435 Hits in 6.8 sec

Real-Time Patient-Specific Lung Radiotherapy Targeting using Deep Learning [article]

Markus D. Foote, Sarang Joshi Scientific Computing and Imaging Institute, Department of Bioengineering, University of Utah, Department of Radiation Oncology, The University of Maryland School of Medicine)
2018 arXiv   pre-print
A deep convolutional neural network and subspace motion tracking is used to recover anatomical positions from a single radiograph projection in real-time.  ...  We approximate the nonlinear inverse of a diffeomorphic transformation composed with radiographic projection as a deep network that produces subspace coordinates to define the patient-specific deformation  ...  With deep learning the combination of these motion patterns observed in real-time radiographs can be recovered to determine the shift in target position from the targeted baseline position.  ... 
arXiv:1807.08388v1 fatcat:ucrshwyivfc33h5xblqjiedoka

Artificial intelligence in image-guided radiotherapy: a review of treatment target localization

Wei Zhao, Liyue Shen, Md Tauhidul Islam, Wenjian Qin, Zhicheng Zhang, Xiaokun Liang, Gaolong Zhang, Shouping Xu, Xiaomeng Li
2021 Quantitative Imaging in Medicine and Surgery  
In this paper, we review the applications of AI-based algorithms in image-guided radiotherapy (IGRT), and discuss the indications of these applications to the future of clinical practice of radiotherapy  ...  Recent advances in artificial intelligence (AI) have greatly augmented our ability to accurately localize the treatment target while sparing the normal tissues.  ...  For spine and lung tumors that have better contrast resolution, 2D/3D registration methods can be applied for patient setup and target monitoring (76, 77) .  ... 
doi:10.21037/qims-21-199 pmid:34888196 pmcid:PMC8611462 fatcat:kk4mvoxmjbf3bfo4t3tlqh4gw4

Synergizing medical imaging and radiotherapy with deep learning

Hongming Shan, Xun Jia, Pingkun Yan, Yunyao Li, Harald Paganetti, Ge Wang
2020 Machine Learning: Science and Technology  
This article reviews deep learning methods for medical imaging (focusing on image reconstruction, segmentation, registration, and radiomics) and radiotherapy (ranging from planning and verification to  ...  It is believed that deep learning in particular, and artificial intelligence and machine learning in general, will have a revolutionary potential to advance and synergize medical imaging and radiotherapy  ...  Acknowledgment This work was partially support by NIH/NCI under award numbers R01CA233888, R01CA237267, R01CA227289, R37CA214639, and R01CA237269, and NIH/NIBIB under award number R01EB026646.  ... 
doi:10.1088/2632-2153/ab869f fatcat:aibfmfelcngkrk4ilwcs25c77a

Image-to-Graph Convolutional Network for Deformable Shape Reconstruction from a Single Projection Image [article]

M. Nakao, F. Tong, M. Nakamura, T. Matsuda
2021 arXiv   pre-print
The IGCN learns relationship between shape/deformation variability and the deep image features based on a deformation mapping scheme.  ...  In experiments targeted to the respiratory motion of abdominal organs, we confirmed the proposed framework with a regularized loss function can reconstruct liver shapes from a single digitally reconstructed  ...  Acknowledgments This research was supported by a JSPS Grant-in-Aid for Scientific Research (B) (Grant number 18H02766a and 19H04484).  ... 
arXiv:2108.12533v2 fatcat:2yqauy47tbbkzkfk4wlwnmgije

Advanced 4-dimensional cone-beam computed tomography reconstruction by combining motion estimation, motion-compensated reconstruction, biomechanical modeling and deep learning

