Development and validation of a deep learning radiomics model with clinical-radiological characteristics for the identification of occult peritoneal metastases in patients with pancreatic ductal adenocarcinoma.

BACKGROUND: Occult peritoneal metastases (OPM) in patients with pancreatic ductal adenocarcinoma (PDAC) are frequently overlooked during imaging. The authors aimed to develop and validate a computed tomography (CT)-based deep learning-based radiomics (DLR) model to identify OPM in PDAC before treatment. METHODS: This retrospective, bicentric study included 302 patients with PDAC (training: n =167, OPM-positive, n =22; internal test: n =72, OPM-positive, n =9: external test, n =63, OPM-positive, n =9) who had undergone baseline CT examinations between January 2012 and October 2022. Handcrafted radiomics (HCR) and DLR features of the tumor and HCR features of peritoneum were extracted from CT images. Mutual information and least absolute shrinkage and selection operator algorithms were used for feature selection. A combined model, which incorporated the selected clinical-radiological, HCR, and DLR features, was developed using a logistic regression classifier using data from the training cohort and validated in the test cohorts. RESULTS: Three clinical-radiological characteristics (carcinoembryonic antigen 19-9 and CT-based T and N stages), nine HCR features of the tumor, 14 DLR features of the tumor, and three HCR features of the peritoneum were retained after feature selection. The combined model yielded satisfactory predictive performance, with an area under the curve (AUC) of 0.853 (95% CI: 0.790-0.903), 0.845 (95% CI: 0.740-0.919), and 0.852 (95% CI: 0.740-0.929) in the training, internal test, and external test cohorts, respectively (all P <0.05). The combined model showed better discrimination than the clinical-radiological model in the training (AUC=0.853 vs. 0.612, P <0.001) and the total test (AUC=0.842 vs. 0.638, P <0.05) cohorts. The decision curves revealed that the combined model had greater clinical applicability than the clinical-radiological model. CONCLUSIONS: The model combining CT-based DLR and clinical-radiological features showed satisfactory performance for predicting OPM in patients with PDAC.

Dual-energy CT improves differentiation of non-hypervascular pancreatic neuroendocrine neoplasms from CA 19-9-negative pancreatic ductal adenocarcinomas.

PURPOSE: To evaluate the utility of dual-energy CT (DECT) in differentiating non-hypervascular pancreatic neuroendocrine neoplasms (PNENs) from pancreatic ductal adenocarcinomas (PDACs) with negative carbohydrate antigen 19-9 (CA 19-9). METHODS: This retrospective study included 26 and 39 patients with pathologically confirmed non-hypervascular PNENs and CA 19-9-negative PDACs, respectively, who underwent contrast-enhanced DECT before treatment between June 2019 and December 2021. The clinical, conventional CT qualitative, conventional CT quantitative, and DECT quantitative parameters of the two groups were compared using univariate analysis and selected by least absolute shrinkage and selection operator regression (LASSO) analysis. Multivariate logistic regression analyses were performed to build qualitative, conventional CT quantitative, DECT quantitative, and comprehensive models. The areas under the receiver operating characteristic curve (AUCs) of the models were compared using DeLong's test. RESULTS: The AUCs of the DECT quantitative (based on normalized iodine concentrations [nICs] in the arterial and portal venous phases: 0.918; 95% confidence interval [CI] 0.852-0.985) and comprehensive (based on tumour location and nICs in the arterial and portal venous phases: 0.966; 95% CI 0.889-0.995) models were higher than those of the qualitative (based on tumour location: 0.782; 95% CI 0.665-0.899) and conventional CT quantitative (based on normalized conventional CT attenuation in the arterial phase: 0.665; 95% CI 0.533-0.797; all P < 0.05) models. The DECT quantitative and comprehensive models had comparable performances (P = 0.076). CONCLUSIONS: Higher nICs in the arterial and portal venous phases were associated with higher blood supply improving the identification of non-hypervascular PNENs.

Circulating Regulatory T Cells: A Novel Marker Associated with Liver Metastasis and the Treatment Response of Transarterial Embolization in Gastroenteropancreatic Neuroendocrine Tumors.

