Biomedical Engineering Department, Eindhoven University of Technology, Eindhoven, The Netherlands.
Philips Research Laboratories, Hamburg, Germany.
Comput Biol Med. 2024 Dec;183:109301. doi: 10.1016/j.compbiomed.2024.109301. Epub 2024 Oct 31.
In the field of medical imaging, high-resolution (HR) magnetic resonance imaging (MRI) is essential for accurate disease diagnosis and analysis. However, HR imaging is prone to artifacts and is not universally available. Consequently, low-resolution (LR) MRI images are typically acquired. Deep learning (DL)-based super-resolution (SR) techniques can transform LR images into HR quality. However, these techniques require paired HR-LR data for training the SR networks.
This research aims to investigate the potential of simulated brain MRI data to train DL-based SR networks.
We simulated a large set of anatomically diverse, voxel-aligned, and artifact-free brain MRI data at different resolutions. We utilized this simulated data to train four distinct DL-based SR networks and augment their training. The trained networks were then evaluated using real data from various sources.
With our trained networks, we produced 0.7mm SR images from standard 1mm resolution multi-source T1w brain MRI. Our experimental results demonstrate that the trained networks significantly enhance the sharpness of LR input MR images. For single-source images, the performance of networks trained solely on simulated data is slightly inferior to those trained solely on real data, with an average structural similarity index (SSIM) difference of 0.025. However, networks augmented with simulated data outperform those trained on single-source real data when evaluated across datasets from multiple sources.
Paired HR-LR simulated brain MRI data is suitable for training and augmenting diverse brain MRI SR networks. Augmenting the training data with simulated data can enhance the generalizability of the SR networks across real datasets from multiple sources.
在医学成像领域，高分辨率（HR）磁共振成像（MRI）对于准确的疾病诊断和分析至关重要。然而，HR 成像容易出现伪影，并且并非普遍可用。因此，通常会采集低分辨率（LR）MRI 图像。基于深度学习（DL）的超分辨率（SR）技术可以将 LR 图像转换为 HR 质量。然而，这些技术需要 HR-LR 配对数据来训练 SR 网络。
本研究旨在探讨模拟脑 MRI 数据在训练基于 DL 的 SR 网络方面的潜力。
我们模拟了大量解剖结构多样、体素对齐且无伪影的不同分辨率的脑 MRI 数据。我们利用这些模拟数据来训练四个不同的基于 DL 的 SR 网络，并扩充它们的训练。然后，我们使用来自不同来源的真实数据评估训练后的网络。
使用我们训练的网络，我们从标准的 1mm 分辨率多源 T1w 脑 MRI 生成了 0.7mm 的 SR 图像。我们的实验结果表明，训练后的网络显著提高了 LR 输入 MR 图像的清晰度。对于单源图像，仅使用模拟数据训练的网络的性能略逊于仅使用真实数据训练的网络，平均结构相似性指数（SSIM）差异为 0.025。然而，当在来自多个来源的多个数据集上进行评估时，使用模拟数据扩充训练数据的网络表现优于仅使用单源真实数据训练的网络。
配对的 HR-LR 模拟脑 MRI 数据适合训练和扩充各种脑 MRI SR 网络。使用模拟数据扩充训练数据可以增强 SR 网络在来自多个来源的真实数据集上的泛化能力。
