A4 Article in conference proceedings
Lung CT Image Registration through Landmark-constrained Learning with Convolutional Neural Network (2020)
Hu, R., Wang, H., Ristaniemi, T., Zhu, W., & Sun, X. (2020). Lung CT Image Registration through Landmark-constrained Learning with Convolutional Neural Network. In EMBC 2020 : Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 1368-1371). IEEE. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. https://doi.org/10.1109/EMBC44109.2020.9176363
JYU authors or editors
Publication details
All authors or editors: Hu, Ruxue; Wang, Hongkai; Ristaniemi, Tapani; Zhu, Wentao; Sun, Xiaobang
Parent publication: EMBC 2020 : Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Place and date of conference: Montreal, QC, Canada, 20.-24.7.2020
ISBN: 978-1-7281-1991-5
eISBN: 978-1-7281-1990-8
Journal or series: Annual International Conference of the IEEE Engineering in Medicine and Biology Society
ISSN: 2375-7477
eISSN: 1557-170X
Publication year: 2020
Pages range: 1368-1371
Publisher: IEEE
Publication country: United States
Publication language: English
DOI: https://doi.org/10.1109/EMBC44109.2020.9176363
Publication open access: Not open
Publication channel open access:
Abstract
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.
Keywords: computed tomography; imaging; lungs; machine learning; neural networks (information technology)
Free keywords: lung CT image; neural networks
Contributing organizations
Ministry reporting: Yes
Reporting Year: 2020
JUFO rating: 1