INTRODUCTION: To investigate the role of circulating regulatory T cells (Tregs) as a novel marker associated with liver metastases and treatment response to transarterial embolization (TAE) in patients with gastroenteropancreatic neuroendocrine tumors (GEP-NETs). METHODS: Circulating Tregs, defined as the CD4+CD25+CD127low/- population, were examined by flow cytometry in peripheral blood mononuclear cells (PBMCs) from patients with GEP-NETs. Clinicopathological parameters, radiologic response, and hepatic progression-free survival (hPFS) data were collected. RESULTS: The association between circulating Tregs and clinicopathological parameters was analyzed in 139 GEP-NET patients. Higher Treg levels were significantly associated with more progressive clinical features, including a higher WHO grade, more advanced TNM stage, and the presence of liver metastases. A Treg level ≥ 8.015% distinguished between patients with and without liver metastases. Among a cohort of 51 GEP-NET patients who were subjected to TAE for reducing liver metastasis burden, patients with higher Treg levels depicted unfavorable responses and significantly reduced hPFS after TAE treatment. We also revealed that patients with Treghigh (≥8.975%) displayed significantly shorter median hPFS than patients with Treglow (< 8.975%). Additionally, after adjusting for other confounding clinical parameters, the association between Tregs and treatment response as well as hPFS remained significant, suggesting that Tregs may have a strong and independent prognostic impact in GEP-NETs. CONCLUSIONS: Our data suggest that circulating Tregs are a novel immunological marker associated with liver metastases and treatment response to TAE in patients with GEP-NETs.

Preoperative assessment of peripheral vascular invasion of pancreatic ductal adenocarcinoma based on high-resolution MRI.

OBJECTIVES: Preoperative imaging of vascular invasion is important for surgical resection of pancreatic ductal adenocarcinoma (PDAC). However, whether MRI and CT share the same evaluation criteria remains unclear. This study aimed to compare the diagnostic accuracy of high-resolution MRI (HR-MRI), conventional MRI (non-HR-MRI) and CT for PDAC vascular invasion. METHODS: Pathologically proven PDAC with preoperative HR-MRI (79 cases, 58 with CT) and non-HR-MRI (77 cases, 59 with CT) were retrospectively collected. Vascular invasion was confirmed surgically or pathologically. The degree of tumour-vascular contact, vessel narrowing and contour irregularity were reviewed respectively. Diagnostic criteria 1 (C1) was the presence of all three characteristics, and criteria 2 (C2) was the presence of any one of them. The diagnostic efficacies of different examination methods and criteria were evaluated and compared. RESULTS: HR-MRI showed satisfactory performance in assessing vascular invasion (AUC: 0.87-0.92), especially better sensitivity (0.79-0.86 vs. 0.40-0.79) than that with non-HR-MRI and CT. HR-MRI was superior to non-HR-MRI. C2 was superior to C1 on CT evaluation (0.85 vs. 0.79, P = 0.03). C1 was superior to C2 in the venous assessment using HR-MRI (0.90 vs. 0.87, P = 0.04) and in the arterial assessment using non-HR-MRI (0.69 vs. 0.68, P = 0.04). The combination of C1-assessed HR-MRI and C2-assessed CT was significantly better than that of CT alone (0.96 vs. 0.86, P = 0.04). CONCLUSIONS: HR-MRI more accurately assessed PDAC vascular invasion than conventional MRI and may contribute to operative decision-making. C1 was more applicable to MRI scans, and C2 to CT scans. The combination of C1-assessed HR-MRI and C2-assessed CT outperformed CT alone and showed the best efficacy in preoperative examination of PDAC.

Improving Tumor Classification by Reusing Self-predicted Segmentation of Medical Images as Guiding Knowledge.

Differential diagnosis of tumors is important for computer-aided diagnosis. In computer-aided diagnosis systems, expert knowledge of lesion segmentation masks is limited as it is only used during preprocessing or as supervision to guide feature extraction. To improve the utilization of lesion segmentation masks, this study proposes a simple and effective multitask learning network that improves medical image classification using self-predicted segmentation as guiding knowledge; we call this network RS 2-net. In RS 2-net, the predicted segmentation probability map obtained from the initial segmentation inference is added to the original image to form a new input, which is then reinput to the network for the final classification inference. We validated the proposed RS 2-net using three datasets: the pNENs-Grade dataset, which tested the prediction of pancreatic neuroendocrine neoplasm grading, and the HCC-MVI dataset, which tested the prediction of microvascular invasion of hepatocellular carcinoma, and ISIC 2017 public skin lesion dataset. The experimental results indicate that the proposed strategy of reusing self-predicted segmentation is effective, and RS 2-net outperforms other popular networks and existing state-of-the-art studies. Interpretive analytics based on feature visualization demonstrates that the improved classification performance of our reuse strategy is due to the semantic information that can be acquired in advance in a shallow network.

