Department of Computer Science and Engineering, Indian Institute of Technology Patna, Bihta, 801103, India.
MAGMA. 2022 Jun;35(3):449-457. doi: 10.1007/s10334-021-00974-5. Epub 2021 Nov 6.
In medical domain, cross-modality image synthesis suffers from multiple issues , such as context-misalignment, image distortion, image blurriness, and loss of details. The fundamental objective behind this study is to address these issues in estimating synthetic Computed tomography (sCT) scans from T2-weighted Magnetic Resonance Imaging (MRI) scans to achieve MRI-guided Radiation Treatment (RT).
We proposed a conditional generative adversarial network (cGAN) with multiple residual blocks to estimate sCT from T2-weighted MRI scans using 367 paired brain MR-CT images dataset. Few state-of-the-art deep learning models were implemented to generate sCT including Pix2Pix model, U-Net model, autoencoder model and their results were compared, respectively.
Results with paired MR-CT image dataset demonstrate that the proposed model with nine residual blocks in generator architecture results in the smallest mean absolute error (MAE) value of [Formula: see text], and mean squared error (MSE) value of [Formula: see text], and produces the largest Pearson correlation coefficient (PCC) value of [Formula: see text], SSIM value of [Formula: see text] and peak signal-to-noise ratio (PSNR) value of [Formula: see text], respectively. We qualitatively evaluated our result by visual comparisons of generated sCT to original CT of respective MRI input.
The quantitative and qualitative comparison of this work demonstrates that deep learning-based cGAN model can be used to estimate sCT scan from a reference T2 weighted MRI scan. The overall accuracy of our proposed model outperforms different state-of-the-art deep learning-based models.
在医学领域，跨模态图像合成存在多个问题，例如上下文失配、图像失真、图像模糊和细节丢失。本研究的基本目标是解决这些问题，以便从 T2 加权磁共振成像（MRI）扫描中估计合成计算机断层扫描（sCT）扫描，从而实现 MRI 引导的放射治疗（RT）。
我们提出了一种具有多个残差块的条件生成对抗网络（cGAN），使用 367 对脑 MR-CT 图像数据集从 T2 加权 MRI 扫描中估计 sCT。实施了几种最先进的深度学习模型来生成 sCT，包括 Pix2Pix 模型、U-Net 模型、自动编码器模型，并分别比较了它们的结果。
使用配对的 MR-CT 图像数据集的结果表明，在生成器架构中具有九个残差块的建议模型导致最小的平均绝对误差（MAE）值为[Formula: see text]，平均平方误差（MSE）值为[Formula: see text]，产生最大的皮尔逊相关系数（PCC）值为[Formula: see text]，结构相似性指数（SSIM）值为[Formula: see text]和峰值信噪比（PSNR）值为[Formula: see text]，分别。我们通过将生成的 sCT 与各自 MRI 输入的原始 CT 进行视觉比较来定性评估我们的结果。
这项工作的定量和定性比较表明，基于深度学习的 cGAN 模型可用于从参考 T2 加权 MRI 扫描中估计 sCT 扫描。我们提出的模型的整体准确性优于不同的最先进的基于深度学习的模型。
