Volumetric texture description and discriminant feature selection for MRI
UNSPECIFIED (2003) Volumetric texture description and discriminant feature selection for MRI. In: 18th International Conference on Information Processing in Medical Imaging, ST MARTINS COLL, AMBLESIDE, ENGLAND, JUL 20-25, 2003. Published in: INFORMATION PROCESSING IN MEDICAL IMAGING, PROCEEDINGS, 2732 pp. 282-293.Full text not available from this repository.
This paper considers the problem of classification of Magnetic Resonance Images using 2D and 3D texture measures. Joint statistics such as co-occurrence matrices are common for analysing texture in 2D since they are simple and effective to implement. However, the computational complexity can be prohibitive especially in 3D. In this work, we develop a texture classification strategy by a sub-band filtering technique that can be extended to 3D. We further propose a feature selection technique based on the Bhattacharyya distance measure that reduces the number of features required for the classification by selecting a set of discriminant features conditioned on a set training texture samples. We describe and illustrate the methodology by quantitatively analysing a series of images: 2D synthetic phantom, 2D natural textures, and MRI of human knees.
|Item Type:||Conference Item (UNSPECIFIED)|
|Subjects:||Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software|
|Series Name:||LECTURE NOTES IN COMPUTER SCIENCE|
|Journal or Publication Title:||INFORMATION PROCESSING IN MEDICAL IMAGING, PROCEEDINGS|
|Editor:||Taylor, C and Noble, JA|
|Number of Pages:||12|
|Page Range:||pp. 282-293|
|Title of Event:||18th International Conference on Information Processing in Medical Imaging|
|Location of Event:||ST MARTINS COLL, AMBLESIDE, ENGLAND|
|Date(s) of Event:||JUL 20-25, 2003|
Actions (login required)