5 in pancreatic neuroendocrine neoplasms (pNENs) remains largely unknown. Here, we demonstrated that ALKBH5 was up-regulated in pNENs and played a critical role in tumor growth and lipid metabolism. Mechanistically, ALKBH5 over-expression was found to increase the expression of FABP5 in an m6A-IGF2BP2 dependent manner, leading to disorders in lipid metabolism. Additionally, ALKBH5 was found to activate PI3K/Akt/mTOR signaling pathway, resulting in enhanced lipid metabolism and proliferation abilities. In conclusion, our study uncovers the ALKBH5/IGF2BP2/FABP5/mTOR axis as a mechanism for aberrant m6A modification in lipid metabolism and highlights a new molecular basis for the development of therapeutic strategies for pNENs treatment.

Predicting the survival of patients with pancreatic neuroendocrine neoplasms using deep learning: A study based on Surveillance, Epidemiology, and End Results database

BACKGROUND

The study aims to evaluate the performance of three advanced machine learning algorithms and a traditional Cox proportional hazard (CoxPH) model in predicting the overall survival (OS) of patients with pancreatic neuroendocrine neoplasms (PNENs).

METHOD

The clinicopathological dataset obtained from the Surveillance, Epidemiology, and End Results database was randomly assigned to the training set and testing set at a ratio of 7:3. The concordance index (C-index) and integrated Brier score (IBS) were used to compare the predictive performance of the models. The accuracy of the model in predicting the 5-year and 10-year survival rates was compared using the receiver operating characteristic curve, decision curve analysis (DCA) and calibration curve.

RESULTS

This study included 3239 patients with PNENs in total. The DeepSurv model had the highest C-index of 0.7882 in the testing set and training set and the lowest IBS of 0.1278 in the testing set compared with the CoxPH, neural multitask logistic and random survival forest models (C-index = 0.7501, 0.7616, and 0.7612, respectively; IBS = 0.1397, 0.1418, and 0.1432, respectively). Moreover, the DeepSurv model had the highest accuracy in predicting 5- and 10-year OS rates (area under the curve: 0.87 and 0.90). DCA showed that the DeepSurv model had high potential for clinical decisions in 5- and 10-year OS models. Finally, we developed an online application based on the DeepSurv model for clinical use (https://whuh-ml-neuroendocrinetumor-app-predict-oyw5km.streamlit.app/).

CONCLUSIONS

All four models analyzed above can predict the prognosis of PNENs well, among which the DeepSurv model has the best prediction performance.

Surgical options for the treatment of neuroendocrine neoplasms of the ampulla of Vater: a reference centre experience

INTRODUCTION

The main objective of this study was to analyse the results of the surgical treatment of ampullary neuroendocrine tumours (NET) based on transduodenal ampullectomy and pancreatoduodenectomy, in a reference centre in hepatobiliopancreatic pathology.

METHOD

Retrospective, observational study, including all patients operated on for pancreatic and/or duodenal NET in a reference unit of hepatobiliopancreatic pathology and prospectively registered between January 1st, 1993 and September 30th, 2021. For those parameters not present, retrospective research was performed. Demographic, clinical, analytical and pathological data were analysed. A descriptive study was carried out. Overall and disease-free survival was calculated using Kaplan-Meier curves and the Log-Rank test.

RESULTS

Of 181 patients operated on for pancreatic and/or duodenal NET, only 9 were located in the ampulla of Vater, which represents 4.9% of all pancreatic and/or duodenal NET. Pancreatoduodenectomy (PD) was performed in 6 patients, while 3 patients underwent transduodenal ampullectomy (TDA). Longer surgical time and more postoperative complications were observed in the PD group. There were no differences in hospital stay. Overall and disease-free survival at 5 years in the PD group compared to ATD was 83.3% vs. 100% and 50% vs. 100%, respectively.

CONCLUSIONS

Ampullary NET without locoregional involvement or risk factors, can be treated by conservative surgeries such as transduodenal ampullectomy.

DNA methylation reveals distinct cells of origin for pancreatic neuroendocrine carcinomas and pancreatic neuroendocrine tumors

Background

Pancreatic neuroendocrine neoplasms (PanNENs) fall into two subclasses: the well-differentiated, low- to high-grade pancreatic neuroendocrine tumors (PanNETs), and the poorly-differentiated, high-grade pancreatic neuroendocrine carcinomas (PanNECs). While recent studies suggest an endocrine descent of PanNETs, the origin of PanNECs remains unknown.

Methods

We performed DNA methylation analysis for 57 PanNEN samples and found that distinct methylation profiles separated PanNENs into two major groups, clearly distinguishing high-grade PanNECs from other PanNETs including high-grade NETG3. DNA alterations and immunohistochemistry of cell-type markers PDX1, ARX, and SOX9 were utilized to further characterize PanNECs and their cell of origin in the pancreas.

Results

Phylo-epigenetic and cell-type signature features derived from alpha, beta, acinar, and ductal adult cells suggest an exocrine cell of origin for PanNECs, thus separating them in cell lineage from other PanNENs of endocrine origin.

