@article{bates_statistical_nodate,
	title = {Statistical {Shape} {Models} of {Cardiac} {Anatomy}},
	abstract = {The quantitative description of anatomical shapes, incorporating the statistical variation present within a population, is well established in biomedical image analysis. It has principally been used to inform image segmentation but it has also been applied as a technique in inferring statistical differences in shape between pathological and normal anatomies. Here we present and analyze a full pipeline from segmentation to classification in attempting to model and classify Hypertrophic Cardiomyopathy patients using both MRI and 3D ultrasound images. By fitting cubic Hermite mesh models to binary segmentations of the cardiac anatomy within the images we show that it is possible to characterize the variation within the population and use this to inform classification of new members as diseased or normal, achieving 92\% sensitivity and 94\% specificity using a combination of MRI and Ultrasound information and a newly proposed medial description.},
	language = {en},
	author = {Bates, Russell},
	pages = {10},
}

{"_id":"SK8chHAznfaeZgEwQ","bibbaseid":"bates-statisticalshapemodelsofcardiacanatomy","author_short":["Bates, R."],"bibdata":{"bibtype":"article","type":"article","title":"Statistical Shape Models of Cardiac Anatomy","abstract":"The quantitative description of anatomical shapes, incorporating the statistical variation present within a population, is well established in biomedical image analysis. It has principally been used to inform image segmentation but it has also been applied as a technique in inferring statistical differences in shape between pathological and normal anatomies. Here we present and analyze a full pipeline from segmentation to classification in attempting to model and classify Hypertrophic Cardiomyopathy patients using both MRI and 3D ultrasound images. By fitting cubic Hermite mesh models to binary segmentations of the cardiac anatomy within the images we show that it is possible to characterize the variation within the population and use this to inform classification of new members as diseased or normal, achieving 92% sensitivity and 94% specificity using a combination of MRI and Ultrasound information and a newly proposed medial description.","language":"en","author":[{"propositions":[],"lastnames":["Bates"],"firstnames":["Russell"],"suffixes":[]}],"pages":"10","bibtex":"@article{bates_statistical_nodate,\n\ttitle = {Statistical {Shape} {Models} of {Cardiac} {Anatomy}},\n\tabstract = {The quantitative description of anatomical shapes, incorporating the statistical variation present within a population, is well established in biomedical image analysis. It has principally been used to inform image segmentation but it has also been applied as a technique in inferring statistical differences in shape between pathological and normal anatomies. Here we present and analyze a full pipeline from segmentation to classification in attempting to model and classify Hypertrophic Cardiomyopathy patients using both MRI and 3D ultrasound images. By fitting cubic Hermite mesh models to binary segmentations of the cardiac anatomy within the images we show that it is possible to characterize the variation within the population and use this to inform classification of new members as diseased or normal, achieving 92\\% sensitivity and 94\\% specificity using a combination of MRI and Ultrasound information and a newly proposed medial description.},\n\tlanguage = {en},\n\tauthor = {Bates, Russell},\n\tpages = {10},\n}\n\n","author_short":["Bates, R."],"key":"bates_statistical_nodate-1-1","id":"bates_statistical_nodate-1-1","bibbaseid":"bates-statisticalshapemodelsofcardiacanatomy","role":"author","urls":{},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/jjAllen01","dataSources":["b2rH2vd6Bpc9f2j4b"],"keywords":[],"search_terms":["statistical","shape","models","cardiac","anatomy","bates"],"title":"Statistical Shape Models of Cardiac Anatomy","year":null}