Please use this identifier to cite or link to this item:
|Title:||An MRI image reconstruction approach based on the minimization of a complex norm||Authors:||Abche, Antoine
|Affiliations:||Department of Electrical Engineering
Department of Electrical Engineering
Conjugate gradient methods
Mean square error methods
Medical image processing
|Issue Date:||2009||Publisher:||IEEE||Part of:||34th Annual Conference of the IEEE Industrial Electronics Society (IECON 2008)||Start page:||1839||End page:||1844||Conference:||Annual Conference of IEEE Industrial Electronics (34th : 10-13 Nov. 2008 : Orlando, FL, USA)||Abstract:||
In this paper, a technique to reconstruct MRI images is proposed and presented. It is based on the decomposition of the collected raw data and the model into real and imaginary components. Then, a corresponding cost (error) function is formed to estimate the image intensities by an optimization procedure based on the conjugate gradient approach. The proposed approach is evaluated and compared with other conventional approaches such as SVD, Conjugate Synthesis, zero-filling and Projection Onto Convex Set (POCS) approaches. The quantitative evaluation is based on three different criteria: the Root Mean Square, the performance test and the Peak Signal to Noise Ratio. The results show that the performance of the proposed approach offers a certain improvement over the other conventional techniques.
|URI:||https://scholarhub.balamand.edu.lb/handle/uob/691||Ezproxy URL:||Link to full text||Type:||Conference Paper|
|Appears in Collections:||Department of Electrical Engineering|
Show full item record
checked on Jul 24, 2021
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.