Statistical Shape Modeling of the Left Ventricle: Myocardial Infarct Classification Challenge

Abstract

Statistical shape modeling is a powerful tool for visualizing and quantifying geometric and functional patterns of the heart. After myocardial infarction (MI), the left ventricle typically remodels in response to physiological challenges. Several methods have been proposed in the literature to describe statistical shape changes. Which method best characterizes left ventricular remodeling after MI is an open research question. A better descriptor of remodeling is expected to provide a more accurate evaluation of disease status in MI patients. We therefore designed a challenge to test shape characterization in MI given a set of three-dimensional left ventricular surface points. The training set comprised 100 MI patients, and 100 asymptomatic volunteers (AV). The challenge was initiated in 2015 at the Statistical Atlases and Computational Models of the Heart workshop, in conjunction with the MICCAI conference. The training set with labels was provided to participants, who were asked to submit the likelihood of MI from a different (validation) set of 200 cases (100 AV and 100 MI). Sensitivity, specificity, accuracy and area under the receiver operating characteristic curve were used as the outcome measures. The goals of this challenge were to (1) establish a common dataset for evaluating statistical shape modeling algorithms in MI, and (2) test whether statistical shape modeling provides additional information characterizing MI patients over standard clinical measures. Eleven groups with a wide variety of classification and feature extraction approaches participated in this challenge. All methods achieved excellent classification results with accuracy ranges from 0.83 to 0.98. The areas under the receiver operating characteristic curves were all above 0.90. Four methods showed significantly higher performance than standard clinical measures. The dataset and software for evaluation are available from the Cardiac Atlas Project website1.

Cardiac Motion Evolution Model for Analysis of Functional Changes Using Tensor Decomposition and Cross-Sectional Data

“…More recent techniques include statistical shape modelling [3] and [4], and atlas-based regional wall motion analysis [5]. A common constraint used in state-of-the-art methods to retain physiological motion dynamics is to enforce the deformations (which describe the motion from one image to another) to be diffeomorphic (smooth transformations that preserve the structure of the material to prevent non-physiological transformations such as folding).…”

Explainable Anatomical Shape Analysis Through Deep Hierarchical Generative Models

“…Moreover, the main modes of shape variation do not necessarily encode the anatomical information needed to differentiate disease classes. For this purpose, approaches that search for alternative axes of variation facilitating this differentiation have been proposed, including shape decomposition into orthogonal modes optimally related to clinical remodeling indices [11], [12].…”

Ventricle Surface Reconstruction from Cardiac MR Slices Using Deep Learning

“…Generating anatomically accurate 3D surface meshes has shown promising uses in a wide range of applications including cardiac function analysis, interventional guidance and diagnosis [1,2,3]. Personalization of cardiac surfaces in 3D is also the first step required for computational simulations of cardiac electromechanics using the finite element method [4,5,6].…”

“…Personalization of cardiac surfaces in 3D is also the first step required for computational simulations of cardiac electromechanics using the finite element method [4,5,6]. Cardiac MR (CMR) imaging provides accurate shape information of the heart non-invasively [2]. A standard clinical CMR study includes a stack of short-axis (SAX) slices, covering at least from the left/right ventricular (LV/RV) apex to the base, plus at least two long-axis (LAX) views: horizontal long-axis (HLA, also known as 4 chamber view or 4CH) and vertical long-axis (VLA, also known as 2 chamber view or 2CH) [7].…”