You Zhang, Xiaokun Huang, Jing Wang
2019 Visual Computing for Industry, Biomedicine, and Art  
To improve the efficiency of reconstruction, we recently developed a U-net-based deformation-vector-field (DVF) optimization technique to leverage a population-based deep learning scheme to improve the  ...  4-Dimensional cone-beam computed tomography (4D-CBCT) offers several key advantages over conventional 3D-CBCT in moving target localization/delineation, structure de-blurring, target motion tracking, treatment  ...  Acknowledgements The authors would like to thank Dr. Paul Segars from the Duke University Medical Center for sharing the NCAT phantom for this study.  ... 
doi:10.1186/s42492-019-0033-6 pmid:32190409 pmcid:PMC7055574 fatcat:qmqmf7x5azhihb6zlp4jq2nx5i

A review of deep learning-based three-dimensional medical image registration methods

Haonan Xiao, Xinzhi Teng, Chenyang Liu, Tian Li, Ge Ren, Ruijie Yang, Dinggang Shen, Jing Cai
2021 Quantitative Imaging in Medicine and Surgery  
Recently, the successful implementation of deep learning (DL) in various fields has prompted many research groups to apply DL to three-dimensional (3D) medical image registration.  ...  The studies were classified into three categories: deep iterative registration, supervised registration, and unsupervised registration.  ...  (based on the objects to be registered), as rigid, affine, and deformable image registration (DIR) (based on the type of deformation), as three-dimensional (3D)-3D, 3D-two dimensional (2D), and 2D-2D  ... 
doi:10.21037/qims-21-175 pmid:34888197 pmcid:PMC8611468 fatcat:jqa27ap7evgwvf3o4uy2vve57e

LiftReg: Limited Angle 2D/3D Deformable Registration [article]

Lin Tian, Yueh Z. Lee, Raúl San José Estépar, Marc Niethammer
2022 arXiv   pre-print
We propose LiftReg, a 2D/3D deformable registration approach.  ...  We test our approach on the DirLab lung registration dataset and show that it outperforms an existing learning-based pairwise registration approach.  ...  Rong Yuan (Peking University) and Boqi Chen (UNC) for valuable suggestions on menuscript writing.  ... 
arXiv:2203.05565v1 fatcat:3bb33ltpmbhupgclrrgd2dfwdm

Medical Image Registration Using Deep Neural Networks: A Comprehensive Review [article]

Hamid Reza Boveiri, Raouf Khayami, Reza Javidan, Ali Reza MehdiZadeh
2020 arXiv   pre-print
to challenge with many medical applications, where the registration is not an exception.  ...  This review allows a deep understanding and insight for the readers active in the field who are investigating the state-of-the-art and seeking to contribute the future literature.  ...  Joshi, "Real-Time 2D-3D Deformable Registration with Deep Learning and Application to Lung Radiotherapy Targeting," Information Processing in Medical Imaging, pp. 265-276, 2019.  ... 
arXiv:2002.03401v1 fatcat:u4utrifr2rg3bf6x6fgohyfmpy

Front Matter: Volume 10576

Robert J. Webster, Baowei Fei
2018 Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling  
0E Real-time image-based 3D-2D registration for ultrasound-guided spinal interventions iii NEUROLOGICAL PROCEDURES AND TECHNOLOGIES 0P Model-based correction for brain shift in deep brain stimulation  ...  extraction methods [10576-94] 10576 2X Bundling 3D-and 2D-based registration of MRI to x-ray breast tomosynthesis [10576-95] ProjectAlign: a real-time ultrasound guidance system for spinal midline detection  ... 
doi:10.1117/12.2323924 fatcat:hva4ny4ftbe2voqifpbt5wewky

Deep Learning in Medical Image Registration: A Review [article]

Yabo Fu, Yang Lei, Tonghe Wang, Walter J. Curran, Tian Liu, Xiaofeng Yang
2019 arXiv   pre-print
We provided a comprehensive comparison among DL-based methods for lung and brain deformable registration using benchmark datasets.  ...  This paper presents a review of deep learning (DL) based medical image registration methods.  ...  Acknowledgements This research is supported in part by the National Cancer Institute of the National Institutes of Health under Award Number R01CA215718, and Dunwoody Golf Club Prostate Cancer Research  ... 
arXiv:1912.12318v1 fatcat:kuvckosqd5hp7asg6dofhuiis4

