Hu Ruxue, Wang Hongkai, Ristaniemi Tapani, Zhu Wentao, Sun Xiaobang
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:1368-1371. doi: 10.1109/EMBC44109.2020.9176363.
Accurate registration of lung computed tomography (CT) image is a significant task in thorax image analysis. Recently deep learning-based medical image registration methods develop fast and achieve promising performance on accuracy and speed. However, most of them learned the deformation field through intensity similarity but ignored the importance of aligning anatomical landmarks (e.g., the branch points of airway and vessels). Accurate alignment of anatomical landmarks is essential for obtaining anatomically correct registration. In this work, we propose landmark constrained learning with a convolutional neural network (CNN) for lung CT registration. Experimental results of 40 lung 3D CT images show that our method achieves 0.93 in terms of Dice index and 3.54 mm of landmark Euclidean distance on lung CT registration task, which outperforms state-of-the-art methods in registration accuracy.
肺部计算机断层扫描（CT）图像的精确配准是胸部图像分析中的一项重要任务。近年来，基于深度学习的医学图像配准方法发展迅速，在准确性和速度方面取得了令人满意的性能。然而，它们大多通过强度相似性来学习变形场，却忽略了对齐解剖标志点（如气道和血管的分支点）的重要性。解剖标志点的精确对齐对于获得解剖学上正确的配准至关重要。在这项工作中，我们提出了一种基于卷积神经网络（CNN）的用于肺部CT配准的地标约束学习方法。对40幅肺部3D CT图像的实验结果表明，我们的方法在肺部CT配准任务中，Dice指数达到0.93，地标欧几里得距离为3.54毫米，在配准精度方面优于现有方法。
