Grading Of Pancreatic Neuroendocrine Tumors Research Articles

S1614 Grading of Pancreatic Neuroendocrine Tumors by EUS FNA/FNB: A Tertiary Care Center Experience

S1614 Grading of Pancreatic Neuroendocrine Tumors by EUS FNA/FNB: A Tertiary Care Center Experience

Comparison of endoscopic ultrasound fine needle aspiration (FNA) vs fine needle biopsy (FNB) for preoperative grading of pancreatic neuroendocrine tumors: A systematic review and meta-analysis

Comparison of endoscopic ultrasound fine needle aspiration (FNA) vs fine needle biopsy (FNB) for preoperative grading of pancreatic neuroendocrine tumors: A systematic review and meta-analysis

C1QA and COMP: plasma-based biomarkers for early diagnosis of pancreatic neuroendocrine tumors

Pancreatic Neuroendocrine tumors (PanNET) are challenging to diagnose and often detected at advanced stages due to a lack of specific and sensitive biomarkers. This study utilized proteomics as a valuable approach for cancer biomarker discovery; therefore, mass spectrometry-based proteomic profiling was conducted on plasma samples from 12 subjects (3 controls; 5 Grade I, 4 Grade II PanNET patients) to identify potential proteins capable of effectively distinguishing PanNET from healthy controls. Data are available via ProteomeXchange with the identifier PXD045045. 13.2% of proteins were uniquely identified in PanNET, while 60% were commonly expressed in PanNET and controls. 17 proteins exhibiting significant differential expression between PanNET and controls were identified with downstream analysis. Further, 5 proteins (C1QA, COMP, HSP90B1, ITGA2B, and FN1) were selected by pathway analysis and were validated using Western blot analysis. Significant downregulation of C1QA (p = 0.001: within groups, 0.03: control vs. grade I, 0.0013: grade I vs. grade II) and COMP (p = 0.011: within groups, 0.019: control vs grade I) were observed in PanNET Grade I & II than in controls. Subsequently, ELISA on 38 samples revealed significant downregulation of C1QA and COMP with increasing disease severity. This study shows the potential of C1QA and COMP in the early detection of PanNET, highlighting their role in the search for early-stage (Grade-I and Grade-II) diagnostic markers and therapeutic targets for PanNET.

Assessing the Relationship between Gastrointestinal and Pancreatic Neuroendocrine Tumor Grade and Overall Survival: A Systematic Review and Meta-Analysis

Background: Neuroendocrine tumors (NET) are a rare group of epithelial neoplasms present in the gastrointestinal tract (GI) (67.5%) and bronchopulmonary tree (25.3–30%), and in 15% of cases, their primary sites cannot be identified. Although endoscopic screening, improvements in pathological techniques, and early detection have shown improvements in NET survival rates, the prognosis of advanced, metastatic, and poorly differentiated NET is very poor. In this study, we aimed to evaluate the effect of gastrointestinal and pancreatic (GEPs) NETs’ grade on overall survival. Method: We searched observational studies describing the overall survival or prognostic factors of primary GEP NETs from May 2011–May 2021 following the PRISMA guidelines. Studies describing the effect of primary grade 3 GEP NETs on overall survival were included. A meta-analysis was performed, and a pooled hazard ratio and their 95% confidence interval (95% CI) were obtained. Forest plots were created using random effects models and a sensitivity analysis was performed to account for the heterogeneity. Results: Seven studies with 7692 confirmed patients were included. In our meta-analysis, grade 3 GEP NETs were associated with higher odds of poor survival (pooled HR: 2.73; 95% CI: 1.36–5.47; p = 0.005), with a 92% heterogeneity between studies (p < 0.0001). To account for this heterogeneity, a sensitivity analysis was performed by removing two outlying studies (Fathi et al. and Foubert et al.) on funnel plots. The results after the sensitivity analysis did not change and still showed a significant association of grade 3 with a poor survival (pooled HR: 4.53; 95% CI: 3.54–5.78; p < 0.00001), with no heterogeneity between studies (p = 0.72; I2 = 0%). Conclusions: Our meta-analysis found that grade 3 GEP NETs are associated with poor survival and additional future studies are needed to identify other risk factors associated with poor survival in GEP NETs to improve their mortality.

