A combined random forest classifier and active shape model improved left ventricle boundary detection accuracy compared to an active shape model alone, producing a global overlap coefficient of 90.09% vs 83.8%.
Left ventricle segmentation from ultrasound images (n=85)
Random forest classifier combined with an active shape model vs Active shape model alone
Global overlap coefficient compared to expert-traced LV contours
Absolute Event Rate: 90.09% vs 83.8%
This paper presents a model-based learning segmentation algorithm to detect the left ventricle (LV) boundary of the heart from ultrasound (US) images by combining a random forest classifier with an active shape model (ASM). Our method applies an ASM for initial detection of the LV landmarks. Each landmark is subsequently directed radially inward or outward as a result of the random forest classifier identifying the landmark as outside or inside the LV boundary, respectively. This is done while preserving the shape characteristics obtained from the ASM. Our objective is to evaluate the combined application of a random forest classifier with an ASM for detecting the LV boundary with US images. Accuracy of this method is evaluated by comparing both our method and ASM to LV contours traced by an expert. A dataset of 85 randomly selected patient studies was chosen. The method exhibits improved accuracy compared to the ASM, producing a global overlap coefficient of 90.09% compared to 83.8% obtained with an active shape model.
Building similarity graph...
Analyzing shared references across papers
Loading...
Gregg Belous
Australian e-Health Research Centre
Andrew Busch
Griffith University
D. D. Rowlands
Griffith University
Griffith University
Greenslopes Private Hospital
Building similarity graph...
Analyzing shared references across papers
Loading...
Belous et al. (Sun,) conducted a other in Left ventricle segmentation from ultrasound images (n=85). Random forest classifier combined with an active shape model vs. Active shape model alone was evaluated on Global overlap coefficient compared to expert-traced LV contours. A combined random forest classifier and active shape model improved left ventricle boundary detection accuracy compared to an active shape model alone, producing a global overlap coefficient of 90.09% vs 83.8%.
synapsesocial.com/papers/6a16e01c66334ab13b056d7e — DOI: https://doi.org/10.1109/aims.2013.58