Maciel Corbin, Zou Qing
Department of Biomedical Engineering, The University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
Division of Pediatric Cardiology, Department of Pediatrics, The University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
Bioengineering (Basel). 2025 Jan 30;12(2):129. doi: 10.3390/bioengineering12020129.
This work aims to develop a three-dimensional (3D) super-resolution (SR) network that would perform arbitrary-scale 3D whole-heart (WH) magnetic resonance imaging (MRI) super-resolution, while maintaining fine image details. One-hundred-twenty 3D WH MR volumes, acquired using four different sequences, are used in this study for training, validation, and testing. The proposed method utilizes a frequency-domain regularization in training to maintain fine image detail along with a 3D autoencoder framework. It is also trained in manner to enable it to perform arbitrary factor SR. The proposed method is compared against multiple super-resolution algorithms including two state-of-the-art deep learning methods referred to here as ACNS and TFC as well as nearest neighbor interpolation. The proposed method was evaluated quantitatively and compared against the competing methods with the mean result of the proposed method and the improvements provided by the proposed method (reported by mean percentage between the proposed method and all other competing methods) were recorded. The metrics of interest used for the quantitative comparison are peak signal-to-noise ratio (PSNR, mean = 34.10, mean percentage of improvement = 4.5%), structural similarity index measure (SSIM, mean = 0.94, mean percentage of improvement = 2.2%), mean squared error (MSE, mean = 0.00094, mean percentage of improvement = 48.2%), and root mean squared error (RMSE, mean = 0.024, mean percentage of improvement = 31.0%). Moreover, qualitative comparison was performed using multiple visual comparisons. The quantitative results achieved demonstrate that the proposed method regularly outperforms all other comparison methods. The visual comparisons demonstrate that the proposed method outperforms current state-of-the-art methods in preserving fine image details, as well as its ability to do so for multiple SR factors.
这项工作旨在开发一种三维（3D）超分辨率（SR）网络，该网络能够对任意尺度的三维全心（WH）磁共振成像（MRI）进行超分辨率处理，同时保持精细的图像细节。本研究使用通过四种不同序列采集的120个三维WH MR容积进行训练、验证和测试。所提出的方法在训练中利用频域正则化来保持精细的图像细节，并采用三维自动编码器框架。它还经过训练，能够执行任意因子的超分辨率。将所提出的方法与多种超分辨率算法进行比较，包括两种在此称为ACNS和TFC的最新深度学习方法以及最近邻插值法。对所提出的方法进行了定量评估，并与竞争方法进行比较，记录了所提出方法的平均结果以及所提出方法带来的改进（以所提出方法与所有其他竞争方法之间的平均百分比报告）。用于定量比较的感兴趣指标包括峰值信噪比（PSNR，平均值 = 34.10，平均改进百分比 = 4.5%）、结构相似性指数测量（SSIM，平均值 = 0.94，平均改进百分比 = 2.2%）、均方误差（MSE，平均值 = 0.00094，平均改进百分比 = 48.2%）和均方根误差（RMSE，平均值 = 0.024，平均改进百分比 = 31.0%）。此外，还通过多次视觉比较进行了定性比较。所取得的定量结果表明，所提出的方法通常优于所有其他比较方法。视觉比较表明，所提出的方法在保留精细图像细节方面优于当前的最先进方法，并且对于多个超分辨率因子都具有这样的能力。