Preoperative prediction of pancreatic neuroendocrine tumor grade based on 68Ga-DOTATATE PET/CT

ObjectiveTo establish a prediction model for preoperatively predicting grade 1 and grade 2/3 tumors in patients with pancreatic neuroendocrine tumors (PNETs) based on 68Ga-DOTATATE PET/CT.MethodsClinical data of 41 patients with PNETs were included in this study. According to the pathological results, they were divided into grade 1 and grade 2/3. 68Ga-DOTATATE PET/CT images were collected within one month before surgery. The clinical risk factors and significant radiological features were filtered, and a clinical predictive model based on these clinical and radiological features was established. 3D slicer was used to extracted 107 radiomic features from the region of interest (ROI) of 68Ga-dotata PET/CT images. The Pearson correlation coefficient (PCC), recursive feature elimination (REF) based five-fold cross validation were adopted for the radiomic feature selection, and a radiomic score was computed subsequently. The comprehensive model combining the clinical risk factors and the rad-score was established as well as the nomogram. The performance of above clinical model and comprehensive model were evaluated and compared.ResultsAdjacent organ invasion, N staging, and M staging were the risk factors for PNET grading (p < 0.05). 12 optimal radiomic features (3 PET radiomic features, 9 CT radiomic features) were screen out. The clinical predictive model achieved an area under the curve (AUC) of 0.785. The comprehensive model has better predictive performance (AUC = 0.953).ConclusionWe proposed a comprehensive nomogram model based on 68Ga-DOTATATE PET/CT to predict grade 1 and grade 2/3 of PNETs and assist personalized clinical diagnosis and treatment plans for patients with PNETs.

A radiomics-based interpretable model to predict the pathological grade of pancreatic neuroendocrine tumors

ObjectivesTo develop a computed tomography (CT) radiomics-based interpretable machine learning (ML) model to predict the pathological grade of pancreatic neuroendocrine tumors (pNETs) in a non-invasive manner.MethodsPatients with pNETs who underwent contrast-enhanced abdominal CT between 2010 and 2022 were included in this retrospective study. Radiomics features were extracted, and five radiomics-based ML models, namely logistic regression (LR), random forest (RF), support vector machine (SVM), XGBoost, and GaussianNB, were developed. The performance of these models was evaluated using a time-independent testing set, and metrics such as sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC) were calculated. The accuracy of the radiomics model was compared to that of needle biopsy. The Shapley Additive Explanation (SHAP) tool and the correlation between radiomics and biological features were employed to explore the interpretability of the model.ResultsA total of 122 patients (mean age: 50 ± 14 years; 53 male) were included in the training set, whereas 100 patients (mean age: 48 ± 13 years; 50 male) were included in the testing set. The AUCs for LR, SVM, RF, XGBoost, and GaussianNB were 0.758, 0.742, 0.779, 0.744, and 0.745, respectively, with corresponding accuracies of 73.0%, 70.0%, 77.0%, 71.9%, and 72.9%. The SHAP tool identified two features of the venous phase as the most significant, which showed significant differences among the Ki-67 index or mitotic count subgroups (p < 0.001).ConclusionsAn interpretable radiomics-based RF model can effectively differentiate between G1 and G2/3 of pNETs, demonstrating favorable interpretability.Clinical relevance statementThe radiomics-based interpretable model developed in this study has significant clinical relevance as it offers a non-invasive method for assessing the pathological grade of pancreatic neuroendocrine tumors and holds promise as an important complementary tool to traditional tissue biopsy.Key Points• A radiomics-based interpretable model was developed to predict the pathological grade of pNETs and compared with preoperative needle biopsy in terms of accuracy.• The model, based on CT radiomics, demonstrated favorable interpretability.• The radiomics model holds potential as a valuable complementary technique to preoperative needle biopsy; however, it should not be considered a replacement for biopsy.

