ObjectiveTo investigate the preference for central vascular access device among breast cancer patients undergoing chemotherapy,and to provide a basis for selecting central vascular access devices for breast cancer patients.MethodsUsing the convenient sampling method,a total of 267 patients who received neoadjuvant chemotherapy in the breast surgery department of Nanjing Drum Tower Hospital from January 2023 to March 2024 were selected as the research subjects.A questionnaire was designed using the discrete choice experiment.A mixed Logit regression model was constructed for preference analysis.ResultsThe preference attributes for central vascular access devices in breast cancer patients undergoing chemotherapy included cost,concealment,catheterization time,and the incidence rate of complications.Different ages,educational levels,monthly income,social frequency,and surgical history of patients had different preferences for central vascular access device(all P<0.05).ConclusionsCost is the most concerned attribute for breast cancer patients when choosing central vascular access device.Medical staff should pay attention to the different preferences of breast cancer patients when choosing central vascular access device,and provide professional guidance to help them make decisions on central venous vascular access devices that meet their own needs,thereby improving the medical experience and quality of life.

Abstract Objective: Acute pancreatitis (AP) incidence is rising globally. Current scoring systems lack sensitivity for early organ failure (OF) prediction and suffer from interobserver variability. This study aimed to develop and validate an artificial intelligence (AI)-driven model for fully automated early prediction of OF in AP using multiphase computed tomography (CT) imaging. Methods: This multicenter study included 2746 AP patients from two tertiary hospitals (2011–2024). Patients were split into training ( n =1820), validation ( n =456), and test cohorts ( n =470). An nnMamba-based segmentation model delineated pancreatic/peripancreatic regions on CT. An organ failure risk assessment with CT and learning engine (ORACLE) model integrated deep learning radiomics (severe organ failure–deep learning radiomics [SOF-DLR] score from 57 optimal features) with clinical variables. The primary outcome was OF (Modified Marshall Score≥2). Results: OF occurred in 8.7% ( n =240). The ORACLE model achieved the receiver operating characteristic curves (area under the curve [AUCs]) of 0.85 (training), 0.89 (validation), and 0.81 (test), outperforming Modified CT Severity Index (M-CTSI) (AUC 0.68–0.74) and clinical models (AUC 0.67–0.71; DeLong’s P <0.001). The overall negative predictive value for the entire cohort ( n =2746) was 97.2%. High-risk patients ( P >0.700; 1.4% of cohort) had 92.1% OF incidence. The model provided a median early warning time of 3.5 hours (mean 9.17 h) before clinical OF onset, with 55% of cases predicted ≥3 h in advance. Conclusions: This AI-based tool enables accurate, automated OF prediction 3.5 h before clinical manifestation, facilitating risk-stratified management. Its generalizability is confirmed in multicenter validation.

BACKGROUND AND OBJECTIVES:Accurate survival prediction for pancreatic ductal adenocarcinoma (PDAC) is crucial for personalized treatment strategies. This study aims to construct a novel pathomics indicator using hematoxylin and eosin-stained whole slide images and deep learning to enhance PDAC prognosis prediction. METHODS:A retrospective, 2-center study analyzed 864 PDAC patients diagnosed between January 2015 and March 2022. Using weakly supervised and multiple instance learning, pathologic features predicting 2-year survival were extracted. Pathomics features, including probability histograms and TF-IDF, were selected through random survival forests. Survival analysis was conducted using Kaplan-Meier curves, log-rank tests, and Cox regression, with AUROC and C-index used to assess model discrimination. RESULTS:The study cohort comprised 489 patients for training, 211 for validation, and 164 in the neoadjuvant therapy (NAT) group. A pathomics score was developed using 7 features, dividing patients into high-risk and low-risk groups based on the median score of 131.11. Significant survival differences were observed between groups (P<0.0001). The pathomics score was a robust independent prognostic factor [Training: hazard ratio (HR)=3.90; Validation: HR=3.49; NAT: HR=4.82; all P<0.001]. Subgroup analyses revealed higher survival rates for early-stage low-risk patients and NAT responders compared to high-risk counterparts (both P<0.05 and P<0.0001). The pathomics model surpassed clinical models in predicting 1-, 2-, and 3-year survival. CONCLUSIONS:The pathomics score serves as a cost-effective and precise prognostic tool, functioning as an independent prognostic indicator that enables precise stratification and enhances the prediction of prognosis when combined with traditional pathologic features. This advancement has the potential to significantly impact PDAC treatment planning and improve patient outcomes.

