Automatic segmentation of the right ventricle from cardiac MRI using a learning‐based approach

• Published in: Magnetic resonance in medicine Vol. 78; no. 6; pp. 2439 - 2448
• Main Authors: Avendi, Michael R., Kheradvar, Arash, Jafarkhani, Hamid
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.12.2017
• Subjects: Algorithms; Artificial neural networks; Automation; Blood pressure; cardiac MRI; Correlation analysis; deep learning; deformable models; Deformation; Formability; Ground truth; Heart; Heart - diagnostic imaging; Heart diseases; Heart Ventricles - diagnostic imaging; Humans; Image Interpretation, Computer-Assisted; Image processing; Image Processing, Computer-Assisted; Learning algorithms; Machine Learning; Magnetic Resonance Imaging; Model accuracy; Models, Statistical; Neural networks; Neural Networks (Computer); Pattern Recognition, Automated; Reproducibility of Results; right ventricle; Segmentation; Ventricle; deep learning; segmentation; cardiac MRI; right ventricle; deformable models
• ISSN: 0740-3194; 1522-2594; 1522-2594
• DOI: 10.1002/mrm.26631

Purpose This study aims to accurately segment the right ventricle (RV) from cardiac MRI using a fully automatic learning‐based method. Methods The proposed method uses deep learning algorithms, i.e., convolutional neural networks and stacked autoencoders, for automatic detection and initial segmentation of the RV chamber. The initial segmentation is then combined with the deformable models to improve the accuracy and robustness of the process. We trained our algorithm using 16 cardiac MRI datasets of the MICCAI 2012 RV Segmentation Challenge database and validated our technique using the rest of the dataset (32 subjects). Results An average Dice metric of 82.5% along with an average Hausdorff distance of 7.85 mm were achieved for all the studied subjects. Furthermore, a high correlation and level of agreement with the ground truth contours for end‐diastolic volume (0.98), end‐systolic volume (0.99), and ejection fraction (0.93) were observed. Conclusion Our results show that deep learning algorithms can be effectively used for automatic segmentation of the RV. Computed quantitative metrics of our method outperformed that of the existing techniques participated in the MICCAI 2012 challenge, as reported by the challenge organizers. Magn Reson Med 78:2439–2448, 2017. © 2017 International Society for Magnetic Resonance in Medicine.