A MAP framework for tag line detection in SPAMM data using markov random fields on the B-spline solid

Yasheng Chen, Amir A. Amini

Research output: Contribution to conferencePaper

10 Scopus citations

Abstract

Magnetic resonance (MR) tagging is a technique for measuring heart deformations through creation of a stripe grid pattern on cardiac images. Typically, sets of tag surfaces are encoded in the tissue appearing as dark lines on 2D images. The B-spline solid model for tagged MRI has the advantage of tracking myocardial tissue with material coordinates. This makes it an effective model in the analysis of heart deformation. In this paper, we present a Maximum A Posteriori (MAP) framework for detecting tags with a markov random field (MRF) defined on a sampled B-spline solid model. We formulate the tag tracking problem as MAP estimation, finding the optimal solid for the tag features present in the current image set given an initial solid for the previous frame. The framework also allows the parameters of the solid model number of knots, and spline order to be adjusted. In this approach, fitting can start with a solid with less knots and lower spline order, and proceed to one with more knots and/or higher order to achieve more accuracy. The approach has been validated on two sets of in-vivo heart data.

Original languageEnglish
Pages131-138
Number of pages8
StatePublished - Dec 1 2001
EventWorkshop on Mathematical Methods in Biomedical Image Analysis MMBIA 2001 - Kauai, HI, United States
Duration: Dec 9 2001Dec 10 2001

Conference

ConferenceWorkshop on Mathematical Methods in Biomedical Image Analysis MMBIA 2001
CountryUnited States
CityKauai, HI
Period12/9/0112/10/01

Fingerprint Dive into the research topics of 'A MAP framework for tag line detection in SPAMM data using markov random fields on the B-spline solid'. Together they form a unique fingerprint.

  • Cite this

    Chen, Y., & Amini, A. A. (2001). A MAP framework for tag line detection in SPAMM data using markov random fields on the B-spline solid. 131-138. Paper presented at Workshop on Mathematical Methods in Biomedical Image Analysis MMBIA 2001, Kauai, HI, United States.