To develop and validate the chronic pancreatitis CT severity model (CATS), an artificial intelligence (AI)-based tool leveraging automated 3D segmentation and radiomics analysis of non-enhanced CT scans for objective severity stratification in chronic pancreatitis (CP). This retrospective study encompassed patients with recurrent acute pancreatitis (RAP) and CP from June 2016 to May 2020. A 3D convolutional neural network segmented non-enhanced CT scans, extracting 1843 radiomic features to calculate the radiomics score (Rad-score). The CATS was formulated using multivariable logistic regression and validated in a subsequent cohort from June 2020 to April 2023. Overall, 2054 patients with RAP and CP were included in the training (n = 927), validation set (n = 616), and external test (n = 511) sets. CP grade I and II patients accounted for 300 (14.61

Accurate renal cell carcinoma (RCC) subtyping, especially challenging TFE3-rearranged RCC, is vital for treatment. We developed RCCNET (RCC Neural Enhancement Technology), a weakly supervised deep learning framework integrating a parallel cellular morphometric module for biological interpretability, for four-class classification (clear cell, papillary, chromophobe, TFE3-rearranged). Validated multicentrically on 340 patients (training n=233; external validation n=107), RCCNET achieved macro-average AUCs of 0.989 (training) and 0.966 (validation). For TFE3 RCC, AUC was 0.976 with 92.3% sensitivity, but a 66.7% positive predictive value necessitates molecular confirmation of all positive cases. Model predictions significantly correlated with quantitative morphological features, grounding decisions in histopathology. An economic analysis projected an RCCNET-assisted workflow could reduce costs by 83.2% and time by 45.2%. RCCNET provides an interpretable, cost-effective solution. We propose a confidence-based clinical integration framework, flagging uncertain TFE3 predictions for pathologist review to manage false positives and ensure safe deployment.

Accurate diagnosis of infected intra-abdominal fluid collections (IAFCs) is challenging, as the conventional “gas bubble sign” on computed tomography (CT) has poor sensitivity. This study aimed to develop and validate a fully automated artificial intelligence (AI) model using non-contrast CT to improve diagnostic accuracy. In this multicenter retrospective study (July 2011-July 2024), 797 patients with IAFCs confirmed by culture were divided into training (n = 637), validation (n = 80), and external test (n = 80) sets. We developed an AI model, Bubble Bed Based Learning Engine for Abdominal Infection (BUBBLE-AI), based on the novel “bubble bed” concept, which analyzes the inflammatory microenvironment around gas bubbles. The model integrates deep learning and radiomic features, extracted from automated segmentations, with clinical data. The BUBBLE-AI model demonstrated robust and generalizable performance, achieving an area under the curve (AUC) of 0.92 in validation and 0.82 (95

The present study evaluated the prognostic value of a new published joint index, the fat mass triceps skinfold-albumin index (TA) in patients with malignant tumors in at least two organs (MTT). Patients for this study were recruited prospectively as part of a multi-center cohort study titled "Investigation on Nutrition Status and its Clinical Outcome of Common Cancers in China" (INSCOC), conducted between January 2013 and December 2019. The study focused on MTT patients. The time-dependent receiver operating characteristic (ROC) curve analysis was employed to assess and compare the predictive accuracy of various nutritional and inflammatory indices, including the triceps skinfold-albumin index (TA), handgrip strength (HGS), midarm circumference (MAC), calf circumference (CC), systemic immune-inflammation index (SII), patient-generated subjective global assessment (PG-SGA), and malnutrition identified by the Global Leadership Initiative on Malnutrition (GLIM) criteria. Multiple Cox regression models were utilized to investigate the relationship between TA levels (categorized as continuous or normal vs. low) and overall survival (OS). Survival outcomes were graphically represented using Kaplan–Meier (K-M) curves. Five hundred five patients (290 male and 215 female) were included in this study. According to the cut-off of TA (women: 49.9; men: 45.6), 347 patients (68.7

