Comparison of Two Software Packages for Perfusion Imaging: Ischemic Core and Penumbra Estimation and Patient Triage in Acute Ischemic Stroke.

Purpose: Automated postprocessing packages have been developed for managing acute ischemic stroke (AIS). These packages identify ischemic core and penumbra using either computed tomographic perfusion imaging (CTP) data or magnetic resonance imaging (MRI) data. Measurements of abnormal tissues and treatment decisions derived from different vendors can vary. The purpose of this study is to investigate the agreement of volumetric and decision-making outcomes derived from two software packages. Methods: A total of 594 AIS patients (174 underwent CTP and 420 underwent MRI) were included. Imaging data were accordingly postprocessed by two software packages: RAPID and RealNow. Volumetric outputs were compared between packages by performing intraclass correlation coefficient (ICC), Wilcoxon paired test and Bland-Altman analysis. Concordance of selecting patients eligible for mechanical thrombectomy (MT) was assessed based on neuroimaging criteria proposed in DEFUSE3. Results: In the group with CTP data, mean ischemic core volume (ICV)/penumbral volume (PV) was 14.9/81.1 mL via RAPID and 12.6/83.2 mL via RealNow. Meanwhile, in the MRI group, mean ICV/PV were 52.4/68.4 mL and 48.9/61.6 mL via RAPID and RealNow, respectively. Reliability, which was measured by ICC of ICV and PV in CTP and MRI groups, ranged from 0.87 to 0.99. The bias remained small between measurements (CTP ICV: 0.89 mL, CTP PV: -2 mL, MRI ICV: 3.5 mL and MRI PV: 6.8 mL). In comparison with CTP ICV with follow-up DWI, the ICC was 0.92 and 0.94 for RAPID and Realnow, respectively. The bias remained small between CTP ICV and follow-up DWI measurements (Rapid: -4.65 mL, RealNow: -3.65 mL). Wilcoxon paired test showed no significant difference between measurements. The results of patient triage were concordant in 159/174 cases (91%, ICC: 0.90) for CTP and 400/420 cases (95%, ICC: 0.93) for MRI. Conclusion: The CTP ICV derived from RealNow was more accurate than RAPID. The similarity in volumetric measurement between packages did not necessarily relate to equivalent patient triage. In this study, RealNow showed excellent agreement with RAPID in measuring ICV and PV as well as patient triage.

Preoperative Prediction of Pancreatic Neuroendocrine Neoplasms Grading Based on Enhanced Computed Tomography Imaging: Validation of Deep Learning with a Convolutional Neural Network.

INTRODUCTION: The pathological grading of pancreatic neuroendocrine neoplasms (pNENs) is an independent predictor of survival and indicator for treatment. Deep learning (DL) with a convolutional neural network (CNN) may improve the preoperative prediction of pNEN grading. METHODS: Ninety-three pNEN patients with preoperative contrast-enhanced computed tomography (CECT) from Hospital I were retrospectively enrolled. A CNN-based DL algorithm was applied to the CECT images to obtain 3 models (arterial, venous, and arterial/venous models), the performances of which were evaluated via an eightfold cross-validation technique. The CECT images of the optimal phase were used for comparing the DL and traditional machine learning (TML) models in predicting the pathological grading of pNENs. The performance of radiologists by using qualitative and quantitative computed tomography findings was also evaluated. The best DL model from the eightfold cross-validation was evaluated on an independent testing set of 19 patients from Hospital II who were scanned on a different scanner. The Kaplan-Meier (KM) analysis was employed for survival analysis. RESULTS: The area under the curve (AUC; 0.81) of arterial phase in validation set was significantly higher than those of venous (AUC 0.57, p = 0.03) and arterial/venous phase (AUC 0.70, p = 0.03) in predicting the pathological grading of pNENs. Compared with the TML models, the DL model gave a higher (although insignificantly) AUC. The highest OR was achieved for the p ratio <0.9, the AUC and accuracy for diagnosing G3 pNENs were 0.80 and 79.1% respectively. The DL algorithm achieved an AUC of 0.82 and an accuracy of 88.1% for the independent testing set. The KM analysis showed a statistical significant difference between the predicted G1/2 and G3 groups in the progression-free survival (p = 0.001) and overall survival (p < 0.001). CONCLUSION: The CNN-based DL method showed a relatively robust performance in predicting pathological grading of pNENs from CECT images.