Multiparametric MRI analysis for the evaluation of renal function in patients with hyperuricemia: a preliminary study

Value of blood oxygenation level-dependent magnetic resonance imaging in early evaluation of the response and prognosis of esophageal squamous cell carcinoma treated with definitive chemoradiotherapy: a preliminary study

BACKGROUND

To find a useful hypoxia non-invasive biomarker for evaluating early treatment response and prognosis to definitive chemoradiotherapy (dCRT) in patients with esophageal squamous cell carcinoma (ESCC), using blood oxygenation level-dependent (BOLD) magnetic resonance imaging (MRI).

METHODS

The R2* values were obtained pre- and 2-3 weeks post-dCRT in 28 patients with ESCC using BOLD MRI. Independent samples t-test (normality) or Mann-Whitney U test (non-normality) was used to compare the differences of R2*-related parameters between the complete response (CR) and the non-CR groups. Diagnostic performance of parameters in predicting response was tested with receiver operating characteristic (ROC) curve analysis. The 3-year overall survival (OS) was evaluated using Kaplan Meier curve, log rank test, and Cox proportional hazards regression analysis.

RESULTS

The post-R2*, ∆R2*, and ∆%R2* in the CR group were significantly higher than those in the non-CR group (P = 0.002, 0.003, and 0.006, respectively). The R2*-related parameters showed good prediction of tumor response, with AUC ranging from 0.813 to 0.829. The 3-year OS rate in patients with ∆R2* >-7.54 s- 1 or CR were significantly longer than those with ∆R2* ≤ -7.54 s- 1 (72.37% vs. 0.00%; Hazard ratio, HR = 0.196; 95% confidence interval, 95% CI = 0.047-0.807; P = 0.024) or non-CR (76.47% vs. 29.27%; HR = 0.238, 95% CI = 0.059-0.963; P = 0.044).

CONCLUSIONS

The preliminary results demonstrated that the R2* value might be a useful hypoxia non-invasive biomarker for assessing response and prognosis of ESCC treated with dCRT. BOLD MRI might be used as a potential tool for evaluating tumor oxygenation metabolism, which is routinely applied in clinical practice and beneficial to clinical decision-making. A large sample size was needed for further follow-up studies to confirm the findings.

Style Transfer-assisted Deep Learning Method for Kidney Segmentation at Multiphase MRI

Purpose

To develop and validate a semisupervised style transfer-assisted deep learning method for automated segmentation of the kidneys using multiphase contrast-enhanced (MCE) MRI acquisitions.

Materials and Methods

This retrospective, Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included 125 patients (mean age, 57.3 years; 67 male, 58 female) with renal masses. Cohort 1 consisted of 102 coronal T2-weighted MRI acquisitions and 27 MCE MRI acquisitions during the corticomedullary phase. Cohort 2 comprised 92 MCE MRI acquisitions (23 acquisitions during four phases each, including precontrast, corticomedullary, early nephrographic, and nephrographic phases). The kidneys were manually segmented on T2-weighted images. A cycle-consistent generative adversarial network (CycleGAN) was trained to generate anatomically coregistered synthetic corticomedullary style images using T2-weighted images as input. Synthetic images for precontrast, early nephrographic, and nephrographic phases were then generated using the synthetic corticomedullary images as input. Mask region-based convolutional neural networks were trained on the four synthetic phase series for kidney segmentation using T2-weighted masks. Segmentation performance was evaluated in a different cohort of 20 originally acquired MCE MRI examinations by using Dice and Jaccard scores.

Results

The CycleGAN network successfully generated anatomically coregistered synthetic MCE MRI-like datasets from T2-weighted acquisitions. The proposed deep learning approach for kidney segmentation achieved high mean Dice scores in all four phases of the original MCE MRI acquisitions (0.91 for precontrast, 0.92 for corticomedullary, 0.91 for early nephrographic, and 0.93 for nephrographic).

Conclusion

The proposed deep learning approach achieved high performance in kidney segmentation on different MCE MRI acquisitions.Keywords: Kidney Segmentation, Generative Adversarial Network, CycleGAN, Convolutional Neural Network, Transfer Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.