Development of MRI-Based Radiomics Model to Predict the Risk of Recurrence in Patients With Advanced High-Grade Serous Ovarian Carcinoma.

OBJECTIVE. The purpose of our study was to develop a radiomics model based on preoperative MRI and clinical information for predicting recurrence-free survival (RFS) in patients with advanced high-grade serous ovarian carcinoma (HGSOC). MATERIALS AND METHODS. This retrospective study enrolled 117 patients with HGSOC, including 90 patients with recurrence and 27 without recurrence; 1046 radiomics features were extracted from T2-weighted images and contrast-enhanced T1-weighted images using a manual segmentation method. L1 regularization-based least absolute shrinkage and selection operator (LASSO) regression was performed to select features, and the synthetic minority oversampling technique (SMOTE) was used to balance our dataset. A support vector machine (SVM) classifier was used to build the classification model. To validate the performance of the proposed models, we applied a leave-one-out cross-validation method to train and test the classifier. Cox proportional hazards regression, Harrell concordance index (C-index), and Kaplan-Meier plots analysis were used to evaluate the associations between radiomics signatures and RFS. RESULTS. The fusion radiomics-based model yielded a significantly higher AUC value of 0.85 in evaluating RFS than the model using contrast-enhanced T1-weighted imaging features alone or T2-weighted imaging features alone (AUC = 0.79 and 0.74 and p = .02 and .01, respectively). Kaplan-Meier survival curves showed significant differences between high and low recurrence risk in patients with HGSOC by different models. The fusion model combining radiomics features and clinical information showed higher performance than the clinical model (C-index = 0.62 and 0.60, respectively). CONCLUSION. The proposed MRI-based radiomics signatures may provide a potential way to develop a prediction model and can help identify patients with advanced HGSOC who have a high risk of recurrence.

Dynamic contrast-enhanced magnetic resonance imaging and diffusion-weighted imaging in the activity staging of terminal ileum Crohn's disease.

BACKGROUND: The activity staging of Crohn's disease (CD) in the terminal ileum is critical in developing an accurate clinical treatment plan. The activity of terminal ileum CD is associated with the microcirculation of involved bowel walls. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion-weighted imaging (DWI) can reflect perfusion and permeability of bowel walls by providing microcirculation information. As such, we hypothesize that DCE-MRI and DWI parameters can assess terminal ileum CD, thereby providing an opportunity to stage CD activity. AIM: To evaluate the value of DCE-MRI and DWI in assessing activity of terminal ileum CD. METHODS: Forty-eight patients with CD who underwent DCE-MRI and DWI were enrolled. The patients' activity was graded as remission, mild and moderate-severe. The transfer constant (Ktrans), wash-out constant (Kep), and extravascular extracellular volume fraction (Ve) were calculated from DCE-MRI and the apparent diffusion coefficient (ADC) was obtained from DWI. Magnetic Resonance Index of Activity (MaRIA) was calculated from magnetic resonance enterography. Differences in these quantitative parameters were compared between normal ileal loop (NIL) and inflamed terminal ileum (ITI) and among different activity grades. The correlations between these parameters, MaRIA, the Crohn's Disease Activity Index (CDAI), and Crohn's Disease Endoscopic Index of Severity (CDEIS) were examined. Receiver operating characteristic curve analyses were used to determine the diagnostic performance of these parameters in differentiating between CD activity levels. RESULTS: Higher Ktrans (0.07 ± 0.04 vs 0.01 ± 0.01), Kep (0.24 ± 0.11 vs 0.15 ± 0.05) and Ve (0.27 ± 0.07 vs 0.08 ± 0.03), but lower ADC (1.41 ± 0.26 vs 2.41 ± 0.30) values were found in ITI than in NIL (all P < 0.001). The Ktrans, Kep, Ve and MaRIA increased with disease activity, whereas the ADC decreased (all P < 0.001). The Ktrans, Kep, Ve and MaRIA showed positive correlations with the CDAI (r = 0.866 for Ktrans, 0.870 for Kep, 0.858 for Ve, 0.890 for MaRIA, all P < 0.001) and CDEIS (r = 0.563 for Ktrans, 0.567 for Kep, 0.571 for Ve, 0.842 for MaRIA, all P < 0.001), while the ADC showed negative correlations with the CDAI (r = -0.857, P < 0.001) and CDEIS (r = -0.536, P < 0.001). The areas under the curve (AUC) for the Ktrans, Kep, Ve, ADC and MaRIA values ranged from 0.68 to 0.91 for differentiating inactive CD (CD remission) from active CD (mild to severe CD). The AUC when combining the Ktrans, Kep and Ve was 0.80, while combining DCE-MRI parameters and ADC values yielded the highest AUC of 0.95. CONCLUSION: DCE-MRI and DWI parameters all serve as measures to stage CD activity. When they are combined, the assessment performance is improved and better than MaRIA.

Changes in DTI parameters in the optic tracts of macaque monkeys with monocular blindness.

For humans and non-human primates, the alteration of the visual pathway's white matter fibers after visual deprivation has been partially explored. However, the changes in the optic tracts after the transection of the optic nerve have not been well characterized. In the current study, we attempted to investigate the differences in optic tracts between normal and unilateral optic nerve transected macaque monkeys using diffusion tensor imaging (DTI). Four healthy neonatal macaque monkeys were randomly divided into 2 groups, with 2 in each group. Group A served as a control group, and Group B underwent unilateral (right eye) optic nerve transection to produce monocular blindness. Sixteen months (Group B16M) and thirty-two months (Group B32M) after optic nerve transection, diffusion tensor imaging was performed on all monkeys. Then, we compared fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD) and radial diffusivity (RD) in bilateral optic tracts between Group A and Group B and between Group B16M and Group B32M. In both Group B16M and Group B32M, when compared with normal monkeys in Group A, FA was decreased and MD, AD and RD were increased in the bilateral optic tracts of monkeys with monocular blindness. Furthermore, compared with Group B16M, FA was reduced and MD, AD, RD were more obviously increased in the bilateral optic tracts of Group B32M, and noticeable differences in MD, AD and RD were found between the left and right optic tracts in group B32M. We believe that the results of this study would be helpful in investigation of the histological abnormalities of the integrity damage, axonal degeneration and demyelination of optic tracts in macaque monkeys with monocular blindness by DTI parameters in noninvasively and quantitatively.