IEEE Trans Med Imaging. 2020 Dec;39(12):4011-4022. doi: 10.1109/TMI.2020.3009002. Epub 2020 Nov 30.
In this study, we propose a fast and accurate method to automatically localize anatomical landmarks in medical images. We employ a global-to-local localization approach using fully convolutional neural networks (FCNNs). First, a global FCNN localizes multiple landmarks through the analysis of image patches, performing regression and classification simultaneously. In regression, displacement vectors pointing from the center of image patches towards landmark locations are determined. In classification, presence of landmarks of interest in the patch is established. Global landmark locations are obtained by averaging the predicted displacement vectors, where the contribution of each displacement vector is weighted by the posterior classification probability of the patch that it is pointing from. Subsequently, for each landmark localized with global localization, local analysis is performed. Specialized FCNNs refine the global landmark locations by analyzing local sub-images in a similar manner, i.e. by performing regression and classification simultaneously and combining the results. Evaluation was performed through localization of 8 anatomical landmarks in CCTA scans, 2 landmarks in olfactory MR scans, and 19 landmarks in cephalometric X-rays. We demonstrate that the method performs similarly to a second observer and is able to localize landmarks in a diverse set of medical images, differing in image modality, image dimensionality, and anatomical coverage.
在这项研究中，我们提出了一种快速而准确的方法，能够自动定位医学图像中的解剖学标志。我们采用了基于全卷积神经网络（FCNN）的全局到局部定位方法。首先，全局 FCNN 通过分析图像块来定位多个标志，同时进行回归和分类。在回归中，确定从图像块中心指向标志位置的位移向量。在分类中，确定感兴趣的标志是否存在于图像块中。通过平均预测的位移向量来获得全局标志位置，其中每个位移向量的贡献由它所指向的图像块的后验分类概率加权。然后，对每个用全局定位定位的标志进行局部分析。专门的 FCNN 通过以类似的方式分析局部子图像来细化全局标志位置，即同时进行回归和分类，并组合结果。通过对 CCTA 扫描中的 8 个解剖学标志、嗅觉 MR 扫描中的 2 个标志和头影测量 X 射线中的 19 个标志的定位，对该方法进行了评估。我们证明该方法的性能与第二名观察者相当，并且能够定位多种医学图像中的标志，这些图像在模态、图像维度和解剖覆盖范围上有所不同。