IGCN: Image-to-graph Convolutional Network for 2D/3D Deformable Registration [article]

Megumi Nakao, Mitsuhiro Nakamura, Tetsuya Matsuda
2021 arXiv   pre-print
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  ...  We propose an image-to-graph convolutional network that achieves deformable registration of a 3D organ mesh for a single-viewpoint 2D projection image.  ...  The IGCN provides a new end-to-end framework that achieves real-time 2D/3D deformable registration through integration of an image-based generative network and GCN.  ... 
arXiv:2111.00484v1 fatcat:v3dxmg4dgzafbfxviq2pxfvop4

The Impact of Machine Learning on 2D/3D Registration for Image-guided Interventions: A Systematic Review and Perspective [article]

Mathias Unberath, Cong Gao, Yicheng Hu, Max Judish, Russell H Taylor, Mehran Armand, Robert Grupp
2021 arXiv   pre-print
A critical component of image guidance is 2D/3D registration, a technique to estimate the spatial relationships between 3D structures, e.g., volumetric imagery or tool models, and 2D images thereof, such  ...  In this manuscript, we review the impact of machine learning on 2D/3D registration to systematically summarize the recent advances made by introduction of this novel technology.  ...  Acknowledgments The viewpoints presented in this manuscript have been shaped by several years of work on 2D/3D registration in the context of image-guided surgery at Johns Hopkins University.  ... 
arXiv:2108.02238v1 fatcat:fjazsnfg45b5jf4nanqw2pyohi

Advances in MRI‐guided precision radiotherapy

Chenyang Liu, Mao Li, Haonan Xiao, Tian Li, Wen Li, Jiang Zhang, Xinzhi Teng, Jing Cai
2022 Precision Radiation Oncology  
Many recent advances in MRI have been shown to be promising for MRI-guided radiotherapy and for improved treatment outcomes.  ...  These techniques can be implemented before, during, or after radiotherapy for various precision radiotherapy applications, such as tumor delineation, tumor motion management, treatment adaptation, and  ...  Deep learning strategies have been used for real-time dose calculation. 21 Further evaluation of the accuracy of real-time imaging and dose calculation needs to be implemented in real-time MRI-guided workflows  ... 
doi:10.1002/pro6.1143 fatcat:cuxdix7st5biflwsd4jsm56wp4

The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective

Mathias Unberath, Cong Gao, Yicheng Hu, Max Judish, Russell H Taylor, Mehran Armand, Robert Grupp
2021 Frontiers in Robotics and AI  
In this manuscript, we review the impact of machine learning on 2D/3D registration to systematically summarize the recent advances made by introduction of this novel technology.  ...  While image-based 2D/3D registration is a mature technique, its transition from the bench to the bedside has been restrained by well-known challenges, including brittleness with respect to optimization  ...  ACKNOWLEDGMENTS We gratefully acknowledge financial support from NIH NIBIB Trailblazer R21 EB028505, and internal funds of the Malone Center for Engineering in Healthcare at Johns Hopkins University.  ... 
doi:10.3389/frobt.2021.716007 pmid:34527706 pmcid:PMC8436154 fatcat:qphhvllqjndwpmca7he4xd7b3e

Front Matter: Volume 9415

Proceedings of SPIE, Robert J. Webster, Ziv R. Yaniv
2015 Medical Imaging 2015: Image-Guided Procedures, Robotic Interventions, and Modeling  
Base 36 numbering is employed for the last two digits and indicates the order of articles within the volume. Numbers start with 00  ...  Numbers in the index correspond to the last two digits of the six-digit citation identifier (CID) article numbering system used in Proceedings of SPIE.  ...  approach for in vivo lung tumor motion prediction during external beam radiation SESSION 8 SEGMENTATION 9415 14 Deep learning for automatic localization, identification, and segmentation of vertebral  ... 
doi:10.1117/12.2184297 dblp:conf/miigp/X15 fatcat:qx5pgjakdfg75mpufw66xc5k5e
« Previous Showing results 1 — 15 out of 435 results