Diagnosis, Treatment, and Prognosis of Patients with Primary Familial Gastrointestinal Stromal Tumor: A Case Report and Literature Review.

Gastrointestinal stromal tumors are the most common mesenchymal tumors of the digestive tract, most of which are sporadic, and familial GISTs with germline mutations are rarely seen. Here, we report a 26-year-old female with a germline p. W557R mutation in exon 11 of the KIT gene. The proband and her father and sister presented with multifocal GIST and pigmented nevi. All 3 patients underwent surgery and imatinib therapy. To date, only 49 kindreds with germline KIT mutations and 6 kindreds with germline PDGFRA mutations have been reported. Summarizing the reported kindreds, the majority of familial GISTs manifest as multiple primary GISTs complicated with special clinical manifestations, including cutaneous hyperpigmentation, dysphagia, mastocytosis, inflammatory fibrous polyps, and large hands. Familial GISTs are generally thought to exhibit TKI sensitivity similar to that of sporadic GISTs with the same mutation.

Development and validation of a radiomics model of magnetic resonance for predicting liver metastasis in resectable pancreatic ductal adenocarcinoma patients.

BACKGROUND: Nearly one fourth of patients with pancreatic ductal adenocarcinoma (PDAC) occur to liver metastasis after surgery, and liver metastasis is a risk factor for prognosis for those patients with surgery therapy. However, there is no effective way to predict liver metastasis post-operation. METHOD: Clinical data and preoperative magnetic resonance imaging (MRI) of PDAC patients diagnosed between July 2010 and July 2020 were retrospectively collected from three hospital centers in China. The significant MRI radiomics features or clinicopathological characteristics were used to establish a model to predict liver metastasis in the development and validation cohort. RESULTS: A total of 204 PDAC patients from three hospital centers were divided randomly (7:3) into development and validation cohort. Due to poor predictive value of clinical features, MRI radiomics model had similar receiver operating characteristics curve (ROC) value to clinical-radiomics combing model in development cohort (0.878 vs. 0.880, p = 0.897) but better ROC in validation dataset (0.815 vs. 0.732, p = 0.022). Radiomics model got a sensitivity of 0.872/0.750 and a specificity of 0.760/0.822 to predict liver metastasis in development and validation cohort, respectively. Among 54 patients randomly selected with post-operation specimens, fibrosis markers (α-smooth muscle actin) staining was shown to promote radiomics model with ROC value from 0.772 to 0.923 (p = 0.049) to predict liver metastasis. CONCLUSION: This study developed and validated an MRI-based radiomics model and showed a good performance in predicting liver metastasis in resectable PDAC patients.

The Mutational, Prognostic, and Therapeutic Landscape of Neuroendocrine Neoplasms.

BACKGROUND: Neuroendocrine neoplasms (NENs) represent clinically and genetically heterogeneous malignancies, thus a comprehensive understanding of underlying molecular characteristics, prognostic signatures, and potential therapeutic targets is urgently needed. METHODS: Next-generation sequencing (NGS) and immunohistochemistry were applied to acquire genomic and immune profiles of NENs from 47 patients. RESULTS: Difference was distinguished based on differentiation grade and primary localization. Poorly differentiated neuroendocrine carcinomas (NECs) and well-differentiated neuroendocrine tumors (NETs) harbored distinct molecular features; we observed that tumor mutational burden (TMB) and tumor neoantigen burden (TNB) were significantly higher in NECs versus NETs. Notably, we identified a 7-gene panel (MLH3, NACA, NOTCH1, NPAP1, RANBP17, TSC2, and ZFHX4) as a novel prognostic signature in NENs; patients who carried mutations in any of the 7 genes exhibited significantly poorer survival. Furthermore, loss of heterozygosity (LOH) and germline homogeneity in human leukocyte antigen (HLA) are common in NENs, accounting for 39% and 36%, respectively. Notably, HLA LOH was an important prognostic biomarker for a subgroup of NEN patients. Finally, we analyzed clinically actionable targets in NENs, revealing that TMB high (TMB-H) or gene mutations in TP53, KRAS, and HRAS were the most frequently observed therapeutic indicators, which granted eligibility to immune checkpoint blockade (ICB) and targeted therapy. CONCLUSION: Our study revealed heterogeneity of NENs, and identified novel prognostic signatures and potential therapeutic targets, which directing improvements of clinical management for NEN patients in the foreseeable future.

