9 Hits in 12.9 sec

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.  ...  This review summarized the progress made in DL-based 3D image registration over the past 5 years and identify existing challenges and potential avenues for further research.  ...  For example, Haskins et al. used a deep CNN to learn a similarity metric for registration between MR and transrectal US (TRUS) images (79) .  ... 
doi:10.21037/qims-21-175 pmid:34888197 pmcid:PMC8611468 fatcat:jqa27ap7evgwvf3o4uy2vve57e

Computer-Assisted Analysis of Biomedical Images [article]

Leonardo Rundo
2021 arXiv   pre-print
In this regard, frameworks based on advanced Machine Learning and Computational Intelligence can significantly improve traditional Image Processing and Pattern Recognition approaches.  ...  In conclusion, the ultimate goal of these research studies is to gain clinically and biologically useful insights that can guide differential diagnosis and therapies, leading towards biomedical data integration  ...  [327] presented an automatic method, based on non-rigid registration of a set of pre-labeled atlas images, for delineating the prostate in 3D MR scans.  ... 
arXiv:2106.04381v1 fatcat:osqiyd3sbja3zgrby7bf4eljfm

Towards Augmented Reality: MRI-TRUS Fusion for Prostate Cancer Interventions

Transrectal ultrasound (TRUS) and magnetic resonance imaging (MRI) are two commonly used medical imaging technologies.  ...  Multimodal image fusion in this fashion would improve the clinical efficacy of image-based guidance for prostate cancer interventions.  ...  non-rigid registration methods, robust point matching (RPM) by Haili et al. [25, 122] and coherent point drift (CPD) by Myronenko et al. [107] appear to be the most frequently used algorithms for non-rigid  ... 
doi:10.26180/5d804de7e5050 fatcat:jv4yu6yyvbelhepoi7ggaab6ny

A Model for Online Interactive Remote Education for Medical Physics Using the Internet

Milton K Woo, Kwan-Hoong Ng
2003 Journal of Medical Internet Research  
To learn to calibrate a prostate US treatment planning unit.  ...  To learn the various philosophies used to plan, perform and evaluate prostate implants. 3.  ...  The other method would be to make appropriate reduction in mAs based on patient dimensions instead of using same mAs techniques for all chest CT scanning.  ... 
doi:10.2196/jmir.5.1.e3 pmid:12746208 pmcid:PMC1550549 fatcat:tsyf45yusza2jiglkq62rgo3qm

ECR 2011 Book of Abstracts - B - Scientific Sessions

2011 Insights into Imaging  
using Wilcoxon test.  ...  MR imaging was performed by 3D T1-weighted THRIVE breathold sequence (TR/ TE=3/1.57 msecs) before and after Gd-BOPTA injection (0.1 mmol/kg; 2 mL/sec) with contrast injection starting after contrast visualisation  ...  All data sets were aligned to a DTI atlas with a non-rigid coregistration algorithm.  ... 
doi:10.1007/s13244-011-0077-4 pmid:23100071 pmcid:PMC3533624 fatcat:lytbu2vohbhhnorjqlpogl77iu

5th International Symposium on Focused Ultrasound

Menashe Zaaroor, Alon Sinai, Dorit Goldsher, Ayelet Eran, Maria Nassar, Ilana Schlesinger, Jonathon Parker, Vinod Ravikumar, Pejman Ghanouni, Sherman Stein, Casey Halpern, Vibhor Krishna (+1008 others)
2016 Journal of Therapeutic Ultrasound  
A3 Tractography-based VIM identification for Focused Ultrasound thalamotomy: initial results which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate  ...  asymmetry and forepaw use bias in 6-OHDA rats).  ...  to make a rigid body for registration.  ... 
doi:10.1186/s40349-016-0076-5 fatcat:4vm7i5mt6vheni3hflxd3pwl2i

Real-time Biomechanical Modeling for Intraoperative Soft Tissue Registration

Stefan Suwelack
In contrast to previous attempts at biomechanically based registration, this novel physics based interpretation allows casting the shape matching problem into a single variational formulation.  ...  This approach treats the non-rigid surface registration as an electrostatic-elastic problem, where an elastic body that is electrically charged (preoperative model) slides into an oppositely charged rigid  ...  In order to use MR based preoperative data in this context, it has to be registered to the TRUS image.  ... 
doi:10.5445/ksp/1000046886 fatcat:l7lu2y5635gvrkmqn5dp3fytum

A design methodology for 2D sparse NDE arrays using an efficient implementation of refracted-ray TFM

Jerzy Dziewierz, Timothy Lardner, Anthony Gachagan
2013 2013 IEEE International Ultrasonics Symposium (IUS)  
One of these technologies takes advantage of the acoustic radiation forces associated with ultrasound standing wave fields to spatially pattern cells within collagen-based hydrogels.  ...  A second technology uses ultrasound to noninvasively control the microstructure of collagen within engineered tissues.  ...  The aim of this work was to develop an MR compatible US platform to enable non-invasive hybrid MR-US-imaging and real-time US-motion compensation.  ... 
doi:10.1109/ultsym.2013.0035 fatcat:th5znfh7y5bklfdbmhb4u6iq2i

International Healthcare Vision 2037 - new technologies, educational goals and entrepreneurial challenges ; proceedings + summary of the 5th BME-IDEA EU Conference ; 11 - 13 June 2017, Magdeburg, Germany [article]

Michael Friebe, Universitäts- Und Landesbibliothek Sachsen-Anhalt, Martin-Luther Universität
Targeted prostate biopsies based on mp-MRI achieve more direct diagnostic hits than conventional 12-core TRUS biopsies [2] .  ...  Deep learning will bring us in to surprise by the level of accurate output prediction. Deep learning is technique of machine learning that learns features and tasks directly from data.  ... 
doi:10.25673/4992 fatcat:ehdh42wbl5gqnd2z3ofkh5qrie