Segmentation of ECG-gated multi-detector row CT cardiac images for functional analysis

Abstract

Multi-row detector CT (MDCT) gated with ECG-tracing allows continuous image acquisition of the heart during a breath-hold with a high spatial and temporal resolution. Dynamic segmentation and display of CT images, especially short- and long-axis view, is important in functional analysis of cardiac morphology. The size of dynamic MDCT cardiac images, however, is typically very large involving several hundred CT images and thus a manual analysis of these images can be time-consuming and tedious. In this paper, an automatic scheme was proposed to segment and reorient the left ventricular images in MDCT. Two segmentation techniques, deformable model and region-growing methods, were developed and tested. The contour of the ventricular cavity was segmented iteratively from a set of initial coarse boundary points placed on a transaxial CT image and was propagated to adjacent CT images. Segmented transaxial diastolic cardiac phase MDCT images were reoriented along the long- and short-axis of the left ventricle. The axes were estimated by calculating the principal components of the ventricular boundary points and then confirmed or adjusted by an operator. The reorientation of the coordinates was applied to other transaxial MDCT image sets reconstructed at different cardiac phases. Estimated short-axes of the left ventricle were in a close agreement with the qualitative assessment by a radiologist. Preliminary results from our methods were promising, with a considerable reduction in analysis time and manual operations.