Use of dual-layer spectral detector computed tomography in the diagnosis of pancreatic neuroendocrine neoplasms.

PURPOSE: To explore the optimal energy level of dual-layer spectral detector computed tomography (DLCT) images of pancreatic neuroendocrine neoplasms (pNENs) and investigate the value in their detection. METHODS: This retrospective analysis included 134 pNEN patients with 136 lesions; they underwent contrast-enhanced DLCT scanning with histopathological confirmation of pNENs. Virtual monoenergetic images (VMI) of 40-100 keV, iodine concentration map (IC map), Z-effective atomic number map (Zeff map), and conventional images were analysed. The optimal energy level was obtained by comparing the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). The lesion detection rates of DLCT and conventional images were compared. Subjective image analysis was performed by two readers who assessed the image quality and lesion conspicuity on a 5-point scale. RESULTS: The SNR of VMIs from 40 to 80 keV (arterial phase, P < 0.001; venous phase, P < 0.05) and CNR from 40 to 60 keV (arterial and venous phases, each P < 0.05) were higher than that of conventional images; VMI40keV showed the highest SNR and CNR. There was a good inter-reader agreement between the two reviewers (Kappa values > 0.61); the scores of Zeff and IC maps were higher than those of conventional images and VMI40keV (P < 0.05). The detection performance of DLCT images was better than conventional images. CONCLUSIONS: The VMI40keV demonstrated the best CNR and SNR of pNENs compared to other VMIs. Zeff and IC maps improve objective image quality and reader preference compared to conventional images. These findings could possess important clinical implications in formulating treatment strategies.

Special issue "The advance of solid tumor research in China": Prediction of Sunitinib efficacy using computed tomography in patients with pancreatic neuroendocrine tumors.

Clinically effective methods to predict the efficacy of sunitinib, for patients with metastatic or locally advanced pancreatic neuroendocrine tumors (panNET) are scarce, making precision treatment difficult. This study aimed to develop and validate a computed tomography (CT)-based method to predict the efficacy of sunitinib in patients with panNET. Pretreatment CT images of 171 lesions from 38 patients with panNET were included. CT value ratio (CT value of tumor/CT value of abdominal aorta from the same patient) and radiomics features were extracted for model development. Receiver operating curve (ROC) with area under the curve (AUC) and decision curve analysis (DCA) were used to evaluate the proposed model. Tumor shrinkage of >10% at first follow-up after sunitinib treatment was significantly associated with longer progression-free survival (PFS; P < .001) and was used as the major treatment outcome. The CT value ratio could predict tumor shrinkage with AUC of 0.759 (95% confidence interval [CI], 0.685-0.833). We then developed a radiomics signature, which showed significantly higher AUC in training (0.915; 95% CI, 0.866-0.964) and validation (0.770; 95% CI, 0.584-0.956) sets than CT value ratio. DCA also confirmed the clinical utility of the model. Subgroup analysis showed that this radiomics signature had a high accuracy in predicting tumor shrinkage both for primary and metastatic tumors, and for treatment-naive and pretreated tumors. Survival analysis showed that radiomics signature correlated with PFS (P = .020). The proposed radiomics-based model accurately predicted tumor shrinkage and PFS in patients with panNET receiving sunitinib and may help select patients suitable for sunitinib treatment.

The role of quantitative tumor burden based on [68 Ga]Ga-DOTA-NOC PET/CT in well-differentiated neuroendocrine tumors: beyond prognosis.

PURPOSE: We aimed to elucidate the role of quantitative tumor burden based on PET/CT of somatostatin receptors in well-differentiated neuroendocrine tumors (NETs). METHODS: This study enrolled patients with [68 Ga]Ga-DOTA-NOC PET/CT-positive advanced NETs who did not receive medical treatment prior to PET/CT. Tumor burden was calculated using methods based on the background threshold and relative fixed threshold values (30%, 40%, and 50%). The prognostic value of the measured tumor burden in reference to overall survival (OS) and progression-free survival (PFS) on treatment with octreotide long-acting repeatable (LAR) was assessed using Cox regression analysis, Harrell's C-index, and survival analysis. A classification and regression tree (CART) was used to determine the optimal threshold for tumor burden. RESULTS: A total of 204 patients were included. Somatostatin receptor-expressing tumor volume (SRETV) and liver SRETV derived from a relative fixed threshold of 30% (SRETV30 and liver SRETV30) were statistically significantly associated with OS (C-index: 0.802 [95% confidence interval (CI), 0.658-0.946] and 0.806 [95% CI, 0.664-0.948], respectively). Extrahepatic tumor burden was not correlated with OS (hazard ratio: 0.617, 95% CI: 0.241-1.574, P = 0.312). Among 155 patients with non-functional NETs with a ki-67 index of ≤ 10%, those with a high SRETV30 (P = 0.016) or high liver SRETV30 (P = 0.014) showed statistically significantly worse PFS on treatment with octreotide LAR. Patients receiving a higher dose of octreotide LAR normalized by SRETV30 or liver SRETV30 (a normalized dose or a liver normalized dose) showed prolonged PFS on treatment with octreotide LAR and a prolonged OS. CONCLUSION: Quantitative tumor burden based on [68 Ga]Ga-DOTA-NOC PET/CT was correlated with OS and PFS in patients with non-functional NETs with a ki-67 index of ≤ 10% who received octreotide LAR. Calculating normalized and liver normalized doses may help in selecting the starting dose of octreotide LAR.

