DeepOrganNet: On-the-Fly Reconstruction and Visualization of 3D / 4D Lung Models from Single-View Projections by Deep Deformation Network

• Published in: IEEE transactions on visualization and computer graphics Vol. 26; no. 1; pp. 960 - 970
• Main Authors: Wang, Yifan, Zhong, Zichun, Hua, Jing
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 2D projections; 3D / 4D shapes; Accuracy; Algorithms; Apexes; Artificial neural networks; Biomedical imaging; Computational efficiency; Computed tomography; Computing time; Cone-Beam Computed Tomography; Deep deformation network; Deep Learning; Deformation; Human subjects; Humans; Image degradation; Image quality; Image reconstruction; Imaging, Three-Dimensional - methods; Lung - diagnostic imaging; Lung Neoplasms - diagnostic imaging; Lungs; Machine learning; Medical imaging; Neural Networks, Computer; organ meshes; Phantoms, Imaging; Radiation dosage; Radiation therapy; Real time; Shape; single-view; Solid modeling; Strain; Tensors; Three dimensional models; Three-dimensional displays; Two dimensional displays; Visualization

This paper introduces a deep neural network based method, i.e., DeepOrganNet, to generate and visualize fully high-fidelity 3D / 4D organ geometric models from single-view medical images with complicated background in real time. Traditional 3D / 4D medical image reconstruction requires near hundreds...