S
Septimiu E. Salcudean
Researcher at University of British Columbia
Publications - 440
Citations - 15689
Septimiu E. Salcudean is an academic researcher from University of British Columbia. The author has contributed to research in topics: Imaging phantom & Elastography. The author has an hindex of 64, co-authored 399 publications receiving 14100 citations. Previous affiliations of Septimiu E. Salcudean include University of California, Berkeley & IBM.
Papers
More filters
Journal ArticleDOI
Parallelism in Autonomous Robotic Surgery
TL;DR: The notion of “automation for surgical manual execution” is proposed where it is argued that autonomous robotic surgery research can be used as a tool for surgeons to discover novel manual execution models that can significantly improve their surgical practice.
Book ChapterDOI
Learning-Based US-MR Liver Image Registration with Spatial Priors
Qiao Jia Zeng,Shahed K. Mohammed,Emily H. T. Pang,Caitlin Schneider,Mohammad Honarvar,Julio Lobo,Changhong Hu,James Jago,G.C. Ng,Robert Rohling,Septimiu E. Salcudean +10 more
TL;DR: In this paper , an image registration workflow is presented to achieve reliable alignment for subject-specific magnetic resonance (MR) and intercostal 3D ultrasound (US) images of the liver.
Journal ArticleDOI
Prostate implant reconstruction from C-arm images with motion-compensated tomosynthesis
Ehsan Dehghan,Mehdi Moradi,Xu Wen,Danny French,Julio Lobo,W. James Morris,Septimiu E. Salcudean,Gabor Fichtinger +7 more
TL;DR: A computational motion compensation method for tomosynthesis-based reconstruction that enables 3D localization of prostate implants from C-arm images despite C- arm oscillation and sagging and is feasible for clinical use is proposed.
Journal ArticleDOI
Denoising of pre-beamformed photoacoustic data using generative adversarial networks.
TL;DR: Generative adversarial networks are trained to mimic both the effect of temporal averaging and of singular value decomposition (SVD) denoising, which effectively removes noise and acquisition artifacts and improves signal-to-noise ratio (SNR) in both the radio-frequency (RF) data and in the corresponding photoacoustic reconstructions.
Book ChapterDOI
Accurate and Robust Segmentation of the Clinical Target Volume for Prostate Brachytherapy
Davood Karimi,Qi Zeng,Prateek Mathur,Apeksha Avinash,Seyedeh Sara Mahdavi,Ingrid Spadinger,Purang Abolmaesumi,Septimiu E. Salcudean +7 more
TL;DR: This work proposes a method for automatic segmentation of the prostate clinical target volume for brachytherapy in transrectal ultrasound (TRUS) images based on a novel convolutional neural network (CNN) architecture and suggests an adaptive sampling strategy that drives the training process to give more attention to images that are difficult to segment.