The Ki67 index evaluation of pancreatic neuroendocrine tumors using 3D immunohistochemistry in small tissue specimens

Background/Objectives: This study aimed to evaluate the usefulness of three-dimensional (3D) immunohistochemistry for the Ki67 index of small tissue specimens of pancreatic neuroendocrine tumor (PanNET). MethodsClinicopathological materials from 17 patients with PanNET who underwent surgical resection at Jichi Medical University Hospital were analyzed. We compared the Ki67 index of endoscopic ultrasonography-fine-needle aspiration biopsy (EUS-FNAB) specimens, surgical specimens, and small tissue specimens hollowed from paraffin blocks of surgical specimens that were substituted for EUS-FNAB specimens (“sub-FNAB”). The sub-FNAB specimens were optically cleared using LUCID (IlLUmination of Cleared organs to IDentify target molecules) and analyzed using 3D immunohistochemistry. ResultsThe median Ki67 index in FNAB, sub-FNAB, and surgical specimens with conventional immunohistochemistry were 1.2% (0.7–5.0), 2.0% (0.5–14.6), and 5.4% (1.0–19.4), respectively. The median Ki67 index in sub-FNAB specimens with tissue clearing was calculated separately using the total number of cells on multiple images (“multiple slice”), with the image of the fewest positive cells (“coldspot”), and with the image of most positive cells (“hotspot”), which were 2.7% (0.2–8.2), 0.8% (0–4.8), and 5.5% (2.3–12.4), respectively. PanNET grade evaluated for the hotspot of the surgical specimens was significantly more consistent with those of the hotspot than multiple images of sub-FNAB specimens (16/17 vs. 10/17, p = 0.015). Hotspot evaluation using 3D immunohistochemistry of the sub-FNAB specimens showed agreement with the assessment of the surgical specimens (Kappa coefficient: 0.82). ConclusionsTissue clearing and 3D immunohistochemistry for the Ki67 index can potentially improve the preoperative evaluation of EUS-FNAB specimens of PanNET in routine clinical practice.

A Lymph Node Ratio Model for Prognosis of Patients with Pancreatic Neuroendocrine Tumors

The objective of this study was to determine the prognostic value of lymph node (LN) involvement and the LN ratio (LNR) and their effect on recurrence rates and survival in patients with pancreatic neuroendocrine tumors (PNETs) undergoing surgery. This single-center retrospective study reviewed the medical records of 95 consecutive patients diagnosed with PNETs who underwent surgery at our medical center between 1997 and 2017. The retrieved information included patient demographics, pathology reports, treatments, and oncological outcomes. Results: 95 consecutive potentially suitable patients were identified. The 78 patients with PNETs who underwent surgery and for whom there was adequate data were included in the analysis. Their mean ± standard deviation age at diagnosis was 57.4 ± 13.4 years (range 20-82), and there were 50 males (64%) and 28 females (36%). 23 patients (30%) had LN metastases (N1). The 2.5- and 5-year disease-free survival (DFS) rates for the entire cohort were 79.5% and 71.8%, respectively, and their 2- and 5-year overall survival (OS) rates were 85.9% and 82.1%, respectively. The optimal value of the LNR was 0.1603, which correlated with the outcome (2-year OS p = 0.002 HR = 13.4 and 5-year DFS p = 0.016 HR = 7.2, respectively, and 5-year OS and 5-year DFS p = 0.004 HR = 9 and p = 0.001 HR = 10.6, respectively). However, the multivariate analysis failed to show that the LNR was an independent prognostic factor in PNETs. Patients with PNETs grade and stage are known key prognostic factors influencing OS and DFS. According to our results, LNR failed to be an independent prognostic factor.

Prediction of Pathological Grades of Pancreatic Neuroendocrine Tumors Based on Dynamic Contrast-Enhanced Ultrasound Quantitative Analysis.

