I R Greenshields | PubMed Health

PubMed1999

A system for computing neuromorphometry from magnetic resonance images.

A new technique for the automated measurement of a variety of gross neuroanatomical structures (such as cerebral ventricles) is described. The system exploits the local statistical properties of dual-echo magnetic resonance images of the brain to produce a fully unsupervised classification of these images into a variety of tissue types. Following this, a simple region agglomeration procedure aggregates the segmented regions by class, and submits these regions to a computational-geometric analysis from which a wide variety of measures are derived.

Brain↗

PubMed1998

A cluster computer system for the analysis and classification of massively large biomedical image data.

The current trend in medical image acquisition is towards the generation of image datasets which are massively large, either because they exhibit fine x, y, or z resolution, are volumetric, are multispectral, or a combination of all of the preceding. Such images pose a significant computational challenge in their analysis, not only in terms of data throughput, but also in terms of platform costs and simplicity. In this paper we describe the role of a cluster of workstations together with two quite different application programming interfaces (APIs) in the quantitative analysis of anatomic image data from the visible human project using an MRF-Gibbs classification algorithm. We describe the typical architecture of a cluster computer, two API options and the parallelization of the MRF-Gibbs procedure for the cluster. Finally, we show speedup results obtained on the cluster and sample classifications of visible human data.

Algorithms↗