Automatic detection of structural changes in single channel long time-span brain MRI images using saliency map and active contour methods

Andrea Kovacs, T. Szirányi, P. Barsi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper introduces a novel method to detect structural changes between MRI scans, without using prior knowledge. After a simple registration step, the method calculates a difference image, based on modified Harris saliency function, which is then used to define change candidates. Localization step filters out false hits with local contour descriptors featuring the neighborhood of candidates. Finally, boundary of the lesion is detected by integration of contour point extraction and Chan-Vese active contour method. Tests on simulated and real data show that the results are very promising.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages1265-1268
Number of pages4
DOIs
Publication statusPublished - 2012
Event2012 19th IEEE International Conference on Image Processing, ICIP 2012 - Lake Buena Vista, FL, United States
Duration: Sep 30 2012Oct 3 2012

Other

Other2012 19th IEEE International Conference on Image Processing, ICIP 2012
CountryUnited States
CityLake Buena Vista, FL
Period9/30/1210/3/12

Fingerprint

Magnetic resonance imaging
Brain
Magnetic Resonance Imaging

Keywords

  • biomedical imaging
  • change detection
  • Harris saliency function
  • local contour descriptors
  • magnetic resonance imaging (MRI)

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Automatic detection of structural changes in single channel long time-span brain MRI images using saliency map and active contour methods. / Kovacs, Andrea; Szirányi, T.; Barsi, P.

Proceedings - International Conference on Image Processing, ICIP. 2012. p. 1265-1268 6467097.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kovacs, A, Szirányi, T & Barsi, P 2012, Automatic detection of structural changes in single channel long time-span brain MRI images using saliency map and active contour methods. in Proceedings - International Conference on Image Processing, ICIP., 6467097, pp. 1265-1268, 2012 19th IEEE International Conference on Image Processing, ICIP 2012, Lake Buena Vista, FL, United States, 9/30/12. https://doi.org/10.1109/ICIP.2012.6467097
@inproceedings{4524f38075a6417bb9a52c4ad1f5dc56,
title = "Automatic detection of structural changes in single channel long time-span brain MRI images using saliency map and active contour methods",
abstract = "This paper introduces a novel method to detect structural changes between MRI scans, without using prior knowledge. After a simple registration step, the method calculates a difference image, based on modified Harris saliency function, which is then used to define change candidates. Localization step filters out false hits with local contour descriptors featuring the neighborhood of candidates. Finally, boundary of the lesion is detected by integration of contour point extraction and Chan-Vese active contour method. Tests on simulated and real data show that the results are very promising.",
keywords = "biomedical imaging, change detection, Harris saliency function, local contour descriptors, magnetic resonance imaging (MRI)",
author = "Andrea Kovacs and T. Szir{\'a}nyi and P. Barsi",
year = "2012",
doi = "10.1109/ICIP.2012.6467097",
language = "English",
isbn = "9781467325332",
pages = "1265--1268",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Automatic detection of structural changes in single channel long time-span brain MRI images using saliency map and active contour methods

AU - Kovacs, Andrea

AU - Szirányi, T.

AU - Barsi, P.

PY - 2012

Y1 - 2012

N2 - This paper introduces a novel method to detect structural changes between MRI scans, without using prior knowledge. After a simple registration step, the method calculates a difference image, based on modified Harris saliency function, which is then used to define change candidates. Localization step filters out false hits with local contour descriptors featuring the neighborhood of candidates. Finally, boundary of the lesion is detected by integration of contour point extraction and Chan-Vese active contour method. Tests on simulated and real data show that the results are very promising.

AB - This paper introduces a novel method to detect structural changes between MRI scans, without using prior knowledge. After a simple registration step, the method calculates a difference image, based on modified Harris saliency function, which is then used to define change candidates. Localization step filters out false hits with local contour descriptors featuring the neighborhood of candidates. Finally, boundary of the lesion is detected by integration of contour point extraction and Chan-Vese active contour method. Tests on simulated and real data show that the results are very promising.

KW - biomedical imaging

KW - change detection

KW - Harris saliency function

KW - local contour descriptors

KW - magnetic resonance imaging (MRI)

UR - http://www.scopus.com/inward/record.url?scp=84875843428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875843428&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2012.6467097

DO - 10.1109/ICIP.2012.6467097

M3 - Conference contribution

AN - SCOPUS:84875843428

SN - 9781467325332

SP - 1265

EP - 1268

BT - Proceedings - International Conference on Image Processing, ICIP

ER -