To investigate whether the dynamic contrast-enhanced ultrasound (DCE-US) analysis and quantitative parameters could be helpful for predicting histopathologic grades of pancreatic neuroendocrine tumors (pNETs). This retrospective study conducted a comprehensive review of the CEUS database between March 2017 and November 2021 in Zhongshan Hospital, Fudan University. Ultrasound examinations were performed by an ACUSON Sequioa unit equipped with a 3.5 MHz 6C-1 convex array transducer, and an ACUSON OXANA2 unit equipped with a 3.5 MHz 5C-1 convex array transducer. SonoVue® (Bracco Inc., Milan, Italy) was used for all CEUS examinations. Time intensity curves (TICs) and quantitative parameters of DCE-US were created by Vuebox® software (Bracco, Italy). Inclusion criteria were: patients with histopathologically proved pNETs, patients who underwent pancreatic B-mode ultrasounds (BMUS) and CEUS scans one week before surgery or biopsy and had DCE-US imaging documented for more than 2 min, patients with solid or predominantly solid lesions and patients with definite diagnosis of histopathological grades of pNETs. Based on their prognosis, patients were categorized into two groups: pNETs G1/G2 group and pNETs G3/pNECs group. A total of 42 patients who underwent surgery (n = 38) or biopsy (n = 4) and had histopathologically confirmed pNETs were included. According to the WHO 2019 criteria, all pNETs were classified into grade 1 (G1, n = 10), grade 2 (G2, n = 21), or grade 3 (G3)/pancreatic neuroendocrine carcinomas (pNECs) (n = 11), based on the Ki-67 proliferation index and the mitotic activity. The majority of the TICs (27/31) of pNETs G1/G2 were above or equal to those of pancreatic parenchyma in the arterial phase, but most (7/11) pNETs G3/pNECs had TICs below those of pancreatic parenchyma from arterial phase to late phase (p &lt; 0.05). Among all the CEUS quantitative parameters of DCE-US, values of relative rise time (rPE), relative mean transit time (rmTT) and relative area under the curve (rAUC) were significantly higher in pNETs G1/G2 group than those in pNETs G3/pNECs group (p &lt; 0.05). Taking an rPE below 1.09 as the optimal cut-off value, the sensitivity, specificity and accuracy for prediction of pNETs G3/pNECs from G1/G2 were 90.91% [58.70% to 99.80%], 67.64% [48.61% to 83.32%] and 85.78% [74.14% to 97.42%], respectively. Taking rAUC below 0.855 as the optimal cut-off value, the sensitivity, specificity and accuracy for prediction of pNETs G3/pNECs from G1/G2 were 90.91% [66.26% to 99.53%], 83.87% [67.37% to 92.91%] and 94.72% [88.30% to 100.00%], respectively. Dynamic contrast-enhanced ultrasound analysis might be helpful for predicting the pathological grades of pNETs. Among all quantitative parameters, rPE, rmTT and rAUC are potentially useful parameters for predicting G3/pNECs with aggressive behavior.

Contrast Enhanced EUS for Predicting Solid Pancreatic Neuroendocrine Tumor Grade and Aggressiveness.

Pancreatic neuroendocrine tumor (PNET) behavior assessment is a daily challenge for physicians. Modern PNET management varies from a watch-and-wait strategy to surgery depending on tumor aggressiveness. Therefore, the aggressiveness definition plays a pivotal role in the PNET work-up. The aggressiveness of PNETs is mainly based on the dimensions and histological grading, with sometimes a lack of specificity and sensibility. In the last twenty years, EUS has become a cornerstone in the diagnostic phase of PNET management for its high diagnostic yield and the possibility of obtaining a histological specimen. The number of EUS applications in the PNET work-up has been rapidly increasing with new and powerful possibilities. The application of contrast has led to an important step in PNET detection; in recent years, it has been gaining interesting applications in aggressiveness assessment. In this review, we underline the latest experiences and opportunities in the behavior assessment of PNETs using contact-enhanced EUS and contested enhanced harmonic EUS with a particular focus on the future application and possibility that these techniques could provide.

