Optimal linear transformation for MRI feature extraction
- 1 January 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 15 (6), 749-767
- https://doi.org/10.1109/42.544494
Abstract
This paper presents development and application of a feature extraction method for magnetic resonance imaging (MRI), without explicit calculation of tissue parameters. A three-dimensional (3-D) feature space representation of the data is generated in which normal tissues are clustered around prespecified target positions and abnormalities are clustered elsewhere. This is accomplished by a linear minimum mean square error transformation of categorical data to target positions. From the 3-D histogram (cluster plot) of the transformed data, clusters are identified and regions of interest (ROI's) for normal and abnormal tissues are defined. These ROI's are used to estimate signature (prototype) vectors for each tissue type which in turn are used to segment the MRI scene. The proposed feature space is compared to those generated by tissue-parameter-weighted images, principal component images, and angle images, demonstrating its superiority for feature extraction and scene segmentation. Its relationship with discriminant analysis is discussed. The method and its performance are illustrated using a computer simulation and MRI images of an egg phantom and a human brain.Keywords
This publication has 21 references indexed in Scilit:
- A multidimensional nonlinear edge-preserving filter for magnetic resonance image restorationIEEE Transactions on Image Processing, 1995
- Computer-assisted identification and quantification of multiple sclerosis lesions in MR imaging volumes in the brainJournal of Magnetic Resonance Imaging, 1994
- Optimization of MRI protocols and pulse sequence parameters for eigenimage filteringIEEE Transactions on Medical Imaging, 1994
- Correction of intensity variations in MR images for computer-aided tissue classificationIEEE Transactions on Medical Imaging, 1993
- Composite and classified color display in MR imaging of the female pelvisMagnetic Resonance Imaging, 1992
- Generation of color composites for enhanced tissue differentiation in magnetic resonance imaging of the brainJournal of Anatomy, 1991
- Tissue Characterization in MR ImagingPublished by Springer Science and Business Media LLC ,1990
- Data analysis of multivariate magnetic resonance images I. A principal component analysis approachChemometrics and Intelligent Laboratory Systems, 1989
- Tissue characterization with T1, T2, and proton density values: results in 160 patients with brain tumors.Radiology, 1988
- Application of the Karhunen-Loève Expansion to Feature Selection and OrderingIEEE Transactions on Computers, 1970