FK-means: automatic atrial fibrosis segmentation using fractal-guided K-means clustering with Voronoi-clipping feature extraction of anatomical structures

Abstract

Assessment of left atrial (LA) fibrosis from late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) adds to the management of patients with atrial fibrillation. However, accurate assessment of fibrosis in the LA wall remains challenging. Excluding anatomical structures in the LA proximity using clipping techniques can reduce misclassification of LA fibrosis. A novel FK-means approach for combined automatic clipping and automatic fibrosis segmentation was developed. This approach combines a feature-based Voronoi diagram with a hierarchical 3D K-means fractal-based method. The proposed automatic Voronoi clipping method was applied on LGE-MRI data and achieved a Dice score of 0.75, similar to the score obtained by a deep learning method (3D UNet) for clipping (0.74). The automatic fibrosis segmentation method, which uses the Voronoi clipping method, achieved a Dice score of 0.76. This outperformed a 3D UNet method for clipping and fibrosis classification, which had a Dice score of 0.69. Moreover, the proposed automatic fibrosis segmentation method achieved a Dice score of 0.90, using manual clipping of anatomical structures. The findings suggest that the automatic FK-means analysis approach enables reliable LA fibrosis segmentation and that clipping of anatomical structures in the atrial proximity can add to the assessment of atrial fibrosis.

Electrifying insights into cardiac arrhythmias: from molecular mechanisms to therapeutic translations

“…The studies presented in this special edition of Interface Focus represent a broad spectrum of approaches that add to our body of arrhythmic knowledge and understanding. They include in vivo [1,2], in silico [3][4][5][6][7], in vitro [8] and ex vivo [7,9] studies covering animal [1,7,9] and human [3,8] models and clinical imaging [2]. Most consider implications for the atria [1,2,[4][5][6], reflecting the dominant morbidity and mortality burden of atrial fibrillation in many parts of the world, with the balance studying ventricular electrical function [3,7,9].…”

“…They include in vivo [1,2], in silico [3][4][5][6][7], in vitro [8] and ex vivo [7,9] studies covering animal [1,7,9] and human [3,8] models and clinical imaging [2]. Most consider implications for the atria [1,2,[4][5][6], reflecting the dominant morbidity and mortality burden of atrial fibrillation in many parts of the world, with the balance studying ventricular electrical function [3,7,9]. The motivating pro-arrhythmic disease states are similarly varied and include metabolic syndrome [1], atrial fibrillation [2,4,6,8], long-QT syndrome [3], pulmonary arterial hypertension [5] and myocardial induced heart failure [9].…”

“…Most consider implications for the atria [1,2,[4][5][6], reflecting the dominant morbidity and mortality burden of atrial fibrillation in many parts of the world, with the balance studying ventricular electrical function [3,7,9]. The motivating pro-arrhythmic disease states are similarly varied and include metabolic syndrome [1], atrial fibrillation [2,4,6,8], long-QT syndrome [3], pulmonary arterial hypertension [5] and myocardial induced heart failure [9]. While some of the studies explicitly consider a range of scales or dimensions [3,5,6], others focus on the cellular or subcellular space [7,9], the whole heart [2,4,8] or non-invasive torso-scale signals [1].…”

“…The motivating pro-arrhythmic disease states are similarly varied and include metabolic syndrome [1], atrial fibrillation [2,4,6,8], long-QT syndrome [3], pulmonary arterial hypertension [5] and myocardial induced heart failure [9]. While some of the studies explicitly consider a range of scales or dimensions [3,5,6], others focus on the cellular or subcellular space [7,9], the whole heart [2,4,8] or non-invasive torso-scale signals [1].…”

“…Together, the studies reported in this special edition of Interface Focus are a taster of the exciting research tracks currently pursued in the cardiac arrhythmia field. Some of these works are poised for clinical and health science translation [1,2], others present tantalizing new mechanistic insights and patient-specific pathways across complexity scales with digital models [3][4][5][6][7], while the final two studies seek to bridge from bench to bedside by examining the links between clinically accessible tissue structure and detailed function [8], as well as pharmaceutical interventions and outcomes [9].…”