Endoscopic ultrasound-guided side-fenestrated needle biopsy sampling is sensitive for pancreatic neuroendocrine tumors but inadequate for tumor grading: a prospective study

Accurate pretreatment grading of pancreatic neuroendocrine tumors (PanNETs) is important to guide patient management. We aimed to evaluate endoscopic ultrasound-guided fine needle biopsy sampling (EUS-FNB) for the preoperative diagnosis and grading of PanNETs. In a tertiary-center setting, patients with suspected PanNETs were prospectively subjected to 22-gauge, reverse-bevel EUS-FNB. The EUS-FNB samples (Ki-67EUS) and corresponding surgical specimens (Ki-67SURG) were analyzed with Ki-67 indexing and thereafter tumor grading, (GRADEEUS) and (GRADESURG) respectively. In total 52 PanNET-patients [median age: 66 years; females: 25/52; surgical resection 22/52 (42%)] were included. EUS-FNB was diagnostic in 44/52 (85%). In 42 available FNB-slides, the median neoplastic cell count was 1034 (IQR: 504–3667) with 32/42 (76%), 22/42 (52%), and 14/42 (33%) cases exceeding 500, 1000, and 2000 neoplastic cells respectively. Ki-67SURG was significantly higher compared to Ki-67EUS with a moderate correlation comparing Ki-67EUS and Ki-67SURG (Pearson r = 0.60, r2 = 0.36, p = 0.011). The GRADEEUS had a weak level of agreement (κ = 0.08) compared with GRADESURG. Only 2/12 (17%) G2-tumors were correctly graded in EUS-FNB-samples. EUS-guided fine needle biopsy sampling is sensitive for preoperative diagnosis of PanNET but biopsy quality is relatively poor. Therefore, the approach seems suboptimal for pretreatment grading of PanNET.

Development and Validation of a Novel Radiomics-Based Nomogram With Machine Learning to Preoperatively Predict Histologic Grade in Pancreatic Neuroendocrine Tumors.

BackgroudTumor grade is the determinant of the biological aggressiveness of pancreatic neuroendocrine tumors (PNETs) and the best current tool to help establish individualized therapeutic strategies. A noninvasive way to accurately predict the histology grade of PNETs preoperatively is urgently needed and extremely limited.MethodsThe models training and the construction of the radiomic signature were carried out separately in three-phase (plain, arterial, and venous) CT. Mann–Whitney U test and least absolute shrinkage and selection operator (LASSO) were applied for feature preselection and radiomic signature construction. SVM-linear models were trained by incorporating the radiomic signature with clinical characteristics. An optimal model was then chosen to build a nomogram.ResultsA total of 139 PNETs (including 83 in the training set and 56 in the independent validation set) were included in the present study. We build a model based on an eight-feature radiomic signature (group 1) to stratify PNET patients into grades 1 and 2/3 groups with an AUC of 0.911 (95% confidence intervals (CI), 0.908–0.914) and 0.837 (95% CI, 0.827–0.847) in the training and validation cohorts, respectively. The nomogram combining the radiomic signature of plain-phase CT with T stage and dilated main pancreatic duct (MPD)/bile duct (BD) (group 2) showed the best performance (training set: AUC = 0.919, 95% CI = 0.916–0.922; validation set: AUC = 0.875, 95% CI = 0.867–0.883).ConclusionsOur developed nomogram that integrates radiomic signature with clinical characteristics could be useful in predicting grades 1 and 2/3 PNETs preoperatively with powerful capability.

Application of CT Imaging in Differential Diagnosis and Nursing of Endocrine Tumors.

In order to investigate the value of preoperative X-ray computed tomography (CT) in predicting the pathological grade of pancreatic neuroendocrine tumors. This paper retrospectively analyzed the CT image examination of pancreatic neuroendocrine tumors, the image characteristics of G-NEC detected by CT image, and the detection of GST by spiral CT. In order to clearly diagnose and evaluate the size and scope of the focus, whether there is adjacent tissue invasion, metastasis, and treatment effect, CT, MR, PET-CT, nuclide specific imaging, and other imaging methods are widely used in the medical treatment of pNEN patients. These imaging methods have the advantages of noninvasive, rapid imaging, objective image medium, and strong repeatability. If the pathological grade of pNEN patients can be obtained by imaging examination before operation, it will be of great benefit to the formulation of treatment strategies and the prediction of clinical outcomes. Combining CT image performance with imaging omics characteristics to establish a prediction model that can develop a better auxiliary decision-making tool for clinical practice. Different pathological grades prompt clinicians to provide personalized and accurate medical treatment for patients, and reduce excessive medical treatment or wrong judgment caused by unclear preoperative diagnostic information.