Bladder paraganglioma, gastrointestinal stromal tumor, and SDHB germline mutation in a patient with Carney-Stratakis syndrome: A case report and literature review.

Background: Carney-Stratakis syndrome (CSS) is a rare dyad of paraganglioma (PGL)/pheochromocytoma (PHEO) and gastrointestinal stromal tumor (GIST). PGLs are neuroendocrine tumors of neural crest origin which are mostly found in the head, neck, and retroperitoneal space. GISTs are the most common mesenchymal tumors of the digestive tract, usually caused by KIT/PDGFRA mutations. Here, we reported a case of CSS with unusual bladder PGL and succinate dehydrogenase (SDH) deficient GIST due to a germline mutation in SDH-subunit B (SDHB) gene. Case presentation: A 39-year-old female patient initially diagnosed with gastric GIST and isolated pelvic metastasis was eventually found to be CSS with bladder PGL and SDH-deficient GIST after surgery. This patient underwent resection of gastric and bladder tumors, and postoperative pathology confirmed the diagnosis of CSS. According to the next-generation sequencing (NGS), the patient carried a germline mutation in the SDHB gene, which was the cause of the disorder. The patient had no tumor recurrence with regular follow-up in 10 months. Conclusions: CSS is an autosomal genetic disorder with no gender difference in incidence, and PGLs are more frequent than GISTs. SDH germline mutation is the molecular biological mechanism of CSS while the most common type is SDHB mutation. The unique mechanism of tumorigenesis including hypoxia and hypermethylation caused by SDH deficiency renders target therapy with tyrosine kinase inhibitors ineffective, therefore complete surgical resection is the optimal treatment in the absence of tumor metastases.

Clinical implications of immune checkpoint markers and immune infiltrates in patients with thymic neuroendocrine neoplasms.

The potential response of immune checkpoint blockade (ICB) in thymic neuroendocrine neoplasms (T-NEN) is largely unknown and full of great expectations. The expression of immune checkpoint molecules and immune infiltrates greatly determine the response to ICB. However, studies regarding the immune landscape in T-NEN are scarce. This work was aimed to characterize the immune landscape and its association with clinical characteristics in T-NEN. The expression of programmed cell death protein 1 (PD-1) and its ligand, programmed death ligand-1 (PD-L1), and the density of tumor-infiltrating lymphocytes (TILs), monocytes, and granulocytes were determined by immunohistochemical (IHC) staining on tumor tissues from T-NEN. Immune landscapes were delineated and correlated with clinicopathological factors. We found that T-NEN with increased immune cell infiltration and enhanced expression of PD-1/PD-L1 tended to have restricted tumor size and less metastases. A higher density of CD8+ TILs was associated with a significantly lower rate of bone metastasis. In addition, we presented three cases of T-NEN who progressed after multiple lines of therapies and received ICB for alternative treatment. ICB elicited durable partial responses with satisfactory safety in two patients with atypical carcinoid, but showed resistance in 1 patient with large cell neuroendocrine carcinoma. This innovative study delineated for the first time the heterogeneous immune landscape in T-NEN and identified CD8+ TILs as a potential marker to predict bone metastasis. An "immune-inflamed" landscape with the presence of TILs predominated in T-NEN, making T-NEN a potentially favorable target for ICB treatment. Further judicious designs of "tailor-made" clinical trials of ICB in T-NEN are urgently needed.

Multi-frequency magnetic resonance elastography of the pancreas: measurement reproducibility and variance among healthy volunteers.

