Liu Z, et al. Korean J Radiol. 2020 Jun;21(6):736-745. https://doi.org/10.3348/kjr.2020.0171

Background: In magnetic resonance-guided high-intensity focused ultrasound (MR-HIFU) treatment of uterine fibroids, the immediate ablation response is significantly affected by blood perfusion. The variability of measurement for blood perfusion is critical due to the inherent non-uniformity of tumor perfusion and its dependence on reproducible region of interest (ROI) placement. Purpose: To investigate the value of whole-tumor ROI (ROIwt) analysis for quantitative perfusion in predicting immediate ablation response of uterine fibroids in MR-HIFU. Material and Methods: Thirty-one fibroids in 28 eligible patients were treated with MR-HIFU. Quantitative perfusion parameters (K^trans, K_ep, and V_p) derived from dynamic contrast-enhanced MRI were obtained before MR-HIFU treatment. The ROIwt and single-layer ROI (ROIsl) were used for quantitative perfusion analysis. T1 contrast-enhanced MRI immediately after MR-HIFU treatment was conducted to determine the non-perfused volume ratio (NPVR). Intraclass correlation coefficient (ICC) was used for consistency test. Spearman’s correlation and multivariate linear regression were used to investigate the predictors of the NPVR. Received operating characteristic (ROC) curve was used to test the predictive efficacy of quantitative perfusion parameter. Results: The intra- and inter-observer ICC of the quantitative perfusion parameters from ROIwt were higher than those from ROIsl. Multivariate analysis showed that the K^trans of ROIwt was a predictor of the immediate ablation response. ROC analysis displayed that the AUC of K^trans of ROIwt is 0.817 in predicting the ablation response. Conclusion: Pretreatment K^trans of ROIwt is more reliable and stable than that of ROIsl. It could be a predictor for the immediate ablation response of uterine fibroids in MR-HIFU.

Credit risk forecasting generally aims to evaluate the default probability of users in financial service. It is usually regarded as a binary classification problem, which suffers from the severe class-imbalance problem due to the extremely limited throngs and the concept drift problem brought by the delayed verification. In this paper, we investigate these problems in credit risk forecasting and propose a semi-supervised meta-learning based approach called TRUST (TRainable Undersampling with Self Training) to resolve. First, it decides whether to sample the data through meta-learning based reinforcement learning. Secondly, it learns the distribution of the data that have not yet shown financial performance via self-training and updates the model trained in the first step. Finally, the updated model is evaluated on the validation dataset, the result of which will be fed back through the evaluator. These three steps will be iterated until the model converges. With the real-world industrial dataset containing 1.75 million users, we investigate the effectiveness of our method. Experimental results exhibit that the proposed method is able to improve AP over 5.94% on credit risk forecasting task compared with the recent methods.

The spiculation sign is one of the main signs to distinguish benign and malignant pulmonary nodules. In order to effectively extract the image feature of a pulmonary nodule for the spiculation sign distinguishment, a new spiculation sign recognition model is proposed based on the doctors’ diagnosis process of pulmonary nodules. A maximum density projection model is established to fuse the local three‐dimensional information into the two‐dimensional image. The complete boundary of a pulmonary nodule is extracted by the improved Snake model, which can take full advantage of the parallel calculation of the Spike Neural P Systems to build a new neural network structure. In this paper, our experiments show that the proposed algorithm can accurately extract the boundary of a pulmonary nodule and effectively improve the recognition rate of the spiculation sign.

BACKGROUND AND PURPOSE: FOV optimized and constrained undistorted single-shot imaging provides relatively high-resolution images with few artifacts. This study evaluated the image quality and value of FOV optimized and constrained undistorted single-shot DWI in the evaluation of normal pituitary glands and pituitary macroadenomas. MATERIALS AND METHODS: Subjects with normal pituitary glands and patients with pituitary macroadenomas underwent FOV optimized and constrained undistorted single-shot and EPI DWI. Two neuroradiologists graded the image quality based on visualization of the pituitary stalk, pituitary gland, and pituitary macroadenoma. Intra- and interobserver agreements were assessed by κ statistics. Image quality and ADCs were compared between the 2 methods by the paired Wilcoxon signed rank test and t test. Differences in ADC between normal pituitary glands and macroadenomas were analyzed by the independent-samples t test. RESULTS: Twenty-eight subjects with normal pituitary glands and 16 patients with macroadenomas were enrolled. Intra- and interobserver agreements for image-quality assessment were moderate to substantial. Relative to EPI DWI, FOV optimized and constrained undistorted single-shot DWI exhibited obviously better image quality both in normal pituitary glands and macroadenomas. There was no significant difference in ADCs of macroadenomas between the 2 methods. Macroadenomas with soft consistency (0.75 ± 0.14 × 10⁻³ mm²/s) had significantly lower mean ADC than normal pituitary glands (1.18 ± 0.19 × 10⁻³ mm²/s; P < .001). CONCLUSIONS: FOV optimized and constrained undistorted single-shot DWI helps acquire high-resolution images of normal pituitary glands and pituitary macroadenomas with relatively few susceptibility artifacts in a clinically feasible scan time. This sequence might be helpful for evaluating the consistency of pituitary macroadenomas.