Quantifying evolving processes in multimodal 3D medical images

Yuhang Wang, Tilmann Steinberg, Fillia Makedon, James Ford, Heather Wishart, Andrew Saykin

Research output: Contribution to journalConference article

1 Scopus citations

Abstract

Quantitative measurements of changes in evolving brain pathology, such as multiple sclerosis lesions and brain tumors, are important for clinicians to perform pertinent diagnoses and to help in patient follow-up. Lesions or tumors can vary over time in size, shape, location and composition because of natural pathological processes or the effect of a drug treatment or therapy. In the past, people have used as a quantitative measurement the change in total or regional lesion/tumor volume. In this paper we propose a new model to quantify changes in evolving processes in multimodal 3D medical images. We believe this model reflects changes in pathology more accurately because it simultaneously takes into account information in multiple imaging modalities and the location of lesion/tumor voxels. We demonstrate the effectiveness of this model with experiments on synthetic lesion data.

Original languageEnglish (US)
Pages (from-to)101-108
Number of pages8
JournalLecture Notes in Computer Science
Volume2879
Issue numberPART 2
StatePublished - Dec 1 2003
Externally publishedYes
EventMedical Image Computing and Computer-Assisted Intervention, MICCAI 2003 - 6th International Conference Proceedings - Montreal, Que., Canada
Duration: Nov 15 2003Nov 18 2003

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Quantifying evolving processes in multimodal 3D medical images'. Together they form a unique fingerprint.

  • Cite this

    Wang, Y., Steinberg, T., Makedon, F., Ford, J., Wishart, H., & Saykin, A. (2003). Quantifying evolving processes in multimodal 3D medical images. Lecture Notes in Computer Science, 2879(PART 2), 101-108.