ITAC volume assessment through a Gaussian hidden Markov random field model-based algorithm

Katia M. Passera, Paolo Potepan, Luca Brambilla, Luca T. Mainardi

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

Abstract

In this paper, a semi-automatic segmentation method for volume assessment of Intestinal-type adenocarcinoma (ITAC) is presented and validated. The method is based on a Gaussian hidden Markov random field (GHMRF) model that represents an advanced version of a finite Gaussian mixture (FGM) model as it encodes spatial information through the mutual influences of neighboring sites. To fit the GHMRF model an expectation maximization (EM) algorithm is used. We applied the method to a magnetic resonance data sets (each of them composed by T1-weighted, Contrast Enhanced Tl-weighted and T2-weighted images) for a total of 49 tumor-contained slices. We tested GHMRF performances with respect to FGM by both a numerical and a clinical evaluation. Results show that the proposed method has a higher accuracy in quantifying lesion area than FGM and it can be applied in the evaluation of tumor response to therapy.

Original languageEnglish
Title of host publicationProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology"
Pages1218-1221
Number of pages4
Publication statusPublished - 2008
Event30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - Vancouver, BC, Canada
Duration: Aug 20 2008Aug 25 2008

Other

Other30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
CountryCanada
CityVancouver, BC
Period8/20/088/25/08

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Fingerprint Dive into the research topics of 'ITAC volume assessment through a Gaussian hidden Markov random field model-based algorithm'. Together they form a unique fingerprint.

Cite this