3D segmentation using space carving and 2D convolutional neural networks
Abstract
A system for generating a 3D segmentation of a target volume is provided. The system accesses views of an X-ray scan of a target volume. The system applies a 2D CNN to each view to generate a 2D multi-channel feature vector for each view. The system applies a space carver to generate a 3D channel volume for each channel based on the 2D multi-channel feature vectors. The system then applies a linear combining technique to the 3D channel volumes to generate a 3D multi-label map that represents a 3D segmentation of the target volume.
- Inventors:
- Issue Date:
- Research Org.:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1987089
- Patent Number(s):
- 11568656
- Application Number:
- 17/032,377
- Assignee:
- Lawrence Livermore National Security, LLC (Livermore, CA)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G - PHYSICS G06 - COMPUTING G06T - IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- DOE Contract Number:
- AC52-07NA27344
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 09/25/2020
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING
Citation Formats
Mohan, Kadri Aditya, and Champley, Kyle. 3D segmentation using space carving and 2D convolutional neural networks. United States: N. p., 2023.
Web.
Mohan, Kadri Aditya, & Champley, Kyle. 3D segmentation using space carving and 2D convolutional neural networks. United States.
Mohan, Kadri Aditya, and Champley, Kyle. Tue .
"3D segmentation using space carving and 2D convolutional neural networks". United States. https://www.osti.gov/servlets/purl/1987089.
@article{osti_1987089,
title = {3D segmentation using space carving and 2D convolutional neural networks},
author = {Mohan, Kadri Aditya and Champley, Kyle},
abstractNote = {A system for generating a 3D segmentation of a target volume is provided. The system accesses views of an X-ray scan of a target volume. The system applies a 2D CNN to each view to generate a 2D multi-channel feature vector for each view. The system applies a space carver to generate a 3D channel volume for each channel based on the 2D multi-channel feature vectors. The system then applies a linear combining technique to the 3D channel volumes to generate a 3D multi-label map that represents a 3D segmentation of the target volume.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2023},
month = {1}
}
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
TIMBIR: A Method for Time-Space Reconstruction From Interlaced Views
journal, June 2015
- Aditya Mohan, K.; Venkatakrishnan, S. V.; Gibbs, John W.
- IEEE Transactions on Computational Imaging, Vol. 1, Issue 2
Medical Image Segmentation Based on Mixed Context CNN Model
patent-application, February 2021
- He, Xuejian; Wang, Lu; Wu, Xiaohua
- US Patent Application 16/538923; 20210049756
Convolutional Neural Networks for Inverse Problems in Imaging: A Review
journal, November 2017
- McCann, Michael T.; Jin, Kyong Hwan; Unser, Michael
- IEEE Signal Processing Magazine, Vol. 34, Issue 6
A theory of shape by space carving
conference, January 1999
- Kutulakos, K. N.; Seitz, S. M.
- Proceedings of the Seventh IEEE International Conference on Computer Vision
Improved total variation-based CT image reconstruction applied to clinical data
journal, February 2011
- Ritschl, Ludwig; Bergner, Frank; Fleischmann, Christof
- Physics in Medicine and Biology, Vol. 56, Issue 6
Practical cone-beam algorithm
journal, January 1984
- Feldkamp, L. A.; Davis, L. C.; Kress, J. W.
- Journal of the Optical Society of America A, Vol. 1, Issue 6
CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction
journal, June 2018
- Gupta, Harshit; Jin, Kyong Hwan; Nguyen, Ha Q.
- IEEE Transactions on Medical Imaging, Vol. 37, Issue 6
Deep Convolutional Neural Network for Inverse Problems in Imaging
journal, September 2017
- Jin, Kyong Hwan; McCann, Michael T.; Froustey, Emmanuel
- IEEE Transactions on Image Processing, Vol. 26, Issue 9
Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization
journal, August 2008
- Sidky, Emil Y.; Pan, Xiaochuan
- Physics in Medicine and Biology, Vol. 53, Issue 17
Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network
journal, December 2017
- Chen, Hu; Zhang, Yi; Kalra, Mannudeep K.
- IEEE Transactions on Medical Imaging, Vol. 36, Issue 12
3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes
patent-application, May 2019
- Liu, Siqi; Xu, Daguang; Zhou, Shaohua Kevin
- US Patent Application 15/996719; 20190130562
Prior image constrained compressed sensing (PICCS): A method to accurately reconstruct dynamic CT images from highly undersampled projection data sets: Prior image constrained compressed sensing (PICCS)
journal, January 2008
- Chen, Guang-Hong; Tang, Jie; Leng, Shuai
- Medical Physics, Vol. 35, Issue 2
Deep back Projection for Sparse-View ct Reconstruction
conference, November 2018
- Ye, Dong Hye; Buzzard, Gregery T.; Ruby, Max
- 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
Iterative CT Reconstruction Using Shearlet-Based Regularization
journal, October 2013
- Vandeghinste, Bert; Goossens, Bart; Van Holen, Roel
- IEEE Transactions on Nuclear Science, Vol. 60, Issue 5