Automated Detection of the Left Ventricle from 4D MR Images: Validation Using Large Clinical Datasets
We present a fully automated method to estimate the location and orientation of the left ventricle (LV) from four-dimensional (4D) cardiac magnetic resonance (CMR) images without requiring user input. The method is based on low-level image processing techniques which incorporate anatomical knowledge and is able to provide rapid, robust feedback for automated scan planning or further processing. The method relies on a novel combination of temporal Fourier analysis of image cines and simple contour detection to achieve a fast localization of the heart. Quantitative validation was performed using two 4D CMR datasets containing 395 patients (63720 images), with a range of cardiac and vascular disease, by comparing manual location with the automatic results. The method failed in only one case, and showed an average bias of better than 5mm in the apical, mid-ventricular and basal slices in the remaining 394. The errors in the automatically detected LV orientation were similar to those found in scan planning when performed by experienced technicians.
KeywordsCardiac Magnetic Resonance Right Ventricle Short Axis Slice Cardiac Magnetic Resonance Examination Middle Slice
Unable to display preview. Download preview PDF.
- 6.Spreeuwers, L., Breeuwer, M.: Automatic detection of the myocardial boundaries of the right and left ventricle. SPIE: Med. Imag. 4322, 1207–1217 (2001)Google Scholar
- 9.Anderson, C.: Rationale and design of the cardiac magnetic resonance imaging substudy of the ONTARGET trial programme. J. Int. Med. Res. 33(4), 50–57 (2005)Google Scholar
- 10.Young, A., Cowan, B., Thrupp, S., Hedley, W., Dell’Italia, L.: Left ventricular mass and volume: fast calculation with guide-point modeling on MR images. Radiology 216, 597–602 (2000)Google Scholar
- 11.Sörgel, W., Vaerman, V.: Automatic heart localization from 4D MRI datasets. SPIE: Med. Imag. 3034, 333–344 (1997)Google Scholar