Background: Patients with abdominal Pheochromocytoma and Paraganglioma (PPGL) are prone to a hypertensive crisis during surgery, which may endanger their lives. This study aimed to develop and validate a Computed Tomography (CT) radiomics nomogram for the prediction of intraoperative hypertensive crisis in patients with PPGL. Methods: In this retrospective study, 212 patients with abdominal PPGL underwent abdominal-enhanced CT and surgical resection. Radiomic features were extracted from arterial and venous phases. Multivariable logistic regression models were developed using an internal validation and an external test set. The performance of the nomograms was determined by their discrimination, calibration, and clinical usefulness. Results: A total of 212 patients with PPGL were included, involving 44 with hypertensive crises. The patients were divided into training (n = 117), validation (n = 51), and test (n = 44) sets. Eighteen radiomics-relevant radiomic features were selected. A history of coronary heart disease and the CT radiomics score were included in the prediction model, which achieved an area under the curve of 0.91 [95% Confidence Interval (CI) 0.85-0.97] in the training set, 0.93 (95% CI 0.84-0.99) in the validation set, and 0.85 (95% CI 0.72-0.97) in the test set. The decision curve analysis demonstrated the radiomics nomogram to be clinically useful. Conclusion: Our study has developed and validated a CT radiomics nomogram that has demonstrated remarkable potential in predicting intraoperative hypertensive crisis in patients with abdominal pheochromocytoma and paraganglioma. This non-invasive, straightforward approach has exhibited high accuracy, ease of use, and predictive power.

To develop and validate a simplified CT prediction model (SCTM) based on the 2019 Bosniak classification for predicting malignancy in cystic renal masses (CRMs), and to create a secondary model to distinguish indolent from aggressive CRMs. This retrospective study included the consecutive patients who were pathologically confirmed to have malignant and benign CRMs at four institutions from January 2013 to December 2022. Two radiologists evaluated all CRMs using the Bosniak classification. Multivariable logistic regression and XGBoost models were used to create prediction models. The models were developed, and validated in an independent internal cohort and four independent external cohorts. Model performance was assessed for differentiation ability and clinical utility. In total, 1138 CRM patients were analyzed across training (n = 655), internal validation (n = 165), and external tests (n = 146, n = 69, n = 103). Benign and malignant CRMs accounted for 710 (62.39

BACKGROUND:Effective chronic pancreatitis (CP) treatment requires accurate severity evaluation, but no histopathology grading system exists. This study aimed to develop and validate a novel CP pathological grade (Histopathology-derived CPpG) using quantified pathological and radiological characteristics through deep learning. METHODS:Patients with pathologically/clinically confirmed CP or recurrent acute pancreatitis were retrospectively enrolled (2011-2023). Whole-slide CP images were automatically segmented and quantified via DeeplabV3+, followed by latent class analysis to develop Histopathology-derived CPpG. A deep learning radiomics score (DLRS) was created to predict Histopathology-derived CPpG using preoperative CT scans of patients with pathologically confirmed CP. CT-predicted CPpG was then validated in an independent group of patients with clinically confirmed CP and recurrent acute pancreatitis. RESULTS:The study included 2054 patients with CP and recurrent acute pancreatitis, with 181 cases of pathologically confirmed CP. Histopathology-derived CPpG I had a higher proportion of acini, acinus-to-stroma ratio, acinus-to-islet ratio, islet-to-stroma ratio, and (acinus + islet)-to-stroma ratio, and a lower proportion of stroma and lymphocytes compared to CPpG II. The DLRS demonstrated high performance in the validation (AUC, 0.84; 95 % CI: 0.75-0.92) and test (AUC, 0.76; 95 % CI: 0.65-0.87) sets. In a large-scale clinical validation, CT-predicted grades were significantly associated with endocrine and exocrine function, as well as prognosis (P < .05). CONCLUSION:This study developed a novel pathological classification, Histopathology-derived CPpG, which accurately reflects disease severity. Additionally, the non-invasive DLRS shows great potential for dynamically monitoring CP severity and evaluating pancreatic endocrine and exocrine function, as well as prognosis.