Quantitative Computed Tomography Image Analysis to Predict Pancreatic Neuroendocrine Tumor Grade.

The therapeutic management of pancreatic neuroendocrine tumors (PanNETs) is based on pathological tumor grade assessment. A noninvasive imaging method to grade tumors would facilitate treatment selection. This study evaluated the ability of quantitative image analysis derived from computed tomography (CT) images to predict PanNET grade. Institutional database was queried for resected PanNET (2000-2017) with a preoperative arterial phase CT scan. Radiomic features were extracted from the primary tumor on the CT scan using quantitative image analysis, and qualitative radiographic descriptors were assessed by two radiologists. Significant features were identified by univariable analysis and used to build multivariable models to predict PanNET grade. Overall, 150 patients were included. The performance of models based on qualitative radiographic descriptors varied between the two radiologists (reader 1: sensitivity, 33%; specificity, 66%; negative predictive value [NPV], 63%; and positive predictive value [PPV], 37%; reader 2: sensitivity, 45%; specificity, 70%; NPV, 72%; and PPV, 47%). The model based on radiomics had a better performance predicting the tumor grade with a sensitivity of 54%, a specificity of 80%, an NPV of 81%, and a PPV of 54%. The inclusion of radiomics in the radiographic descriptor models improved both the radiologists' performance. CT quantitative image analysis of PanNETs helps predict tumor grade from routinely acquired scans and should be investigated in future prospective studies.

Generalized methodology for radiomic feature selection and modeling in predicting clinical outcomes

Background. Quantitative radiomic features of medical images could provide clinical significance in assisting decision-making, but the existing feature selection and modeling methods are usually parameter-dependent. We aim to develop and validate a generalized radiomic method applicable to a variety of clinical outcomes. Methods and materials. A generalized methodology for radiomic feature selection and modeling (‘GRFM’ for short), including two-step feature selection and logistic regression, was proposed for studying clinical outcomes correlations. The two-step feature selection consists of Pearson correlation analysis followed by a sequential forward floating selection algorithm to identify robust feature subsets. We also applied an adaptive searching strategy to systematically determine globally optimal parameters, rather than relying on preset parameters. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of three outcomes: lymph node metastasis of gastric cancer (GC), the five-year survival status of high-grade osteosarcoma (HOS), and the pathological grade of pancreatic neuroendocrine tumors (pNETs). Results. The optimal Pearson thresholds were 0.85, 0.80 and 0.75, and the optimal feature numbers were 11, 14 and 8 in GC, HOS and pNETs, respectively. The AUC values of the three predictive models combined with the corresponding parameters were 0.9017 versus 0.9026, 0.7652 versus 0.7113, and 0.8438 versus 0.8212 for the training and validation cohorts, showing promissing generality and classifier performance . Conclusion. The proposed method was helpful in predicting different clinical outcomes, and has potential application as a general and noninvasive prediction tool to guide clinical decision-making in various cancer sites.

Radiomics analysis combining unsupervised learning and handcrafted features: A multiple-disease study.

