Comprehensive Segmentation of Cine Cardiac MR Images

Abstract

Abstract. A typical Cardiac Magnetic Resonance (CMR) examination includes acquisition of a sequence of short-axis (SA) and long-axis (LA) images covering the cardiac cycle. Quantitative analysis of the heart function requires segmentation of the left ventricle (LV) SA images, while segmented LA views allow more accurate estimation of the basal slice and can be used for slice registration. Since manual segmentation of CMR images is very tedious and time-consuming, its automation is highly required. In this paper, we propose a fully automatic 2D method for segmenting LV consecutively in LA and SA images. The approach was validated on 35 patients giving mean segmentation error smaller than one pixel, both for LA and SA, and accurate LV volume measurements.

Combining Registration and Minimum Surfaces for the Segmentation of the Left Ventricle in Cardiac Cine MR Images

“…We demonstrated on 19 datasets that the results look very good and the errors are small enough that the system can be used in clinical settings. In the future, we would like to combine this short axis segmentation with a long axis segmentation (similar to [4]) as it will help in resolving the more difficult cases in the basal and apical slices.…”

“…The opposite approach of segmenting each image individually [2] results in little cohesion between images and unsmooth contours over time. The intermediate approach used very often of segmenting the LV in one phase on all slices [3,4] can be quite difficult. When a model is used, it needs to be carefully trained for all possible LV shapes and all possible MR acquisition protocols.…”

Collaborative Tracking for MRI-Guided Robotic Intervention on the Beating Heart

“…Such approach may entail defining an appropriate optimization scheme to iteratively minimize a cost function, and the computational cost can be significant. For example, in [6], while the proposed boundary segmentation method achieved very high accuracy, the computational time was 10 seconds per slice. In contrast, Yuen et al [7] achieved real-time performance in Ultrasound images with an extended Kalman filter tracker.…”

Left Ventricle Segmentation via Graph Cut Distribution Matching

“…Albeit an impressive research effort has been devoted to the LV [1]- [15], current methods are still not sufficiently fast and flexible for routine clinical use, mainly because of the difficulties inherent to MR cardiac images [4]. Existing methods are based, among others, on active contours [1]- [3], [5]- [11], active appearance/shape models [12], [14], and registration [15]. Generally, the problem is stated as an energy optimization.…”

“…Generally, the problem is stated as an energy optimization. In this connection, optimization of active contour functionals has been the most prevalent and flexible choice in the literature because it allows introducing a wide range of photometric and geometric 1 constraints on the solution [1]- [3], [5]- [11]. Generally, these constraints reference a sum over the target region or its boundary of pixelwise correspondences between the image and geometric/photometric models learned from a training set.…”