Independent Component Analysis for the Examination of Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging Data
Authors:
- Seung-Schik YooSYSeung-Schik Yoo
- Byung GIL ChoiBCByung GIL Choi
- Ji-Youn HanJHJi-Youn Han
- Hak Hee KimHKHak Hee Kim
- 1 December 2002
- journal article
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 37 (12) , 647-654
Abstract
An application of independent component analysis (ICA) is reported for the detection and characterization of breast lesions in dynamic contrast-enhanced MRI. The ICA technique, which uses a novel statistical algorithm to separate mixed signal sources of unknown nature, enables the extraction of spatial and temporal features of dynamic MRI data. Six patients with confirmed lesion diagnosis (three with malignancy and three with benign condition) participated in this study. T1-weighted MRI covering both breast volumes was dynamically acquired in every 90 seconds after the bolus injection of contrast media using three-dimensional fast low-angle shot sequence (3-D FLASH). With the application of the ICA, differential signal responses were delineated from benign and malignant lesions, and areas with high temporal correlations with the extracted signal components were selectively visualized. The results suggest that ICA allowed for an identification of lesion morphology and lesion-specific dynamic enhancement patterns.Keywords
This publication has 35 references indexed in Scilit:
- Critical role of spatial resolution in dynamic contrast‐enhanced breast MRIJournal of Magnetic Resonance Imaging, 2001
- Removing electroencephalographic artifacts by blind source separationPsychophysiology, 2000
- SENSE: Sensitivity encoding for fast MRIMagnetic Resonance in Medicine, 1999
- Dynamic Magnetic Resonance Imaging in Evaluating Suspicious Breast LesionsSouthern Medical Journal, 1998
- Multifeature analysis of Gd‐enhanced MR images of breast lesionsJournal of Magnetic Resonance Imaging, 1997
- Application of a quantitative model to differentiate benign from malignant breast lesions detected by dynamic, gadolinium‐enhanced MRIJournal of Magnetic Resonance Imaging, 1996
- Clustered Breast Microcalcifications: Evaluation by Dynamic Contrast-Enhanced Subtraction MRIJournal of Computer Assisted Tomography, 1996
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995
- Quantitative Analysis of Dynamic Gd‐DTPA Enhancement in Breast Tumors Using a Permeability ModelMagnetic Resonance in Medicine, 1995
- Blind separation of sources: A nonlinear neural algorithmNeural Networks, 1992