Skip to main navigation Skip to search Skip to main content

High-resolution reconstruction of human brain MRI image based on local polynomial regression

  • Z. G. Zhang
  • , S. C. Chan
  • , X. Zhang
  • , E. Y. Lam
  • , E. X. Wu
  • , Y. Hu
  • The University of Hong Kong

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper introduces a new local polynomial regression (LPR)-based high-resolution image reconstruction method for human brain magnetic resonance images. In LPR, the image pixels are modeled locally by a polynomial using least-squares (LS) criterion with a kernel having a certain bandwidth matrix. Steering kernels with local orientation are used in LPR to adapt better to local characteristics of images. Furthermore, a refined intersection of confidence intervals (RICI) adaptive scale selector is adopted to select the scale of the steering kernels. The resulting steering-kernel-based LPR with RICI (SK-LPR-RICI) method is applied to reconstruct a high-resolution brain MRI image from a set of low-resolution MRI images. Simulation results show that the proposed SK-LPR-RICI method can effectively improve the image resolution and peak signal-to-noise ratio.

Original languageEnglish
Title of host publication2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09
Pages245-248
Number of pages4
DOIs
StatePublished - 2009
Externally publishedYes
Event2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09 - Antalya, Turkey
Duration: 29 Apr 20092 May 2009

Publication series

Name2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09

Conference

Conference2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09
Country/TerritoryTurkey
CityAntalya
Period29/04/092/05/09

Keywords

  • Adaptive scale selection
  • Image reconstruction
  • Local polynomial regression
  • MRI

Fingerprint

Dive into the research topics of 'High-resolution reconstruction of human brain MRI image based on local polynomial regression'. Together they form a unique fingerprint.

Cite this