Patient-Specific Modeling and Quantification of the Aortic and Mitral Valves From 4-D Cardiac CT and TEE

Abstract

As decisions in cardiology increasingly rely on noninvasive methods, fast and precise image processing tools have become a crucial component of the analysis workflow. To the best of our knowledge, we propose the first automatic system for patient-specific modeling and quantification of the left heart valves, which operates on cardiac computed tomography (CT) and transesophageal echocardiogram (TEE) data. Robust algorithms, based on recent advances in discriminative learning, are used to estimate patient-specific parameters from sequences of volumes covering an entire cardiac cycle. A novel physiological model of the aortic and mitral valves is introduced, which captures complex morphologic, dynamic, and pathologic variations. This holistic representation is hierarchically defined on three abstraction levels: global location and rigid motion model, nonrigid landmark motion model, and comprehensive aortic-mitral model. First we compute the rough location and cardiac motion applying marginal space learning. The rapid and complex motion of the valves, represented by anatomical landmarks, is estimated using a novel trajectory spectrum learning algorithm. The obtained landmark model guides the fitting of the full physiological valve model, which is locally refined through learned boundary detectors. Measurements efficiently computed from the aortic-mitral representation support an effective morphological and functional clinical evaluation. Extensive experiments on a heterogeneous data set, cumulated to 1516 TEE volumes from 65 4-D TEE sequences and 690 cardiac CT volumes from 69 4-D CT sequences, demonstrated a speed of 4.8 seconds per volume and average accuracy of 1.45 mm with respect to expert defined ground-truth. Additional clinical validations prove the quantification precision to be in the range of inter-user variability. To the best of our knowledge this is the first time a patient-specific model of the aortic and mitral valves is automatically estimated from volumetric sequences.

Modeling Mitral Valve Leaflets from Three-Dimensional Ultrasound

“…The method subsequently required manual intervention and the assumption of a planar annulus to construct an isolated leaflet mesh geometry. The method presented in [5] segmented and tracked the locations of several features of the mitral and aortic valve structures in 3DUS using machine learning techniques. It then fit a parametric model to the segmented locations.…”

Patient-Specific Model of Left Heart Anatomy, Dynamics and Hemodynamics from 4D TEE: A First Validation Study

“…On average the precision was 1.73mm at a speed of 4.8sec per volume for the valvular model and 2.68mm at a speed of less than 1sec per volume for the left ventricle [6,7].…”

“…Given the physiological complexity of the left heart, we selected a modular and hierarchical approach, which facilitates capturing a broad spectrum of morphological and pathological variations. The model is parameterized as follows: The patient-specific parameters of the valvular apparatus and left ventricle are estimated from 4D TEE images using a hierarchical discriminative learning algorithm as proposed in [6,7]. The a posteriori probability p(B, L, M |I) of the model given the image data I is incrementally modeled within the Marginal Space Learning (MSL) framework.…”

“…The complex local motion of the surface structures is estimated with a combination of the aforementioned techniques and speckle tracking methods [7]. For further details on model estimation the reader is referred to [6,7]. The left atrium (LA) and pulmonary veins are commonly only partially visible in TEE acquisitions, which hampered an accurate automatic segmentation.…”

“…Although patient-specific measurements have been increasingly used to enhanced computational models [4,5], current simulations are still lacking the accuracy required in the clinical practice. Recently, detailed anatomical models of the heart dynamics have been proposed [6]. Such models, coupled with CFD frameworks [4] open the way to data-driven patient-specific models of anatomy, dynamics and hemodynamics.…”