To study and investigate the synergistic benefit of incorporating both conventional handcrafted and learning-based features in disease identification across a wide range of clinical setups. In this retrospective study, we collected 170, 150, 209, and 137 patients with four different disease types associated with identification objectives : Lymph node metastasis status of gastric cancer (GC), 5-year survival status of patients with high-grade osteosarcoma (HOS), early recurrence status of intrahepatic cholangiocarcinoma (ICC), and pathological grades of pancreatic neuroendocrine tumors (pNETs). Computed tomography (CT) and magnetic resonance imaging (MRI) were used to derive image features for GC/HOS/pNETs and ICC, respectively. In each study, 67 universal handcrafted features and study-specific features based on the sparse autoencoder (SAE) method were extracted and fed into the subsequent feature selection and learning model to predict the corresponding disease identification. Models using handcrafted alone, SAE alone, and hybrid features were optimized and their performance was compared. Prominent features were analyzed both qualitatively and quantitatively to generate study-specific and cross-study insight. In addition to direct performance gain assessment, correlation analysis was performed to assess the complementarity between handcrafted features and SAE features. On the independent hold-off test, the handcrafted, SAE, and hybrid features based prediction yielded area under the curve of 0.761versus 0.769versus 0.829 for GC, 0.629versus 0.740versus 0.709 for HOS, 0.717versus 0.718versus 0.758 for ICC, and 0.739versus 0.715versus 0.771 for pNETs studies, respectively. In three out of the four studies, prediction using the hybrid features yields the best performance, demonstrating the general benefit in using hybrid features. Prediction with SAE features alone had the best performance in the HOS study, which may be explained by the complexity of HOS prognosis and the possibility of a slight overfit due to higher correlation between handcrafted and SAE features. This study demonstrated the general benefit of combing handcrafted and learning-based features in radiomics modeling. It also clearly illustrates the task-specific and data-specific dependency on the performance gain and suggests that while the common methodology of feature combination may be applied across various studies and tasks, study-specific feature selection and model optimization are still necessary to achieve high accuracy and robustness.

Contrast-Enhanced Ultrasonography Findings Correlate with Pathologic Grades of Pancreatic Neuroendocrine Tumors

The correlation of sonographic findings with pathologic grades of pancreatic neuroendocrine tumors (PNETs) remains unclear. This study aimed to evaluate the usefulness of sonographic features in diagnosing the pathologic grade of PNETs. Conventional and contrast-enhanced ultrasonography findings of PNETs diagnosed by surgical pathology from July 2010 to June 2020 were retrospectively reviewed. Sonographic features were compared among three pathologic grades of PNETs according to the World Health Organization 2010 classification. Ordinal regression models were constructed to evaluate the usefulness of the sonographic features in diagnosing the pathologic grade of PNETs. This study enrolled 93 participants with PNETs: 50 grade 1, 31 grade 2 and 12 grade 3. Multivariate ordinal regression analysis suggested that tumor size ≥2 cm (odds ratio [OR], 0.110; 95% confidence interval [CI], 0.020–0.606; p = 0.011), dilation of the main pancreatic duct (OR, 0.103; 95% CI, 0.025–0.430; p = 0.002), hepatic metastases (OR, 0.250; 95% CI, 0.072–0.869; p = 0.029) and hyper-enhancement in arterial phase (OR, 4.676; 95% CI, 1.656–13.206; p = 0.004) were significantly associated with the pathologic grades of PNETs. The accuracy of the ordinal logistic regression model in identifying grade 1, 2 and 3 PNETs was 77.4%, 67.7% and 90.3%, respectively. The findings suggest that sonographic features, including tumor size, pancreatic duct dilation and hepatic metastasis, as well as the enhancement level in arterial phase, may help identify different pathologic grades of PNETs.

Application of Radiomics Analysis Based on CT Combined With Machine Learning in Diagnostic of Pancreatic Neuroendocrine Tumors Patient’s Pathological Grades