BACKGROUND:Extrapancreatic perineural invasion (EPNI) increases the risk of postoperative recurrence in pancreatic ductal adenocarcinoma (PDAC). This study aimed to develop and validate a computed tomography (CT)-based, fully automated preoperative artificial intelligence (AI) model to predict EPNI in patients with PDAC. METHODS:The authors retrospectively enrolled 1065 patients from two Shanghai hospitals between June 2014 and April 2023. Patients were split into training (n=497), internal validation (n=212), internal test (n=180), and external test (n=176) sets. The AI model used perivascular space and tumor contact for EPNI detection. The authors evaluated the AI model's performance based on its discrimination. Kaplan-Meier curves, log-rank tests, and Cox regression were used for survival analysis. RESULTS:The AI model demonstrated superior diagnostic performance for EPNI with 1-pixel expansion. The area under the curve in the training, validation, internal test, and external test sets were 0.87, 0.88, 0.82, and 0.83, respectively. The log-rank test revealed a significantly longer survival in the AI-predicted EPNI-negative group than the AI-predicted EPNI-positive group in the training, validation, and internal test sets (P<0.05). Moreover, the AI model exhibited exceptional prognostic stratification in early PDAC and improved assessment of neoadjuvant therapy's effectiveness. CONCLUSION:The AI model presents a robust modality for EPNI diagnosis, risk stratification, and neoadjuvant treatment guidance in PDAC, and can be applied to guide personalized precision therapy.

Abstract Instance objects captured in aerial imagery display a range of orientations and exhibit significant scaling differences in their dimensions. Recent researches mainly address the above problems in terms of label assignment strategies and extended backbone spatial receptive fields, however, the former may still introduce lower quality samples, while the latter usually introduces considerable background noise. In this paper, the proposed Multiscale Convolutional Kernels Combined with Bi-Level Routing Attention for backbone Feature Extraction Network (MKBANet) employs multi-scale convolutional kernels to extract feature information at different scales, capture local context information, and combine with a Bi-Level Routing Attention (BRA) to capture remote context information and reduce computational complexity. In addition, an adaptive constrained oriented point set strategy (ACOPSS) is proposed. The adaptive point set constraint strategy is introduced in training, and then the quality metric function is utilized to select the top k high-quality directed point set samples in training, and finally the outliers are penalized. 81.23% mAP on DOTA dataset, the efficacy of the introduced approach is demonstrated.

Motivation: Cystic fluid appears hyperintense via T2WI, the most sensitive detection method and T2WI is a conventional sequence. However, distinguishing pancreatic MCNs from SCNs using T2WI is difficult because both neoplasms appear as hyperintense lesions, especially when both are unilocular. Goal(s): We aimed to develop and validate a T2WI radiomics nomogram for the differentiation of SCNs from MCNs. Approach: A radiomics model that was included clinical characteristics, MRI characteristics, and T2WI rad-scores for differentiating MCNs from SCN. Results: We developed and validated a T2WI radiomics nomogram that functions as a non-invasive and convenient tool for preoperatively predicting the presence of SCNs and MCNs. Impact: The tool has the potential to help clinicians identify patients requiring surveillance or surgery.

To develop and validate a radiomics nomogram based on a fully automated pancreas segmentation to assess pancreatic exocrine function. Furthermore, we aimed to compare the performance of the radiomics nomogram with the pancreatic flow output rate (PFR) and conclude on the replacement of secretin-enhanced magnetic resonance cholangiopancreatography (S-MRCP) by the radiomics nomogram for pancreatic exocrine function assessment. All participants underwent S-MRCP between April 2011 and December 2014 in this retrospective study. PFR was quantified using S-MRCP. Participants were divided into normal and pancreatic exocrine insufficiency (PEI) groups using the cut-off of 200 µg/L of fecal elastase-1. Two prediction models were developed including the clinical and non-enhanced T1-weighted imaging radiomics model. A multivariate logistic regression analysis was conducted to develop the prediction models. The models’ performances were determined based on their discrimination, calibration, and clinical utility. A total of 159 participants (mean age ± standard deviation, 45 years ± 14;119 men) included 85 normal and 74 PEI. All the participants were divided into a training set comprising 119 consecutive patients and an independent validation set comprising 40 consecutive patients. The radiomics score was an independent risk factor for PEI (odds ratio = 11.69; p < 0.001). In the validation set, the radiomics nomogram exhibited the highest performance (AUC, 0.92) in PEI prediction, whereas the clinical nomogram and PFR had AUCs of 0.79 and 0.78, respectively. The radiomics nomogram accurately predicted pancreatic exocrine function and outperformed pancreatic flow output rate on S-MRCP in patients with chronic pancreatitis. • The clinical nomogram exhibited moderate performance in diagnosing pancreatic exocrine insufficiency. • The radiomics score was an independent risk factor for pancreatic exocrine insufficiency, and every point rise in the rad-score was associated with an 11.69-fold increase in pancreatic exocrine insufficiency risk. • The radiomics nomogram accurately predicted pancreatic exocrine function and outperformed the clinical model and pancreatic flow output rate quantified by secretin-enhanced magnetic resonance cholangiopancreatography on MRI in patients with chronic pancreatitis.