Background: Patients with chronic pancreatitis often have irreversible pancreatic insufficiency before a clinical diagnosis. Pancreatic cancer is a fatal malignant tumor in the advanced stages. Patients having high risk of pancreatic diseases must be screened early to obtain better outcomes using new imaging modalities. Therefore, this study aimed to investigate the reproducibility of tomoelastography measurements for assessing pancreatic stiffness and fluidity and the variance among healthy volunteers. Methods: Forty-seven healthy volunteers were prospectively enrolled and underwent two tomoelastography examinations at a mean interval of 7 days. Two radiologists blindly and independently measured the pancreatic stiffness and fluidity at the first examination to determine the reproducibility between readers. One radiologist measured the adjacent pancreatic slice at the first examination to determine the reproducibility among slices and measured the pancreas at the second examination to determine short-term repeatability. The stiffness and fluidity of the pancreatic head, body, and tail were compared to determine anatomical differences. The pancreatic stiffness and fluidity were compared based on sex, age, and body mass index (BMI). Results: Bland-Altman analyses (all P > 0.05) and intraclass correlation coefficients (all >0.9) indicated near perfect reproducibility among readers, slices, and examinations at short intervals. Neither stiffness (P = 0.477) nor fluidity (P = 0.368) differed among the pancreatic anatomical regions. The mean pancreatic stiffness was 1.45 ± 0.09 m/s; the mean pancreatic fluidity was 0.83 ± 0.06 rad. Stiffness and fluidity did not differ by sex, age, or BMI. Conclusion: Tomoelastography is a promising and reproducible tool for assessing pancreatic stiffness and fluidity in healthy volunteers.

Tumor fibrosis correlates with the survival of patients with pancreatic adenocarcinoma and is predictable using clinicoradiological features.

OBJECTIVES: To evaluate the prognostic value of fibrosis for patients with pancreatic adenocarcinoma (PDAC) and preoperatively predict fibrosis using clinicoradiological features. Tumor fibrosis plays an important role in the chemoresistance of PDAC. However, the prognostic value of tumor fibrosis remains contradiction and accurate prediction of tumor fibrosis is required. METHODS: The study included 131 patients with PDAC who underwent first-line surgery. The prognostic value of fibrosis and rounded cutoff fibrosis points for median overall survival (OS) and disease-free survival (DFS) were determined using Cox regression and receiver operating characteristic (ROC) analyses. Then the whole cohort was randomly divided into training (n = 88) and validation (n = 43) sets. Binary logistic regression analysis was performed to select independent risk factors for fibrosis in the training set, and a nomogram was constructed. Nomogram performance was assessed using a calibration curve and decision curve analysis (DCA). RESULTS: Hazard ratios of fibrosis for OS and DFS were 1.121 (95% confidence interval [CI]: 1.082-1.161) and 1.110 (95% CI: 1.067-1.155). ROC analysis identified 40% as the rounded cutoff fibrosis point for median OS and DFS. Tumor diameter, carbohydrate antigen 19-9 level, and peripancreatic tumor infiltration were independent risk factors; areas under the nomogram curve were 0.810 and 0.804 in the training and validation sets, respectively. The calibration curve indicated good agreement of the nomogram, and DCA demonstrated good clinical usefulness. CONCLUSIONS: Tumor fibrosis was associated with poor OS and DFS in patients with PDAC. The nomogram incorporating clinicoradiological features was useful for preoperatively predicting tumor fibrosis. KEY POINTS: • Tumor fibrosis is correlated with poor prognosis in patients with pancreatic adenocarcinoma. • Tumor fibrosis can be categorized according to its association with overall survival and disease-free survival. • A nomogram incorporating carbohydrate antigen 19-9 level, tumor diameter, and peripancreatic tumor infiltration is useful for preoperatively predicting tumor fibrosis.

Utility of Quantitative Metrics From Dual-Layer Spectral-Detector CT for Differentiation of Pancreatic Neuroendocrine Tumor and Neuroendocrine Carcinoma.

