Interactive Hierarchical-Flow Segmentation of Scar Tissue From Late-Enhancement Cardiac MR Images

Abstract

We propose a novel multi-region image segmentation approach to extract myocardial scar tissue from 3-D whole-heart cardiac late-enhancement magnetic resonance images in an interactive manner. For this purpose, we developed a graphical user interface to initialize a fast max-flow-based segmentation algorithm and segment scar accurately with progressive interaction. We propose a partially-ordered Potts (POP) model to multi-region segmentation to properly encode the known spatial consistency of cardiac regions. Its generalization introduces a custom label/region order constraint to Potts model to multi-region segmentation. The combinatorial optimization problem associated with the proposed POP model is solved by means of convex relaxation, for which a novel multi-level continuous max-flow formulation, i.e., the hierarchical continuous max-flow (HMF) model, is proposed and studied. We demonstrate that the proposed HMF model is dual or equivalent to the convex relaxed POP model and introduces a new and efficient hierarchical continuous max-flow based algorithm by modern convex optimization theory. In practice, the introduced hierarchical continuous max-flow based algorithm can be implemented on the parallel GPU to achieve significant acceleration in numerics. Experiments are performed in 50 whole heart 3-D LE datasets, 35 with left-ventricular and 15 with right-ventricular scar. The experimental results are compared to full-width-at-half-maximum and Signal-threshold to reference-mean methods using manual expert myocardial segmentations and operator variabilities and the effect of user interaction are assessed. The results indicate a substantial reduction in image processing time with robust accuracy for detection of myocardial scar. This is achieved without the need for additional region constraints and using a single optimization procedure, substantially reducing the potential for error.

Right ventricle segmentation from cardiac MRI: A collation study

“…This is still the main stream, and it has some advantages: the 2D short-axis acquisition is accompanied by 4-chamber and long-axis imaging acquisitions which allow for an easy identification of the pulmonary and tricuspid valves, thus preventing to include ''out-of-RV'' volumes (such as pulmonary artery or atrial volume). However, it seems that some groups have started to work on 3D isotropic MR images: voxel reported to be 1.4 Â 1.4 Â 1.4 mm in Rajchl et al (2014), 2.5 Â 2.5 Â 2.5 mm in Uribe et al (2007), 2Â 2 Â 4 mm (reconstructed to 2 Â 2 Â 2 mm) in Dawes et al (2013). Authors of Uribe et al (2007) mentioned the drawback of the 3D SSFP sequence is that ''current methods, even those that use undersampling techniques, involve breath-holding for periods that are too long for many patients.''…”

Three-dimensional segmentation of retroperitoneal masses using continuous convex relaxation and accumulated gradient distance for radiotherapy planning

“…One study, published by Ukwatta et al [45], described the segmentation of the carotid artery in 3D MRI images. The same research group also used this technique to extract myocardial scar tissue [38], to segment the femoral artery lumen and outer wall surfaces [46], to segment lateral ventricles in preterm neonates with intraventricular hemorrhage [36], and to delineate 3D prostate boundaries for the planning and guiding of prostate biopsies [37,53].…”

Directed Acyclic Graph Continuous Max-Flow Image Segmentation for Unconstrained Label Orderings

“…The Potts model only allows for completely unordered labels and the Ishikawa model only allows for fully ordered labels. Recent approaches in partially ordered labels in continuous max-flow image segmentation [35] illustrated that relaxing these constraints on extendable models could have practical significance, using a flexible label ordering to encode knowledge about the scene composition.…”

“…This is in contrast to earlier work in hierarchical max-flow label ordering in which the particular label ordering (and thus the number of labels) was fixed. [35] The solvers guarantee global optimality for fuzzy labels where u L (x) ∈ [0, 1], but as this framework is a strict generalization of the Potts model, it cannot in general guarantee an globally optimal binary labeling where u L (x) ∈ {0, 1}.…”