Background : Early diagnosis of pancreatic cancer (PC) can potentially improve long-term patient outcomes. An economical and feasible screening tool is urgently needed, globally. We sought to develop and validate an automated artificial intelligence (AI)-based PC detection tool using deep learning.Methods: From March 2018 and December 2021, we collected CT images of individuals with and without PC (control group) were compared. An end-to-end ensemble model, comprising segmentation and classification models, was developed and validated in an internal validation and three external test sets. Model performance was assessed based on discrimination ability.Findings: A total of 1815 individuals including 841 patients (62 10 years; 511 men) with PC and 974 controls (53 11 years; 516 men) from four centers were enrolled in this study. Patients were divided into training (n = 692), validation (n = 299), test-1 (n = 252), test-2 (n = 438) and test-3 (n = 134) sets. The AI ensemble model distinguished well between the control and PC groups, with areas under the curve (AUC) of 0.95, 0.90, 0.96 and 0.87 in the validation and three external sets. The diagnostic ability of the AI ensemble model was superior to the four radiologists (P < .05). With model augmentation, the AUC, sensitivity, and specificity of the four radiologists increased significantly (P < .0001). Their sensitivity for detecting PC 2 cm and stage IA was better with than without augmentation (P < .0001), and their diagnostic time was significantly shortened (P < .0001) with augmentation.Interpretation : Our study established an economical, feasible and robust tool to screen PC and achieve excellent performance. The AI ensemble model significantly improved radiologists’ diagnostic performance, including that for small and early PC, significantly improved diagnostic time, and interrater reliability.Funding: This work was supported in part by the National Science Foundation for Scientists of China (81871352, 82171915, 82171930, and 82271972), The Natural Science Foundation of Shanghai Science and Technology Innovation Action Plan (21ZR1478500, 21Y11910300), Clinical Research Plan of SHDC (SHDC2020CR4073, SHDC2022CRD028), and 234 Platform Discipline Consolidation Foundation Project (2019YPT001, 2020YPT001).Declaration of Interest: The authors declare no potential conflicts of interest.Ethical Approval: This retrospective multicenter study was reviewed and approved by the Biomedical Research Ethics Committee of our institution (No. CHEC-Y2020-011)

Purpose: To evaluate the diagnostic performance of the radiomics score (rad-score) for differentiating focal-type autoimmune pancreatitis (fAIP) from pancreatic ductal adenocarcinoma (PDAC). Methods: This retrospective review included 42 consecutive patients with fAIP diagnosed according to the International Consensus Diagnostic Criteria between January 2011 and December 2018. Furthermore, 334 consecutive patients with PDAC confirmed by pathology were also reviewed during the same period. Patients with PDAC and fAIP were matched via propensity score matching (PSM). All patients underwent multidetector computed tomography (MDCT). For each patient, 1409 radiomics features of the portal phase were extracted and reduced using the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm. The portal rad-score performance was assessed based on its discriminative ability. Results: After PSM, we matched 55 patients with PDAC to 42 patients with fAIP, based on clinical and CT characteristics (e.g., patient age, sex, body mass index, location, size, enhanced mode). A rad-score for discriminating fAIP from PDAC, which contained four CT derived radiomic features, was developed (area under the curve = 0.97). The sensitivity, specificity, and accuracy of the radiomics model were 95.24%, 92.73% and 0.94, respectively. Conclusion: The portal rad-score can accurately and noninvasively differentiate fAIP from PDAC.

