Segmentation of 3D Transesophageal Echocardiograms by Multi-cavity Active Shape Model and Gamma Mixture Model.

Segmentation of three-dimensional (3D) transesophageal ultrasound (TEE) is highly desired for intervention monitoring and guidance, but it is still a challenging image processing task due to complex local anatomy, limited field of view and typical ultrasound artifacts. We propose to use a multi-cavity active shape model (ASM) derived from Computed Tomography Angiography (CTA) segmentations in conjunction with a blood/tissue classification by Gamma Mixture Models to identify and segment the individual cavities simultaneously. A scheme that utilized successively ASMs of the whole heart and the individual cavities was used to segment the entire heart. We successfully validated our segmentation scheme with manually outlined contours and with CTA segmentations for three patients. The segmentations of the three patients had an average distance of 2.3, 4.9, and 2.1 mm to the manual outlines.