Semi-Automatic Segmentation of the LV Cavity in Contrast Enhanced Echocardiographic Clips

Myocardial contrast enhanced ultrasound (CEUS) is an imaging method for assessing left ventricle (LV) volume and function, and for myocardial perfusion estimation. Accurate automatic segmentation may help physicians estimate more objectively the function of the heart (e.g.) measuring end-diastolic volume, ejection fraction). Thus, a segmentation algorithm of the LV endocardial boundary in CEUS clips was developed. First, the user defines a ROI and marks the center of the cavity and the two basal points on the first frame of the clip. Then, attenuation correction is performed on the images, to correct the intensity attenuation along the LV cavity. An initial estimation of the boundary is defined, followed by correction of the initial segmented boundary in three steps: (1) Endocardial boundary estimation, (2) Basal region correction, (3) Papillary muscle correction. We have compared the automatic boundaries to the manually segmented boundaries in 9 clips from 9 patients, and obtained a mean absolute distance (MAD) of 5.94 (SD=1.40) pixels between the two boundaries and a mean Jaccard index of 0.90 (SD=0.02). These results prove high similarity between manual and automatic curves and areas. Our algorithm provides a semi-automatic and accurate segmentation, enabling objective and efficient LV cavity delineation.