Simultaneous segmentation of multiple heart cavities in 3D transesophageal echocardiograms

Three-dimensional transesophageal echocardiography (3D TEE) is an excellent modality for real-time visualization of the heart and monitoring of interventions. However, 3D TEE segmentation is still a challenging task due to the complex anatomy, the limited field of view, and typical ultrasound artifacts. To improve the usability of 3D TEE for monitoring interventions, we propose to segment all cavities within the TEE view with a multi-cavity Active Shape Model (ASM) derived from Computed Tomography Angiography (CTA) in conjunction with a tissue/blood classification based on a Gamma Mixture Model (GMM). 3D TEE image data of five patients were acquired with a Philips X7-2t matrix TEE probe. Tissue probability maps were estimated by a two class (blood/tissue) GMM. A statistical shape model containing left and right ventricle, left and right atrium and aorta (LV, LA, RV, LA, Ao) was derived from CTA scans of 151 patients by Principal Component Analysis. Models from individual cavities (ASMpart: ASMLV etc.) and of the whole heart (ASMtot) were generated. First, ASMtot was aligned with the 3D TEE by indicating 3 anatomical landmarks. Second, pose and shape of ASMtot were iteratively updated by a weighted update scheme excluding parts outside of the image sector. Third, shape and pose of each ASMpart were initialized based on shape and pose of ASMtot and iteratively updated in a constrained manner to fit the tissue probability maps. All 3D TEE sets were manually outlined in multiple short and long axis views by two observers. The mean outline of both observers was compared to the ASM segmentations by calculating Dice coefficients. All patients had preoperative CTA scans which were segmented using an atlas approach. The TEE and the CTA segmentation were registered and Dice coefficients were computed. The Dice coefficients of the whole heart between the average observer and ASM segmentations were 0.- 1, 0.75, 0.87, 0.88, and 0.84 (interobserver variability: 0.95, 0.92, 0.92, 0.88, and 0.90) for TEE set 1 to 5 respectively. The Dice coefficient for the whole hart between CTA and TEE segmentation were 0.85, 0.80, 0.80, 0.81, and 0.71 and showed good agreement. In this work we could successfully show the accuracy and robustness of the proposed multi-cavity segmentation scheme.