Max-flow segmentation of the left ventricle by recovering subject-specific distributions via a bound of the Bhattacharyya measure

• Published in: Medical image analysis Vol. 16; no. 1; pp. 87 - 100
• Main Authors: Ben Ayed, Ismail, Chen, Hua-mei, Punithakumar, Kumaradevan, Ross, Ian, Li, Shuo
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.01.2012
• Subjects: Algorithms; Bhattacharyya measure; Cardiac magnetic resonance images (cardiac MRI); Heart Ventricles - pathology; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Left ventricle segmentation; Magnetic Resonance Imaging, Cine - methods; Max-flow optimization; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Ventricular Dysfunction, Left - pathology; Bhattacharyya measure; Left ventricle segmentation; Max-flow optimization; Cardiac magnetic resonance images (cardiac MRI)
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2011.05.009

This study investigates fast detection of left ventricle boundaries following the optimization of new distribution-based functions. Based on max-flow iterations and bound relaxation, the proposed algorithm yields a competitive performance in nearly real-time. [Display omitted] ► Novel distribution-based cost functions for left ventricle segmentation. ► Novel optimization based on bound derivation and max-flow iterations. ► Competitive performance in nearly real-time. This study investigates fast detection of the left ventricle (LV) endo- and epicardium boundaries in a cardiac magnetic resonance (MR) sequence following the optimization of two original discrete cost functions, each containing global intensity and geometry constraints based on the Bhattacharyya similarity. The cost functions and the corresponding max-flow optimization built upon an original bound of the Bhattacharyya measure yield competitive results in nearly real-time. Within each frame, the algorithm seeks the LV cavity and myocardium regions consistent with subject-specific model distributions learned from the first frame in the sequence. Based on global rather than pixel-wise information, the proposed formulation relaxes the need of a large training set and optimization with respect to geometric transformations. Different from related active contour methods, it does not require a large number of iterative updates of the segmentation and the corresponding computationally onerous kernel density estimates (KDEs). The algorithm requires very few iterations and KDEs to converge. Furthermore, the proposed bound can be used for several other applications and, therefore, can lead to segmentation algorithms which share the flexibility of active contours and computational advantages of max-flow optimization. Quantitative evaluations over 2280 images acquired from 20 subjects demonstrated that the results correlate well with independent manual segmentations by an expert. Moreover, comparisons with a related recent active contour method showed that the proposed framework brings significant improvements in regard to accuracy and computational efficiency.