Combination of Hematoma Volume and Perihematoma Radiomics Analysis on Baseline CT Scan Predicts the Growth of Perihematomal Edema.

PURPOSE: The aim is to explore the potential value of CT-based radiomics in predicting perihematomal edema (PHE) volumes after acute intracerebral hemorrhage (ICH) from admission to 24 h. METHODS: A total of 231 patients newly diagnosed with acute ICH at two institutes were analyzed retrospectively. The patients were randomly divided into training (N = 117) and internal validation cohort (N = 45) from institute 1 with a ratio of 7:3. According to radiomics features extracted from baseline CT, the radiomics signatures were constructed. Multiple logistic regression analysis was used for clinical radiological factors and then the nomogram model was generated to predict the extent of PHE according to the optimal radiomics signature and the clinical radiological factors. The receiver operating characteristic (ROC) curve was used to evaluate the discrimination performance. The calibration curve and Hosmer-Lemeshow test were used to evaluate the consistency between the predicted and actual probability. The support vector regression (SVR) model was constructed to predict the overall value of follow-up PHE. The performance of the models was evaluated on the internal and independent validation cohorts. RESULTS: The perihematoma 5 mm radiomics signature (AUC: 0.875) showed good ability to discriminate the small relative PHE(rPHE) from large rPHE volumes, comparing to intrahematoma radiomics signature (AUC: 0.711) or perihematoma 10 mm radiomics signature (AUC: 0.692) on the training cohort. The AUC of the combined nomogram model was 0.922 for the training cohort, 0.945 and 0.902 for the internal and independent validation cohorts, respectively. The calibration curves and Hosmer-Lemeshow test of the nomogram model suggested that the predictive performance and actual outcome were in favorable agreement. The SVR model also predicted the overall value of follow-up rPHE (root mean squared error, 0.60 and 0.45; Pearson correlation coefficient, 0.73 and 0.68; P < 0.001). CONCLUSION: Among patients with acute ICH, the established nomogram and SVR model with favorable performance can offer a noninvasive tool for the prediction of PHE after ICH.

Magnetic resonance diffusion kurtosis imaging in differential diagnosis of benign and malignant renal tumors.

BACKGROUND: Benign and malignant renal tumors share similar some imaging findings. METHODS: Sixty-six patients with clear cell renal cell carcinoma (CCRCC), 13 patients with renal angiomyolipoma with minimal fat (RAMF) and 7 patients with renal oncocytoma (RO) were examined. For diffusion kurtosis imaging (DKI), respiratory triggered echo-planar imaging sequences were acquired in axial plane (3 b-values: 0, 500, 1000s/mm2). Mean Diffusivity (MD), fractional Anisotropy (FA), mean kurtosis (MK), kurtosis anisotropy (KA) and radial kurtosis (RK) were performed. RESULTS: For MD, a significant higher value was shown in CCRCC (3.08 ± 0.23) than the rest renal tumors (2.93 ± 0.30 for RO, 1.52 ± 0.24 for AML, P < 0.05). The MD values were higher for RO than for AML (2.93 ± 0.30 vs.1.52 ± 0.24, P < 0.05), while comparable MD values were found between CCRCC and RO (3.08 ± 0.23 vs. 2.93 ± 0.30, P > 0.05). For MK, KA and RK, a significant higher value was shown in AML (1.32 ± 0.16, 1.42 ± 0.23, 1.41 ± 0.29) than CCRCC (0.43 ± 0.08, 0.57 ± 0.16, 0.37 ± 0.11) and RO (0.81 ± 0.08, 0.86 ± 0.16, 0.69 ± 0.08) (P < 0.05). The MK, KA and RK values were higher for RO than for CCRCC (0.81 ± 0.08 vs. 0.43 ± 0.08, 0.86 ± 0.16 vs. 0.57 ± 0.16, 0.69 ± 0.08 vs. 0.37 ± 0.11, P < 0.05). Using MD values of 2.86 as the threshold value for differentiating CCRCC from RO and AML, the best result obtained had a sensitivity of 76.1%, specificity of 72.6%. Using MK, KA and RK values of 1.19,1.13 and 1.11 as the threshold value for differentiating AML from CCRCC and RO, the best result obtained had a sensitivity of 91.2, 86.7, 82.1%, and specificity of 86.7, 83.2, 72.8%. CONCLUSION: DKI can be used as another noninvasive biomarker for benign and malignant renal tumors' differential diagnosis.

[Differential diagnosis between renal cell carcinoma associated with XP11.2 translocation/TFE gene fusion and papillary renal cell carcinoma based on CT and MRI findings].

OBJECTIVE: To comparative study of CT and MRI appearances in renal cell carcinoma associated with XP11.2 translocation/TFE gene fusion (XP11.2 RCC) and papillary renal cell carcinoma (PRCC). METHODS: 12 patients with XP11.2 RCC and 18 patients with PRCC were retrospectively studied, and the data was analyzed by AVONA and chi-square text. RESULTS: 12 patients with XP11.2 RCC and 18 patients with PRCC, cystic components (2 vs 11, P < 0.05), calcification (0 vs 6, P < 0.05), hemorrhage (9 vs 5, P < 0.05), homogeneous enhancement (10 vs 7, P < 0.05) and had lymph node (3 vs 0) or hepatic metastasis (1vs 0) (P < 0.05). On unenhanced CT, the density of XP11.2 RCC was greater than PRCC, normal renal cortex or medulla (P < 0.05). Their degree of enhancement were less than normal renal cortex on all enhanced phases (P < 0.05). The enhancement degree of XP11.2 RCC was higher than PRCC (on all phases) and renal medulla (on cortical and medullary phase) (P < 0.05), but less than normal renal medulla on the delayed phase (P < 0.05). The enhancement degree of PRCC was lower than renal medulla on all phases (P < 0.05). The XP11.2 RCC was isointense on T1-weighted imaging, hypointense on T2-weighted imaging. The PRCC was isointense or hypointense on T1-weighted imaging, isointense on T2-weighted imaging. CONCLUSION: The CT and MRI could show imagings features of XP11.2 RCC and PRCC, and these features were helpful in predicting a specific subtype of renal cell carcinoma.