Image-to-Graph Convolutional Network for 2D/3D Deformable Model Registration of Low-Contrast Organs

被引:19
|
作者
Nakao, Megumi [1 ]
Nakamura, Mitsuhiro [2 ]
Matsuda, Tetsuya [1 ]
机构
[1] Kyoto Univ, Grad Sch Informat, Kyoto 6068501, Japan
[2] Kyoto Univ, Grad Sch Med, Kyoto 6068507, Japan
基金
日本学术振兴会;
关键词
Deep learning; deformable registration; graph convolutional network; abdominal organs; low-contrast images; 3D-2D REGISTRATION; VOLUME MANIPULATION; LEARNING FRAMEWORK; MOTION;
D O I
10.1109/TMI.2022.3194517
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Organ shape reconstruction based on a single-projection image during treatment has wide clinical scope, e.g., in image-guided radiotherapy and surgical guidance. We propose an image-to-graph convolutional network that achieves deformable registration of a three-dimensional (3D) organ mesh for a low-contrast two-dimensional (2D) projection image. This framework enables simultaneous training of two types of transformation: from the 2D projection image to a displacement map, and from the sampled per-vertex feature to a 3D displacement that satisfies the geometrical constraint of the mesh structure. Assuming application to radiation therapy, the 2D/3D deformable registration performance is verified for multiple abdominal organs that have not been targeted to date, i.e., the liver, stomach, duodenum, and kidney, and for pancreatic cancer. The experimental results show shape prediction considering relationships among multiple organs can be used to predict respiratory motion and deformation from digitally reconstructed radiographs with clinically acceptable accuracy.
引用
收藏
页码:3747 / 3761
页数:15
相关论文
共 50 条
  • [1] Linear and Deformable Image Registration with 3D Convolutional Neural Networks
    Stergios, Christodoulidis
    Mihir, Sahasrabudhe
    Maria, Vakalopoulou
    Guillaume, Chassagnon
    Marie-Pierre, Revel
    Stavroula, Mougiakakou
    Nikos, Paragios
    IMAGE ANALYSIS FOR MOVING ORGAN, BREAST, AND THORACIC IMAGES, 2018, 11040 : 13 - 22
  • [2] LiftReg: Limited Angle 2D/3D Deformable Registration
    Tian, Lin
    Lee, Yueh Z.
    Estepar, Raul San Jose
    Niethammer, Marc
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT VI, 2022, 13436 : 207 - 216
  • [3] An Unsupervised 3D Image Registration Network for Brain MRI Deformable Registration
    Huang, Min
    Ren, Guanyu
    Zhang, Shizheng
    Zheng, Qian
    Niu, Huiyang
    COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2022, 2022
  • [4] Deformable MRI-Ultrasound Registration Using 3D Convolutional Neural Network
    Sun, Li
    Zhang, Songtao
    SIMULATION, IMAGE PROCESSING, AND ULTRASOUND SYSTEMS FOR ASSISTED DIAGNOSIS AND NAVIGATION, 2018, 11042 : 152 - 158
  • [5] 2D/3D image registration using regression learning
    Chou, Chen-Rui
    Frederick, Brandon
    Mageras, Gig
    Chang, Sha
    Pizer, Stephen
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2013, 117 (09) : 1095 - 1106
  • [6] Local Metric Learning in 2D/3D Deformable Registration With Application in the Abdomen
    Zhao, Qingyu
    Chou, Chen-Rui
    Mageras, Gig
    Pizer, Stephen
    IEEE TRANSACTIONS ON MEDICAL IMAGING, 2014, 33 (08) : 1592 - 1600
  • [7] 3D/2D model-to-image registration by imitation learning for cardiac procedures
    Daniel Toth
    Shun Miao
    Tanja Kurzendorfer
    Christopher A. Rinaldi
    Rui Liao
    Tommaso Mansi
    Kawal Rhode
    Peter Mountney
    International Journal of Computer Assisted Radiology and Surgery, 2018, 13 : 1141 - 1149
  • [8] 3D/2D model-to-image registration by imitation learning for cardiac procedures
    Toth, Daniel
    Miao, Shun
    Kurzendorfer, Tanja
    Rinaldi, Christopher A.
    Liao, Rui
    Mansi, Tommaso
    Rhode, Kawal
    Mountney, Peter
    INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2018, 13 (08) : 1141 - 1149
  • [9] 3D Point Cloud Classification and Segmentation Model Based on Graph Convolutional Network
    Hou Xiangdan
    Yu Xixin
    Liu Hongpu
    LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (18)
  • [10] Deep Iterative 2D/3D Registration
    Jaganathan, Srikrishna
    Wang, Jian
    Borsdorf, Anja
    Shetty, Karthik
    Maier, Andreas
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT IV, 2021, 12904 : 383 - 392