Fully automatic segmentation of left atrium and pulmonary veins in late gadolinium-enhanced MRI: Towards objective atrial scar assessment

• Published in: Journal of magnetic resonance imaging Vol. 44; no. 2; pp. 346 - 354
• Main Authors: Tao, Qian, Ipek, Esra Gucuk, Shahzad, Rahil, Berendsen, Floris F., Nazarian, Saman, van der Geest, Rob J.
• Format: Journal Article
• Language: English
• Published: United States Blackwell Publishing Ltd 01.08.2016; Wiley Subscription Services, Inc
• Subjects: Ablation; Age; Algorithms; Anatomy; Angiography; Atrial Fibrillation - diagnostic imaging; Atrial Fibrillation - etiology; Atrium; automatic segmentation; Cicatrix - complications; Cicatrix - diagnostic imaging; Contrast Media - administration & dosage; Fibrillation; Gadolinium; Gadolinium DTPA - administration & dosage; Heart Atria - diagnostic imaging; Heart diseases; Human performance; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Image processing; Image segmentation; Imaging, Three-Dimensional; Information dissemination; left atrium; LGE-MRI; Magnetic Resonance Angiography - methods; Magnetic resonance imaging; MRA; NMR; Nuclear magnetic resonance; Patients; Pattern Recognition, Automated - methods; pulmonary veins; Pulmonary Veins - diagnostic imaging; Reproducibility of Results; Resonance; Sensitivity and Specificity; Veins; LGE-MRI; automatic segmentation; left atrium; MRA; pulmonary veins
• ISSN: 1053-1807; 1522-2586; 1522-2586
• DOI: 10.1002/jmri.25148

Purpose To realize objective atrial scar assessment, this study aimed to develop a fully automatic method to segment the left atrium (LA) and pulmonary veins (PV) from late gadolinium‐enhanced (LGE) magnetic resonance imaging (MRI). The extent and distribution of atrial scar, visualized by LGE‐MRI, provides important information for clinical treatment of atrial fibrillation (AF) patients. Materials and Methods Forty‐six AF patients (age 62 ± 8, 14 female) who underwent cardiac MRI prior to RF ablation were included. A contrast‐enhanced MR angiography (MRA) sequence was acquired for anatomy assessment followed by an LGE sequence for LA scar assessment. A fully automatic segmentation method was proposed consisting of two stages: 1) global segmentation by multiatlas registration; and 2) local refinement by 3D level‐set. These automatic segmentation results were compared with manual segmentation. Results The LA and PVs were automatically segmented in all subjects. Compared with manual segmentation, the method yielded a surface‐to‐surface distance of 1.49 ± 0.65 mm in the LA region when using both MRA and LGE, and 1.80 ± 0.93 mm when using LGE alone (P < 0.05). In the PV regions, the distance was 2.13 ± 0.67 mm and 2.46 ± 1.81 mm (P < 0.05), respectively. The difference between automatic and manual segmentation was comparable to the interobserver difference (P = 0.8 in LA region and P = 0.7 in PV region). Conclusion We developed a fully automatic method for LA and PV segmentation from LGE‐MRI, with comparable performance to a human observer. Inclusion of an MRA sequence further improves the segmentation accuracy. The method leads to automatic generation of a patient‐specific model, and potentially enables objective atrial scar assessment for AF patients. J. Magn. Reson. Imaging 2016;44:346–354.