Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Marzieh S. Tahaei"'
Modern Convolutional Neural Network (CNN) architectures, despite their superiority in solving various problems, are generally too large to be deployed on resource constrained edge devices. In this paper, we reduce memory usage and floating-point oper
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7dd6b71f00b9da20abdc41208c51139
http://arxiv.org/abs/2109.14710
http://arxiv.org/abs/2109.14710
Autor:
Francis Dutil, Thomas Fevens, Qicheng Lao, Mehrzad Mortazavi, Marzieh S. Tahaei, Mohammad Havaei
In this paper, we propose a general framework in continual learning for generative models: Feature-oriented Continual Learning (FoCL). Unlike previous works that aim to solve the catastrophic forgetting problem by introducing regularization in the pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4d0b6ff4768cf94c30a84b584e14ddc
Publikováno v:
Tahaei, M S, Reader, A J & Collins, D L 2019, ' Two Novel PET Image Restoration Methods Guided by PET-MR Kernels : Application to Brain Imaging ', Medical Physics, vol. 46, no. 5, pp. 2085-2102 . https://doi.org/10.1002/mp.13418
Purpose Post-reconstruction positron emission tomography (PET) image restoration methods that take advantage of available anatomical information can play an important role in accurate quantification of PET images. However, when using anatomical infor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2204df4a9e9ffab6e734b5e54fff05a8
https://kclpure.kcl.ac.uk/ws/files/105135820/manuscript_medPhys_1_.pdf
https://kclpure.kcl.ac.uk/ws/files/105135820/manuscript_medPhys_1_.pdf
Publikováno v:
2016 IEEE Nuclear Science Symposium, Medical Imaging Conference and Room-Temperature Semiconductor Detector Workshop (NSS/MIC/RTSD).
With the growing interest in conducting multi-centre and multi-modality studies on neurological disorders, post-reconstruction PET image enhancement methods that take advantage of available anatomical information are becoming more important. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3a2b525352efce4361b21a978019cadf
https://doi.org/10.1109/nssmic.2016.8069564
https://doi.org/10.1109/nssmic.2016.8069564
Autor:
Marzieh S, Tahaei, Andrew J, Reader
Publikováno v:
Physics in medicine and biology. 61(18)
In PET image reconstruction, regularization is often needed to reduce the noise in the resulting images. Patch-based image processing techniques have recently been successfully used for regularization in medical image reconstruction through a penaliz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::f38174e9be7b66ee712a37420bfd4499
https://pubmed.ncbi.nlm.nih.gov/27581747
https://pubmed.ncbi.nlm.nih.gov/27581747
Autor:
Andrew J. Reader, Marzieh S. Tahaei
Publikováno v:
2014 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC).
A variety of approaches have been proposed to reduce the variance in reconstructed PET images. In this work, we assess the effect of different combinations of variance reduction techniques on the quality of reconstructed images. These methods include
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e1afebbe86ccd91bdb9848968a48fbd5
https://doi.org/10.1109/nssmic.2014.7430943
https://doi.org/10.1109/nssmic.2014.7430943
Autor:
Jean-Paul Soucy, Arman Rahmim, Stephan Blinder, Marzieh S. Tahaei, Sune H. Keller, Merence Sibomana, Andrew J. Reader
Publikováno v:
2013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC).
To date, the high resolution research tomograph (HRRT) still offers the highest resolution PET imaging capability of the human brain. Spatial uniformity of the images is of paramount importance, as many radioligand studies require either accurate reg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5f51480575343c92a2bf1a3c38823355
https://doi.org/10.1109/nssmic.2013.6829403
https://doi.org/10.1109/nssmic.2013.6829403
Publikováno v:
2013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC).
PET imaging with scanners such as the HRRT and the HR+ enables functional images of the binding of radioligands to neuroreceptors to be obtained, which is of great utility in neuroscience research. Usually a time series of images is acquired in order
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bfa6aa52ffc4fe7e12d7506489d3ffaf
https://doi.org/10.1109/nssmic.2013.6829381
https://doi.org/10.1109/nssmic.2013.6829381
Publikováno v:
ICDM Workshops
This paper introduces a novel coding scheme based on the diffusion map framework. The idea is to run a t-step random walk on the data graph to capture the similarity of a data point to the codebook atoms. By doing this we exploit local similarities e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad240a1c9636f1ba5e58f4804b618c1c
https://doi.org/10.1109/icdmw.2012.86
https://doi.org/10.1109/icdmw.2012.86
Publikováno v:
IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engin
Recently graph theory and complex networks have been widely used as a mean to model functionality of the brain. Among different neuroimaging techniques available for constructing the brain functional networks, electroencephalography (EEG) with its hi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71418d03de33a87eb1f29b85ef6c1b9a
https://pubmed.ncbi.nlm.nih.gov/22695360
https://pubmed.ncbi.nlm.nih.gov/22695360