BACKGROUND. The 2019 WHO classification of digestive system tumors separates neuroendocrine neoplasms (NENs) into neuroendocrine tumors (NETs) and neuroendocrine carcinomas (NECs), which are considered to represent pathologically distinct entities warranting different management approaches. Dual-layer spectral-detector CT (DLCT) may aid their differentiation through specific material decomposition. OBJECTIVE. The purpose of this study was to assess the utility of quantitative metrics derived from DLCT for the differentiation of pancreatic NET and NEC. METHODS. This retrospective study included 104 patients (mean age, 51 ± 13 [SD] years; 52 women, 52 men) with pathologically confirmed NEN (89 NET, including 22 grade 1, 48 grade 2, and 19 grade 3; 15 NEC) who underwent multiphase DLCT within 15 days before biopsy or resection. Two radiologists independently placed ROIs to record tumor attenuation, iodine concentration (IC), and effective atomic number (Zeff) across phases and assessed qualitative features (composition, homogeneity, margins, calcifications, main pancreatic duct dilatation, vascular invasion, lymphadenopathy). Interobserver agreement was assessed. Mean and median values of both readers' measurements were obtained for quantitative measures; consensus was reached for qualitative features. NET and NEC were compared using multivariable regression analysis and ROC analysis. RESULTS. Interobserver agreement, expressed as intraclass correlation coefficients, ranged from 0.869 to 0.992 for quantitative metrics and, expressed as kappa coefficients, ranged from 0.723 to 0.816 for qualitative features. In multivariable analysis of qualitative and quantitative features, significant independent predictors of NEC (p < .05) were IC in the portal venous phase (median, 1.3 mg/mL for NEC vs 2.7 mg/mL for NET), Zeff in the portal venous phase (median, 8.1 vs 8.6), and attenuation in the portal venous phase (median, 78.2 vs 113.5 HU). AUC for predicting NEC was 0.897 for IC, 0.884 for Zeff, 0.921 for combination of IC and Zeff, and 0.855 for attenuation. Predicted probability based on a combination of IC and Zeff achieved sensitivity of 93.33% and specificity of 80.90% for predicting NEC. Significant independent predictors (p < .05) for differentiating grade 3 NET and NEC were IC (median, 2.0 vs 1.3 mg/mL; AUC = 0.789) and attenuation (mean, 90.3 vs 78.2 HU; AUC = 0.647), both measured in the portal venous phase. CONCLUSION. Incorporation of DLCT metrics improves differentiation of NET and NEC compared with conventional CT attenuation and qualitative features. CLINICAL IMPACT. DLCT may help select patients with pancreatic NENs for platinum-based chemotherapies.

Optimization of the tumour response threshold in advanced gastroenteropancreatic neuroendocrine carcinomas treated with cisplatin/etoposide combined chemotherapy.

OBJECTIVES: To identify early and more accurate imaging response criteria for computed tomography evaluation to define 'responders' in advanced gastroenteropancreatic neuroendocrine carcinoma (GEP-NEC) patients treated with cisplatin/etoposide combined chemotherapy. MATERIALS AND METHODS: Thirty-seven patients with GEP-NEC treated with first-line cisplatin/etoposide (E/P) combined chemotherapy were enrolled in this study. Computed tomography scans of the chest, abdomen, and pelvis were performed at baseline, during the treatment course, and during follow-up. Tumour size was measured, and tumour response was evaluated by Response Evaluation Criteria in Solid Tumours (RECIST) 1.1. Receiver operating characteristic (ROC) analysis was carried out among the patients who progressed during follow-up. Thresholds from -55% to + 5% were tested by Kaplan-Meier analysis to define "responders" for significantly improved progression-free survival (PFS). The overall survival rate was compared between these two groups. RESULTS: A reduction of 45% (vs. baseline) achieved the highest sensitivity (70%) and specificity (90%) by ROC analysis. This threshold divided patients into 15 responders and 22 nonresponders. Patients who were grouped as responders by the -45% threshold had a significantly longer PFS (11.06 months) than nonresponders (7.97 months, hazard ratio, 3.636; 95% confidence interval, 1.293-10.164). No significant difference was shown in overall survival between these two groups (29.1 vs. 21.4 months, P = 0.190). CONCLUSION: A 45% reduction in target lesions may be considered to be a more reliable predictor than the RECIST 1.1 criteria in evaluating the outcome of GEP-NEC patients treated with E/P chemotherapy.

A narrative review of multiple endocrine neoplasia syndromes: genetics, clinical features, imaging findings, and diagnosis.

