Tianshu Zhou1, Tao Tan2, Xiaoyan Pan1, Hui Tang3, Jingsong Li1,4. 1. Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, China. 2. Department of Mathematics and Computer Science, Eindhoven University of Technology and Radiology, Netherlands Cancer Institute, Amsterdam, the Netherlands. 3. Biomedical Imaging Group Rotterdam, Departments of Radiology and Medical Informatics, Erasmus MC, 3000 CA Rotterdam, the Netherlands. 4. Research Center for Healthcare Data Science, Zhejiang Lab, Hangzhou, China.
Abstract
BACKGROUND: The objectives of this study were to develop a 3D convolutional deep learning framework (CarotidNet) for fully automatic segmentation of carotid bifurcations in computed tomography angiography (CTA) images and to facilitate the quantification of carotid stenosis and risk assessment of stroke. METHODS: Our pipeline was a two-stage cascade network that included a localization phase and a segmentation phase. The network framework was based on the 3D version of U-Net, but was refined in three ways: (I) by adding residual connections and a deep supervision strategy to cope with the vanishing problem in back-propagation; (II) by adopting dilated convolution in order to strengthen the capacity to capture contextual information; and (III) by establishing a hybrid objective function to address the extreme imbalance between foreground and background voxels. RESULTS: We trained our networks on 15 cases and evaluated their performance based on 41 cases from the MICCAI Challenge 2009 dataset. A Dice similarity coefficient of 82.3% was achieved for the test cases. CONCLUSIONS: We developed a carotid segmentation method based on U-Net that can segment tiny carotid bifurcation lumens from very large backgrounds with no manual intervention. This was the first attempt to use deep learning to achieve carotid bifurcation segmentation in 3D CTA images. Our results indicate that deep learning is a promising method for automatically extracting carotid bifurcation lumens. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.
BACKGROUND: The objectives of this study were to develop a 3D convolutional deep learning framework (CarotidNet) for fully automatic segmentation of carotid bifurcations in computed tomography angiography (CTA) images and to facilitate the quantification of carotid stenosis and risk assessment of stroke. METHODS: Our pipeline was a two-stage cascade network that included a localization phase and a segmentation phase. The network framework was based on the 3D version of U-Net, but was refined in three ways: (I) by adding residual connections and a deep supervision strategy to cope with the vanishing problem in back-propagation; (II) by adopting dilated convolution in order to strengthen the capacity to capture contextual information; and (III) by establishing a hybrid objective function to address the extreme imbalance between foreground and background voxels. RESULTS: We trained our networks on 15 cases and evaluated their performance based on 41 cases from the MICCAI Challenge 2009 dataset. A Dice similarity coefficient of 82.3% was achieved for the test cases. CONCLUSIONS: We developed a carotid segmentation method based on U-Net that can segment tiny carotid bifurcation lumens from very large backgrounds with no manual intervention. This was the first attempt to use deep learning to achieve carotid bifurcation segmentation in 3D CTA images. Our results indicate that deep learning is a promising method for automatically extracting carotid bifurcation lumens. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.
Entities:
Keywords:
Automatic lumen segmentation; U-Net; carotid stenosis; dominance of background voxels; large 3D volumes
Authors: Hongxia Zhang; Yan Cheng; Zhenbo Chen; Xinying Cong; Han Kang; Rongguo Zhang; Xiaojuan Guo; Min Liu Journal: Quant Imaging Med Surg Date: 2022-01
Authors: L Saba; C Loewe; T Weikert; M C Williams; N Galea; R P J Budde; R Vliegenthart; B K Velthuis; M Francone; J Bremerich; L Natale; K Nikolaou; J N Dacher; C Peebles; F Caobelli; A Redheuil; M Dewey; K F Kreitner; R Salgado Journal: Eur Radiol Date: 2022-10-04 Impact factor: 7.034