Machine Learning-Derived Fractal Features of Shape and Texture of the Left Atrium and Pulmonary Veins From Cardiac Computed Tomography Scans Are Associated With Risk of Recurrence of Atrial Fibrillation Postablation

Circ Arrhythm Electrophysiol. 2021 Mar;14(3):e009265. doi: 10.1161/CIRCEP.120.009265. Epub 2021 Feb 12.

Marjan Firouznia¹, Albert K Feeny², Michael A LaBarbera², Meghan McHale^{3

4}, Catherine Cantlay⁴, Natalie Kalfas⁴, Paul Schoenhagen^{2

3

5}, Walid Saliba³, Patrick Tchou³, John Barnard⁶, Mina K Chung^{2

3}, Anant Madabhushi^{1

4

7}

¹ Department of Biomedical Engineering (M.F., A.M.), Case Western Reserve University.
² Cleveland Clinic Lerner College of Medicine (A.K.F., M.A.L., P.S., M.K.C.), Case Western Reserve University.
³ Department of Cardiovascular Medicine, Heart, Vascular & Thoracic Institute (M.M., P.S., W.S., P.T., M.K.C.).
⁴ Cardiovascular and Metabolic Sciences, Lerner Research Institute (M.M., C.C., N.K., M.K.C.), Diagnostic Radiology, Cleveland Clinic.
⁵ Imaging Institute (P.S.), Diagnostic Radiology, Cleveland Clinic.
⁶ Quantitative Health Sciences, Lerner Research Institute (J.B.), Diagnostic Radiology, Cleveland Clinic.
⁷ Louis Stokes Cleveland Veterans Administration Medical Center, OH (A.M.).

Abstract

[Figure: see text].

Keywords: atrial fibrillation; catheter ablation; heart failure; machine learning; pulmonary veins.