Conclusions

Our study provides a robust and clinically applicable method to clearly distinguish PanNECs from G3 PanNETs, improving patient stratification.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13073-022-01018-w.

Predictive Factors for Resistant Disease with Medical/Radiologic/Liver-Directed Anti-Tumor Treatments in Patients with Advanced Pancreatic Neuroendocrine Neoplasms: Recent Advances and Controversies

Simple Summary

Tumor resistance, both primary and acquired, is leading to increased complexity in the nonsurgical treatment of patients with advanced panNENs, which would be greatly helped by reliable prognostic/predictive factors. The importance in identifying resistance is being contributed to by the increased array of possible treatments available for treating resistant advanced disease; the variable clinical course as well as response to any given treatment approach of patients within one staging or grading system, the advances in imaging which are providing increasing promising results/parameters that correlate with grading/outcome/resistance, the increased understanding of the molecular pathogenesis providing promising prognostic markers, all of which can contribute to selecting the best treatment to overcome resistance disease. Several factors have been identified that have prognostic/predictive value for identifying development resistant disease and affecting overall survival (OS)/PFS with various nonsurgical treatments of patients with advanced panNENs. Prognostic factors identified for patients with advanced panNENs for both OS/PFSs include various clinically-related factors (clinical, laboratory/biological markers, imaging, treatment-related factors), pathological factors (histological, classification, grading) and molecular factors. Particularly important prognostic factors for the different treatment modalities studies are the recent grading systems. Most prognostic factors for each treatment modality for OS/PFS are not specific for a given treatment option. These advances have generated several controversies and new unanswered questions, particularly those related to their possible role in predicting the possible sequence of different anti-tumor treatments in patients with different presentations. Each of these areas is reviewed in this paper.

Abstract

Purpose: Recent advances in the diagnosis, management and nonsurgical treatment of patients with advanced pancreatic neuroendocrine neoplasms (panNENs) have led to an emerging need for sensitive and useful prognostic factors for predicting responses/survival. Areas covered: The predictive value of a number of reported prognostic factors including clinically-related factors (clinical/laboratory/imaging/treatment-related factors), pathological factors (histological/classification/grading), and molecular factors, on therapeutic outcomes of anti-tumor medical therapies with molecular targeting agents (everolimus/sunitinib/somatostatin analogues), chemotherapy, radiological therapy with peptide receptor radionuclide therapy, or liver-directed therapies (embolization/chemoembolization/radio-embolization (SIRTs)) are reviewed. Recent findings in each of these areas, as well as remaining controversies and uncertainties, are discussed in detail, particularly from the viewpoint of treatment sequencing. Conclusions: The recent increase in the number of available therapeutic agents for the nonsurgical treatment of patients with advanced panNENs have raised the importance of prognostic factors predictive for therapeutic outcomes of each treatment option. The establishment of sensitive and useful prognostic markers will have a significant impact on optimal treatment selection, as well as in tailoring the therapeutic sequence, and for maximizing the survival benefit of each individual patient. In the paper, the progress in this area, as well as the controversies/uncertainties, are reviewed.

Trends in Incidence and Survival of Patients with Pancreatic Neuroendocrine Neoplasm, 1987-2016

Background

Pancreatic neuroendocrine neoplasm (pNEN), with the lowest 5-year survival rates in neuroendocrine tumors (NETs), exerts great threat to human health. Because large-scale population research aimed at pNEN is rare, we aimed to explore the tendencies and differences of changes in incidences and survival rates of pNEN in each decade from 1987 to 2016 and evaluate the impacts of age, sex, race, socioeconomic status (SES), and grade.

Methods

Data on pNEN cases from 1987 to 2016 were extracted from the Surveillance, Epidemiology, and End Results Program (SEER) database. Kaplan-Meier, Cox proportional hazards regression analyses, and relative survival rates (RSRs) were used to identify risk factors for pNEN.

Results

The incidence and survival duration of pNEN increase every decade due to medical developments. The disparities of long-term survival in different age, sex, and grade groups expanded over time while that in race and SES groups narrowed. Older age and higher grade are independent risk factors for poorer survival. Females have lower incidence and longer survival than males. Prognosis of Black patients and poor (medium and high poverty) patients improved.

Conclusions

This study depicted changes in incidence and survival rates of pNEN over the past three decades and evaluated potential risk factors related to pNEN, benefiting future prediction of vulnerable and clinical options.

The overriding role of surgery and tumor grade for long-term survival in patients with gastroenteropancreatic neuroendocrine neoplasms: A population-based cohort study

Background

Gastroenteropancreatic neuroendocrine neoplasms (GEP‐NENs) comprise a heterogeneous disease group. Factors that affect long‐term survival remain uncertain. Complete population‐representative cohorts with long‐term follow‐up are scarce.

Aim

To evaluate factors of importance for the long‐term survival.

