MRI-based machine learning models predict the malignant biological behavior of meningioma.

BACKGROUND: The WHO grade and Ki-67 index are independent indices used to evaluate the malignant biological behavior of meningioma. This study aims to develop MRI-based machine learning models to predict the malignant biological behavior of meningioma from the perspective of the WHO grade, Ki-67 index, and their combination. METHODS: This multicenter, retrospective study included 313 meningioma patients, of which 70 were classified as high-grade (WHO II/III) and 243 as low-grade (WHO I). The Ki-67 expression was classified into low-expression (n = 216) and high-expression (n = 97) groups with a threshold of 5%. Among them, there were 128 patients with malignant biological behavior whose WHO grade or Ki-67 index increased either or both. Data from Center A and B are were utilized for model development, while data from Center C and D were used for external validation. Radiomic features were extracted from the maximum cross-sectional area (2D) region of Interest (ROI) and the whole tumor volume (3D) ROI using different paraments from the T1, T2-weighted, and T1 contrast-enhanced sequences (T1CE), followed by five independent feature selections and eight classifiers. 240 prediction models were constructed to predict the WHO grade, Ki-67 index and their combination respectively. Models were evaluated by cross-validation in training set (n = 224). Suitable models were chosen by comparing the cross-validation (CV) area under the curves (AUC) and their relative standard deviations (RSD). Clinical and radiological features were collected and analyzed; meaningful features were combined with radiomic features to establish the clinical-radiological-radiomic (CRR) models. The receiver operating characteristic (ROC) analysis was used to evaluate those models in validation set. Radiomic models and CRR models were compared by Delong test. RESULTS: 1218 and 1781 radiomic features were extracted from 2D ROI and 3D ROI of each sequence. The selected grade, Ki-67 index and their combination radiomic models were T1CE-2D-LASSO-LR, T1CE-3D-LASSO-NB, and T1CE-2D-LASSO-LR, with cross-validated AUCs on the training set were 0.857, 0.798, and 0.888, the RSDs were 0.06, 0.09, and 0.05, the validation set AUCs were 0.829, 0.752, and 0.904, respectively. Heterogeneous enhancement was found to be associated with high grade and Ki-67 status, while surrounding invasion was associated with the high grade status, peritumoral edema and cerebrospinal fluid space surrounding tumor were correlated with the high Ki-67 status. The Delong test showed that these significant radiological features did not significantly improve the predictive performance. The AUCs for CRR models predicting grade, Ki-67 index, and their combination in the validation set were 0.821, 0.753, and 0.906, respectively. CONCLUSIONS: This study demonstrated that MRI-based machine learning models could effectively predict the grade, Ki-67 index of meningioma. Models considering these two indices might be valuable for improving the predictive sensitivity and comprehensiveness of prediction of malignant biological behavior of meningioma.

Evaluation of 18F-PSMA-1007 PET/CT in prostate cancer patients with biochemical recurrence after radical prostatectomy.

PURPOSE: Prostate-specific membrane antigen (PSMA) ligands targeting has shown promising results in staging of prostate cancer (PCa). The aim of present study was to evaluate the value of 18F-PSMA-1007 PET/CT in PCa patients with biochemical recurrence. METHODS: 71 patients with PCa after radical prostatectomy (RP) were included in the present study. Median prostate-specific antigen (PSA) level was 1.27 ng/mL (range 0.01-67.40 ng/mL, n = 69). All patients underwent whole-body PET/CT imaging after injection of 333±38 MBq 18F-PSMA-1007. The distribution of PSMA-positive lesions was assessed. The influence of PSA level, androgen deprivation therapy and primary Gleason score on PSMA-positive finding and uptake of 18F-PSMA-1007 were evaluated. RESULTS: 56 (79%) patients showed at least one pathological finding on 18F-PSMA-1007 PET/CT. The rates of positive scans were 50%, 80%, 100%, 100% among patients with PSA levels ≤0.5, 0.51-1.0, 1.1-2.0 and >2.0 ng/mL, respectively. The median Gleason score was 8 (range 7-10), and higher Gleason score (≤7 vs. ≥8) leads to higher detection rates (58.3% (14/24) vs. 88.9% (32/36), P = 0.006). The median SUVmax of positive findings in patients with PSA levels ≤0.5, 0.51-1.0, 1.1-2.0 and >2.0 ng/mL were 4.51, 4.27, 11.50 and 14.08, respectively. The median SUVmax in patients with PSA level >2.0 ng/mL was significantly higher than that in patients with PSA ≤2.0 ng/mL (14.08 vs. 6.13, P<0.001). CONCLUSION: 18F-PSMA-1007 PET/CT demonstrated a high detection rate for patients with a raised PSA level after radical prostatectomy even in patients with extremely low PSA level (eg. PSA level ≤0.5 ng/mL), which was essential for further clinical management for PCa patients.

Relationship of epicardial fat volume with coronary plaque characteristics, coronary artery calcification score, coronary stenosis, and CT-FFR for lesion-specific ischemia in patients with known or suspected coronary artery disease.

BACKGROUND: We explored the association of epicardial fat volume (EFV) with coronary plaque characteristics, coronary artery calcification (CAC) score, coronary stenosis, lesion-specific ischemia in patients with known or suspected coronary artery disease (CAD). METHODS: 88 controls and 221 patients were analyzed in the study. High-risk plaque was defined as existing≥2 features, including positive remodeling, low attenuation, napkin-ring sign and spotty calcification. EFV, CAC score was measured. The severity of coronary stenosis was quantified using Gensini score. CT-FFR was performed in three major coronary arteries, with a threshold of ≤0.8 considered the presence of ischemia. Univariate and multivariate regression was used to evaluate the association of EFV with CAD, palque characteristics, CAC score, Gensini score, and lesion-specific ischemia derived from CT-FFR. RESULTS: Median EFV was 104.97 cm3 (85.47-136.09) in controls and 129.28cm3 (101.19-159.44) in patients (P < 0.001). Logistic regression analysis revealed a significant association of EFV with CAD even after adjusting for confounding factors (P < 0.05). At linear regression analysis, EFV was significantly correlated with high-risk plaque and lesion-specific ischemia, but not with non-calcified plaque, mixed plaque, calcified plaque, CAC score and Gensini score (P ≥ 0.05). CONCLUSION: We found that EFV was associated with CAD, suggesting that it may be a promising marker of CAD. EFV was also correlated with high-risk plaque and lesion-specific ischemia, indicating that EAT was likely to be involved in myocardial ischemia and had the potential to definite patients' risk profile.