Title :
A novel aortic valve segmentation from ultrasound image using continuous max-flow approach
Author :
Yuanyuan Nie ; Zhe Luo ; Junfeng Cai ; Lixu Gu
Author_Institution :
Lab. of Image Guided Surg. & Therapy (IGST), Shanghai Jiao Tong Univ. (SJTU), Shanghai, China
Abstract :
Geometric features of aortic valve can be applied in diagnostic, modeling and image-guided cardiac intervention, however methods to accurately and effectively delineate aortic valve from ultrasound (US) image are not well addressed. This paper proposes a novel aortic valve segmentation algorithm for intra-operative 2D short-axis US image using probability estimation and continuous max-flow (CMF) approach. The algorithm first calculates composite probability estimation (CPE) and single probability estimation (SPE) over 5 prior images based on both intensity and distance to the corresponding centroid, then the energy function for the current input image is constructed, followed by a Graphic Processing Unit (GPU) accelerated CMF approach to achieve aortic valve contours in approximately real time. Quantitative evaluations over 270 images acquired from 3 subjects indicated the results of the algorithm had good correlation with the manual segmentation results (ground truth) by an expert. The Average Symmetric Contour Distance (ASCD), Dice Metric (DM), and Reliability were employed to evaluate our algorithm, and the evaluation results of these three metrics were 1.79±0.46 (in pixels), 0.96±0.01 and 0.84 (d=0.95) respectively, where the computational time was 39.23±5.02 ms per frame.
Keywords :
biomedical ultrasonics; cardiology; feature extraction; graphics processing units; image segmentation; medical image processing; probability; ultrasonic imaging; Dice metrics; GPU; average symmetric contour distance; continuous max-flow approach; current input image; diagnostic cardiac intervention; energy function; geometric features; graphic processing unit; image acquisition; image-guided cardiac intervention; intraoperative 2D short-axis ultrasound image; manual segmentation results; novel aortic valve segmentation algorithm; quantitative evaluations; reliability; single probability estimation; Biomedical imaging; Estimation; Graphics processing units; Image segmentation; Reliability; Ultrasonic imaging; Valves;
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE
Conference_Location :
Osaka
DOI :
10.1109/EMBC.2013.6610249