Methods and results

An Observational population‐based study on consecutive GEP‐NEN patients diagnosed from 2003 to 2013, managed according to national guidelines. Univariable and multivariable survival analyses were performed to evaluate overall survival (OS) and to identify independent prognostic factors. One hundred ninety eligible patients (males, 58.9%) (median age, 60.0 years; range, 10.0–94.2 years) were included. The small bowel, appendix, and pancreas were the most common tumor locations. The World Health Organization (WHO) tumor grade 1–3 distributions varied according to the primary location and disease stage. Primary surgery with curative intent was performed in 66% of the patients. The median OS of the study population was 183 months with 5‐ and 10‐year OS rates of 66% and 57%, respectively. Only age, WHO tumor grade, and primary surgical treatment were independent prognostic factors for OS.

Conclusion

The outcomes of GEP‐NEN patients are related to several factors including age and primary surgical treatment. WHO tumor grading, based on the established criteria, should be routine in clinical practice. This may improve clinical decision‐making and allow the comparison of outcomes among different centers.

Development and comparison of novel bioluminescent mouse models of pancreatic neuroendocrine neoplasm metastasis

Pancreatic neuroendocrine neoplasms (pNENs) are slow growing cancers of increasing incidence that lack effective treatments once they become metastatic. Unfortunately, nearly half of pNEN patients present with metastatic liver tumors at diagnosis and current therapies fail to improve overall survival. Pre-clinical models of pNEN metastasis are needed to advance our understanding of the mechanisms driving the metastatic process and for the development of novel, targeted therapeutic interventions. To model metastatic dissemination of tumor cells, human pNEN cell lines (BON1 and Qgp1) stably expressing firefly luciferase (luc) were generated and introduced into NSG immunodeficient mice by intracardiac (IC) or intravenous (IV) injection. The efficiency, kinetics and distribution of tumor growth was evaluated weekly by non-invasive bioluminescent imaging (BLI). Tumors formed in all animals in both the IC and IV models. Bioluminescent Qgp1.luc cells preferentially metastasized to the liver regardless of delivery route, mimicking the predominant site of pNEN metastasis in patients. By comparison, BON1.luc cells most commonly formed lung tumors following either IV or IC administration and colonized a wider variety of tissues than Qgp1.luc cells. These models provide a unique platform for testing candidate metastasis genes and anti-metastatic therapies for pNENs.

Pancreatic neuroendocrine tumors: Surgical outcomes and survival analysis

BACKGROUND

Pancreatic neuroendocrine tumors are rare, with rising incidence and limited clinicopathological studies.

METHODS

Adult patients with pNET at a single tertiary care center were retrospectively evaluated.

RESULTS

In total, 87 patients with histologically confirmed pNET who underwent resection were evaluated. 11% of patients had functioning pNETs: 9 insulinoma and 1 VIPoma. The majority (88.5%) were nonfunctioning. The most common surgical procedure performed was distal pancreatectomy with splenectomy (36.8%). 35.6% of cases were performed with minimally invasive surgery (MIS). MIS patients had fewer postoperative complications, shorter length of stay, and fewer ICU admissions.Disease-free survival (DFS) was unaffected by tumor size (p = 0.5) or lymph node status (p = 0.62). Patients with high-grade (G3) tumors experienced significantly shorter DFS (p = 0.02).

CONCLUSIONS

This series demonstrates that survival in patients with pNET is driven mostly by tumor grade, though overall most have long-term survival after surgical resection. Additionally, an MIS approach is efficacious in appropriately selected cases.

Pancreatic Cancer Imaging: A New Look at an Old Problem

Computed tomography is the most commonly used imaging modality to detect and stage pancreatic cancer. Previous advances in pancreatic cancer imaging have focused on optimizing image acquisition parameters and reporting standards. However, current state-of-the-art imaging approaches still misdiagnose some potentially curable pancreatic cancers and do not provide prognostic information or inform optimal management strategies beyond stage. Several recent developments in pancreatic cancer imaging, including artificial intelligence and advanced visualization techniques, are rapidly changing the field. The purpose of this article is to review how these recent advances have the potential to revolutionize pancreatic cancer imaging.

A prognostic nomogram in patients with distant metastasis of pancreatic neuroendocrine tumors: a population-based study

Aim: Prognostic factors in patients with distant metastatic pancreatic neuroendocrine tumors (PNETs) remain uncertain. The purpose of our study is to establish a nomogram to predict survival outcomes in patients with metastatic PNETs. Methods: A total of 878 patients diagnosed with PNETs in the Surveillance, Epidemiology and End Results database between 2004 and 2016 were retrospectively identified. The Kaplan-Meier survival analysis with log-rank test was used to analyze survival outcomes. The nomogram was established after a univariate and multivariate Cox analysis. Results: The independent prognostic variables, including age, tumor grade and primary site surgery were applied to develop a nomogram. The original concordance index was 0.773 (95% CI: 0.751-0.795), and the bias-corrected concordance index was 0.769 (95% CI: 0.748-0.791). The internal calibration curves showed well consistency and veracity in predicting cancer-specific survival probabilities. Conclusion: A nomogram was constructed and verified to predict survival outcomes in patients with distant-stage PNETs.