Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI

• Published in: Medical image analysis Vol. 31; pp. 77 - 87
• Main Authors: Zhuang, Xiahai, Shen, Juan
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.07.2016
• Subjects: Algorithms; Heart - anatomy & histology; Heart - diagnostic imaging; Humans; Image Enhancement; Image Interpretation, Computer-Assisted - methods; Local atlas ranking; Magnetic Resonance Imaging - methods; Multi-modality atlas; Multi-scale patch; Multimodal Imaging - methods; Pattern Recognition, Automated - methods; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique; Tomography, X-Ray Computed; Whole heart segmentation; Whole heart segmentation; Multi-modality atlas; Multi-scale patch; Local atlas ranking
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2016.02.006

•Multi-scale patch is proposed for hierarchical local atlas ranking.•A multi-modality multi-atlas scheme is developed for whole heart segmentation.•A validation and comparison study for whole heart MRI segmentation is performed.•Segmentation results demonstrate the performance of the proposed method.•The proposed method may be useful in clinical care of cardiovascular diseases. [Display omitted] A whole heart segmentation (WHS) method is presented for cardiac MRI. This segmentation method employs multi-modality atlases from MRI and CT and adopts a new label fusion algorithm which is based on the proposed multi-scale patch (MSP) strategy and a new global atlas ranking scheme. MSP, developed from the scale-space theory, uses the information of multi-scale images and provides different levels of the structural information of images for multi-level local atlas ranking. Both the local and global atlas ranking steps use the information theoretic measures to compute the similarity between the target image and the atlases from multiple modalities. The proposed segmentation scheme was evaluated on a set of data involving 20 cardiac MRI and 20 CT images. Our proposed algorithm demonstrated a promising performance, yielding a mean WHS Dice score of 0.899 ± 0.0340, Jaccard index of 0.818 ± 0.0549, and surface distance error of 1.09 ± 1.11 mm for the 20 MRI data. The average runtime for the proposed label fusion was 12.58 min.