Reinhold Jacob C, Dewey Blake E, Carass Aaron, Prince Jerry L
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA 21218.
F.M. Kirby Center for Functional Brain Imaging, Kennedy Krieger Institute, Baltimore, MD, USA, 21205.
Proc SPIE Int Soc Opt Eng. 2019 Mar;10949. doi: 10.1117/12.2513089.
Image synthesis learns a transformation from the intensity features of an input image to yield a different tissue contrast of the output image. This process has been shown to have application in many medical image analysis tasks including imputation, registration, and segmentation. To carry out synthesis, the intensities of the input images are typically scaled-i.e., normalized-both in training to learn the transformation and in testing when applying the transformation, but it is not presently known what type of input scaling is optimal. In this paper, we consider seven different intensity normalization algorithms and three different synthesis methods to evaluate the impact of normalization. Our experiments demonstrate that intensity normalization as a preprocessing step improves the synthesis results across all investigated synthesis algorithms. Furthermore, we show evidence that suggests intensity normalization is vital for successful deep learning-based MR image synthesis.
图像合成学习从输入图像的强度特征进行转换，以产生输出图像的不同组织对比度。这一过程已被证明在许多医学图像分析任务中都有应用，包括插补、配准和分割。为了进行合成，输入图像的强度通常在训练中进行缩放（即归一化）以学习转换，在测试中应用转换时也进行缩放，但目前尚不清楚哪种类型的输入缩放是最优的。在本文中，我们考虑了七种不同的强度归一化算法和三种不同的合成方法，以评估归一化的影响。我们的实验表明，强度归一化作为预处理步骤可改善所有研究的合成算法的合成结果。此外，我们还表明有证据表明强度归一化对于基于深度学习的磁共振图像合成的成功至关重要。