Purpose To develop and validate a radiomics model to predict fibroblast activation protein (FAP) expression in patients with pancreatic ductal adenocarcinoma (PDAC). Methods This retrospective study included consecutive 152 patients with PDAC who underwent MDCT scan and surgical resection from January 2017 to December 2017 (training set) and from January 2018 to April 2018 (validation set). In the training set, 1409 portal radiomic features were extracted from each patient's preoperative imaging. Optimal features were selected using the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm, whereupon the extreme gradient boosting (XGBoost) was developed using the radiomics features. The performance of the XGBoost classifier performance was assessed by its calibration, discrimination, and clinical usefulness. Results The patients were divided into FAP-low (n = 91; 59.87%) and FAP-high (n = 61; 40.13%) groups according to the optimal FAP cutoff (45.71%). Patients in the FAP-low group showed longer survival. The XGBoost classifier comprised 13 selected radiomics features and showed good discrimination in the training set [area under the curve (AUC), 0.97] and the validation set (AUC, 0.75). It also performed well in the calibration test and decision-curve analysis, demonstrating its potential clinical value. Conclusions The XGBoost classifier based on CT radiomics in the portal venous phase can non-invasively predict FAP expression and may help to improve clinical decision-making in patients with PDAC.

Background CD8 + T cell in pancreatic ductal adenocarcinoma (PDAC) is closely related to the prognosis and treatment response of patients. Accurate preoperative CD8 + T‐cell expression can better identify the population benefitting from immunotherapy. Purpose To develop and validate a machine learning classifier based on noncontrast magnetic resonance imaging (MRI) for the preoperative prediction of CD8 + T‐cell expression in patients with PDAC. Study Type Retrospective cohort study. Population Overall, 114 patients with PDAC undergoing MR scan and surgical resection; 97 and 47 patients in the training and validation cohorts. Field Strength/Sequence/3 T Breath‐hold single‐shot fast‐spin echo T2‐weighted sequence and noncontrast T1‐weighted fat‐suppressed sequences. Assessment CD8 + T‐cell expression was quantified using immunohistochemistry. For each patient, 2232 radiomics features were extracted from noncontrast T1‐ and T2‐weighted images and reduced using the Wilcoxon rank‐sum test and least absolute shrinkage and selection operator method. Linear discriminative analysis was used to construct radiomics and mixed models. Model performance was determined by its discriminative ability, calibration, and clinical utility. Statistical Tests Kaplan–Meier estimates, Student's t‐test, the Kruskal–Wallis H test, and the chi‐square test, receiver operating characteristic curve, and decision curve analysis. Results A log‐rank test showed that the survival duration in the CD8‐high group (25.51 months) was significantly longer than that in the CD8‐low group (22.92 months). The mixed model included all MRI characteristics and 13 selected radiomics features, and the area under the curve (AUC) was 0.89 (95% confidence interval [CI], 0.77–0.92) and 0.69 (95% CI, 0.53–0.82) in the training and validation cohorts. The radiomics model included 13 radiomics features, which showed good discrimination in the training cohort (AUC, 0.85; 95% CI, 0.77–0.92) and the validation cohort (AUC, 0.76; 95% CI, 0.61–0.87). Data Conclusions This study developed a noncontrast MRI‐based radiomics model that can preoperatively determine CD8 + T‐cell expression in patients with PDAC and potentially immunotherapy planning. Evidence Level 5 Technical Efficacy Stage 2

Purpose: To evaluate the diagnostic performance of the delayed-phase difference between tumor and pancreas for differentiating solid pseudopapillary tumors (SPTs) from non-functional neuroendocrine tumors (NF-NETS) of the pancreas. Methods: This retrospective review included 148 consecutive patients with SPT and 98 consecutive patients with NF-NET confirmed by pathology. Patients with SPT and NF-NET were matched via propensity score matching (PSM). All patients underwent multidetector computed tomography (MDCT). For each patient, the delayed-phase difference between the tumor and pancreas was measured, and the performance of this variable was assessed based on its discriminative ability and clinical utility. Results: After PSM, 27 patients with SPT and 27 patients with NF-NET were included in the matched analysis. There were no statistically significant differences in clinical and CT characteristics between the resulting two groups (p > 0.05). The delayed-phase difference values between the tumor and pancreas were significantly lower in patients with SPT (median: -0.45; range: -2.05 to 0.73) than in patients with NF-NET (median: 0.71; range: -1.39 to 2.38). The delayed-phase difference between tumor and pancreas had a high diagnostic accuracy (area under the curve=0.88). The best cutoff point based on maximizing the sum of the sensitivity and specificity was -0.23 (sensitivity = 88.89%; specificity = 88.89%; accuracy = 0.89). Conclusions: The delayed-phase difference between tumor and pancreas can accurately and noninvasively differentiate SPT from NF-NET.