Integrating a gradient–based difference operator with machine learning techniques in right heart segmentation

dc.contributor.authorHuérfano, Y.
dc.contributor.authorVera, M.
dc.contributor.authorMar, A.
dc.contributor.authorBravo, A.
dc.description.abstractIn this research a three step method for right heart segmentation based on a gradient– based difference operator and machine learning techniques is reported. The proposed method is applied to human heart multi–slice computerized tomography (MSCT) volumes. The first step is the preprocessing, where a gradient–based difference operator is applied to exploit the functional relationship between the original input image and its edge enhanced version. In the second step, the least squares support vector machines (LSSVM) are used with a double purpose. First, an appropriate volume-of-interest is automatically established in order to isolate the structure to segment. Second, another LSSVM is trained for locating the voxels required for initializing the seed based clustering procedure. In the third step (segmentation step), the preprocessed volumes are subsequently processed with an unsupervised clustering technique based on simple linkage region growing. Dice score is used as a metric function to compare the segmentations obtained using the proposed method with respect to ground truth volumes traced by a cardiologist. The right atrium, pulmonary valve, right ventricle and venae cavae are segmented from 80 cardiac MSCT volumes. Reported metrics confirm that this method is a promising technique for right heart segmentation.eng
dc.publisherIOP Publishingeng
dc.rights.licenseLicencia de Creative Commons Reconocimiento-NoComercial-CompartirIgual 4.0 Internacionalspa
dc.sourceJournal of Physicseng
dc.sourceIOP Conf. Series: Journal of Physics: Conf. Series 1160 (2019) 012003eng
dc.subjectComputed tomographyeng
dc.subjectSegmentation of the hearteng
dc.subjectHeart - Diseases - Diagnosiseng
dc.titleIntegrating a gradient–based difference operator with machine learning techniques in right heart segmentationeng
dcterms.referencesPetitjean C et al. 2015 Right ventricle segmentation from cardiac MRI: A collation study Med. Image Anal. 19(1) 187eng
dcterms.referencesZhuang X, Rhode K, Razavi R, Hawkes D and Ourselin S 2010 A registration-based propagation framework for automatic whole heart segmentation of cardiac MRI IEEE Trans. Med. Imag. 29(9) 1612eng
dcterms.referencesKirisli H et al. 2010 Evaluation of a multi–atlas based method for segmentation of cardiac CTA data: A large–scale, multi–center and multi–vendor study Med. Phys. 37(12) 6279eng
dcterms.referencesGhesu F, Krubasik E, Georgescu B, Singh V, Zheng Y, Hornegger J and Comaniciu D 2016 Marginal space deep learning: Efficient architecture for volumetric image parsing IEEE Transactions on Medical Imaging 35(5) 1217eng
dcterms.referencesFernandez N, Gonzalez S, Rodriguez C, Ciobanu C and Saint–Pierre G 2012 FE analysis applied for validation of a biostable aortic valve replacement device: stent and leaflet material selection Int. J. of Biomedical Engineering and Technology 9(4) 378eng
dcterms.referencesChen S, Kohlberger T and Kirchberg K 2011 Advanced level set segmentation of the right atrium in MR Proc. SPIE 7964 31eng
dcterms.referencesFuchs A, Kühl J, Lnborg J, Engstrøm T, Vejlstrup N, Køber L and Kofoed K 2012 Automated assessment of heart chamber volumes and function in patients with previous myocardial infarction using multidetector computed tomography Journal of Cardiovascular Computed Tomography 6(5) 325eng
dcterms.referencesBankman I 2000 Handbook of medical imaging: Processing and analysis (San Diego: Academic Press)eng
dcterms.referencesSuykens J, Gestel T and Brabanter JD 2002 Least squares support vector machines (UK: World Scientific Publishing Co.)eng
dcterms.referencesScholkopf B and Smola A 2002 Learning with kernels. Support vector machines, regularization, optimization, and beyond (Massachusetts: The MIT Press)eng
dcterms.referencesVera M et al. 2018 Automatic segmentation of subdural hematomas using a computational technique based on smart operators Global Medical Engineering Physics Exchanges/Pan American Health Care Exchanges (GMEPE/PAHCE) (Porto: IEEE)eng
dcterms.referencesDice L 1945 Measures of the amount of ecologic association between species Ecology 26(3) 297eng


Bloque original
Mostrando 1 - 1 de 1
Integrating a gradient–based difference operator with machine learning.pdf
822.97 KB
Adobe Portable Document Format
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
368 B
Item-specific license agreed upon to submission