OBJECTIVE: We aimed to provide ideas for clinicians, especially radiologists, for the diagnosis of multiple endocrine neoplasia (MEN) syndromes. BACKGROUND: MEN syndromes include MEN1, MEN2, and MEN4 and usually involve 2 or more endocrine tumors. The MEN syndromes are a group of euchromatic dominant genetic diseases, and the main genes involved include MEN1 (MEN1), RET (MEN2), and CDKN1B (MEN4). METHODS: In this article, involving 8 cases (4 cases of MEN1, 2 cases of MEN2A, 1 case of MEN2B, 1 case of MEN4) from our center, we introduced the disease spectrum, clinical manifestations (especially imaging findings), and related genes involved in each type of MEN syndromes. We also discussed the differential diagnosis between MEN and sporadic tumors and emphasized that MEN should be screened and the relevant required examinations. CONCLUSIONS: Considering that MEN syndromes involve multiple endocrine gland tumors and nonendocrine organ diseases, it is very important to identify potential patients early and perform multiple examinations on them, including biochemical and multitype, and multisite imaging examinations according to the disease spectrum of each type. Considering that this is a group of genetic diseases, both interviewing patients about their family history and genetic testing are also very important. Only in this way can a comprehensive and accurate diagnosis be made, enabling patients to receive appropriate treatment and improve their prognosis.

Predicting the recurrence risk of pancreatic neuroendocrine neoplasms after radical resection using deep learning radiomics with preoperative computed tomography images.

BACKGROUND: To establish and validate a prediction model for pancreatic neuroendocrine neoplasms (pNENs) recurrence after radical surgery with preoperative computed tomography (CT) images. METHODS: We retrospectively collected data from 74 patients with pathologically confirmed pNENs (internal group: 56 patients, Hospital I; external validation group: 18 patients, Hospital II). Using the internal group, models were trained with CT findings evaluated by radiologists, radiomics, and deep learning radiomics (DLR) to predict 5-year pNEN recurrence. Radiomics and DLR models were established for arterial (A), venous (V), and arterial and venous (A&V) contrast phases. The model with the optimal performance was further combined with clinical information, and all patients were divided into high- and low-risk groups to analyze survival with the Kaplan-Meier method. RESULTS: In the internal group, the areas under the curves (AUCs) of DLR-A, DLR-V, and DLR-A&V models were 0.80, 0.58, and 0.72, respectively. The corresponding radiomics AUCs were 0.74, 0.68, and 0.70. The AUC of the CT findings model was 0.53. The DLR-A model represented the optimum; added clinical information improved the AUC from 0.80 to 0.83. In the validation group, the AUCs of DLR-A, DLR-V, and DLR-A&V models were 0.77, 0.48, and 0.64, respectively, and those of radiomics-A, radiomics-V, and radiomics-A&V models were 0.56, 0.52, and 0.56, respectively. The AUC of the CT findings model was 0.52. In the validation group, the comparison between the DLR-A and the random models showed a trend of significant difference (P=0.058). Recurrence-free survival differed significantly between high- and low-risk groups (P=0.003). CONCLUSIONS: Using DLR, we successfully established a preoperative recurrence prediction model for pNEN patients after radical surgery. This allows a risk evaluation of pNEN recurrence, optimizing clinical decision-making.

Accurate and Feasible Deep Learning Based Semi-Automatic Segmentation in CT for Radiomics Analysis in Pancreatic Neuroendocrine Neoplasms.

Current clinical practice or radiomics studies of pancreatic neuroendocrine neoplasms (pNENs) require manual delineation of the lesions in computed tomography (CT) images, which is time-consuming and subjective. We used a semi-automatic deep learning (DL) method for segmentation of pNENs and verified its feasibility in radiomics analysis. This retrospective study included two datasets: Dataset 1, contrast-enhanced CT images (CECT) of 80 and 18 patients respectively collected from two centers; and Dataset 2, CECT of 56 and 16 patients respectively from two centers. A DL-based semi-automatic segmentation model was developed and validated with Dataset 1 and Dataset 2, and the segmentation results were used for radiomics analysis from which the performance was compared against that based on manual segmentation. The mean Dice similarity coefficient of the trained segmentation model was 81.8% and 74.8% for external validation with Dataset 1 and Dataset 2 respectively. Four classifiers frequently used in radiomics studies were trained and tested with leave-one-out cross-validation strategy. For pathological grading prediction with Dataset 1, the area under the receiver operating characteristic curve (AUC) with semi-automatic segmentation was up to 0.76 and 0.87 respectively for internal and external validation. For recurrence study with Dataset 2, the AUC with semi-automatic segmentation was up to 0.78. All these AUCs were not statistically significant from the corresponding results based on manual segmentation. Our study showed that DL-based semi-automatic segmentation is accurate and feasible for the radiomics analysis in pNENs.