PurposeTo evaluate the value of multiple machine learning methods in classifying pathological grades (G1,G2, and G3), and to provide the best machine learning method for the identification of pathological grades of pancreatic neuroendocrine tumors (PNETs) based on radiomics.Materials and MethodsA retrospective study was conducted on 82 patients with Pancreatic Neuroendocrine tumors. All patients had definite pathological diagnosis and grading results. Using Lifex software to extract the radiomics features from CT images manually. The sensitivity, specificity, area under the curve (AUC) and accuracy were used to evaluate the performance of the classification model.ResultOur analysis shows that the CT based radiomics features combined with multi algorithm machine learning method has a strong ability to identify the pathological grades of pancreatic neuroendocrine tumors. DC + AdaBoost, DC + GBDT, and Xgboost+RF were very valuable for the differential diagnosis of three pathological grades of PNET. They showed a strong ability to identify the pathological grade of pancreatic neuroendocrine tumors. The validation set AUC of DC + AdaBoost is 0.82 (G1 vs G2), 0.70 (G2 vs G3), and 0.85 (G1 vs G3), respectively.ConclusionIn conclusion, based on enhanced CT radiomics features could differentiate between different pathological grades of pancreatic neuroendocrine tumors. Feature selection method Distance Correlation + classifier method Adaptive Boosting show a good application prospect.

Application of low dose pancreas perfusion CT combined with enhancement scanning in diagnosis of pancreatic neuroendocrine tumors

PurposeTo explore the diagnostic value of pancreatic perfusion CT combined with contrast-enhanced CT in one-time scanning (PCECT) in pancreatic neuroendocrine tumors (PNETs) and to evaluate the difference of perfusion parameters between different grades of PNETs. Materials and methodsFrom October 2016 to December 2018, forty consecutive patients with histopathological-proven PNETs were identified retrospectively that received PCECT for the preoperative PNETs evaluation. Two board certified radiologists who were blinded to the clinical data evaluated the images independently. The image characters of PNETs vs. tumor-free pancreatic parenchymal and different grades of PNETs were analyzed. ResultsOne-time PCECT scanning had a detection rate of 89.1% for PNETs, which was higher than the detection accuracy of the perfusion CT only (83.6%). The perfusion parameters of PNETs including blood volume (BV), blood flow (BF), mean slope of increase (MSI), and capillary surface permeability (PS) were significantly increased than those of tumor-free pancreatic parenchyma (p < 0.05, respectively). For differential comparison between grade I (G1) and grade II (G2) tumors, the parameters of BF and impulse residue function (IRF) of tumor tissue were significantly higher in the G2 tumors (p < 0.05, for both). In this study, the total radiation dose of the whole PCECT scan was 16.241 ± 2.289 mSv. ConclusionThe one-time PCECT scan may improve the detection of PNETs according to morphological features and perfusion parameters with a relative small radiation dose. The perfusion parameters of BF and IRF may be used to help distinguish G1 and G2 tumors in the preoperative evaluation.

Histological diagnosis and grading of pancreatic neuroendocrine tumor by endoscopic ultrasound-guided fine needle biopsy using a 25-gauge needle with a core trap: A multicenter prospective trial

ObjectivesPreoperative grading of pancreatic neuroendocrine tumors (PanNET) is challenging. The aim of this study was to prospectively evaluate the use of a 25-gauge needle with a core trap for diagnosis and grading of PanNET. MethodsThis multicenter prospective trial was registered with the University Hospital Medical Information Network (UMIN000021409). Consecutive patients with suspected PanNET between June 2016 and November 2017 were enrolled. All patients underwent endoscopic ultrasound-guided fine needle biopsy (EUS-FNB) using a 25-gauge needle with a core trap. Samples obtained after the first needle pass were used for central pathological review. EUS-FNB was evaluated in terms of (i) technical success rate, (ii) adequacy for histological evaluation, (iii) complication rate during the procedure, and (iv) concordance between PanNET grading on EUS-FNB and that after analysis of the resected tumor. ResultsFifty-two patients were enrolled. Of the 36/52 patients who underwent surgical resection, 31 were finally diagnosed with PanNET and were eligible for analysis. The technical success rate of EUS-FNB was 100%. The rate of adequacy for histological evaluation was 90.3%. There were no complications related to EUS-FNB. The concordance rate between PanNET grading on EUS-FNB and that after analysis of the resected tumor was 82.6% (95% confidence interval = 61.22–95.05, P = 0.579). ConclusionsEUS-FNB using a 25-gauge needle with a core trap is feasible, providing histological samples are of sufficient quality for diagnosis and grading of PanNET.