Atrial Fibrosis Quantiﬁcation Based on Maximum Likelihood Estimator of Multivariate Images

Atrial Fibrosis Quantiﬁcation Based on Maximum Likelihood Estimator of Multivariate Images. Wu, F., Yang, G., Li, L., Xu, L., Wong, T., Mohiaddin, R., Firmin, D., Keegan, J., Zhuang, X., Yang, G., Wong, T., Mohiaddin, R., Firmin, D., Keegan, J., Xu, L., & Zhuang, X. In Medical Image Computing and Computer Assisted Intervention (MICCAI 2018), volume 11073 LNCS, pages 604-612, 2018. Springer International Publishing.

Paper

Atrial Fibrosis Quantiﬁcation Based on Maximum Likelihood Estimator of Multivariate Images [link]

Website doi abstract bibtex

We present a fully-automated segmentation and quantification of the left atrial (LA) fibrosis and scars combining two cardiac MRIs, one is the target late gadolinium-enhanced (LGE) image, and the other is an anatomical MRI from the same acquisition session. We formulate the joint distribution of images using a multivariate mixture model (MvMM), and employ the maximum likelihood estimator (MLE) for texture classification of the images simultaneously. The MvMM can also embed transformations assigned to the images to correct the misregistration. The iterated conditional mode algorithm is adopted for optimization. This method first extracts the anatomical shape of the LA, and then estimates a prior probability map. It projects the resulting segmentation onto the LA surface, for quantification and analysis of scarring. We applied the proposed method to 36 clinical data sets and obtained promising results (Accuracy: 0.809±150, Dice: 0.556±187). We compared the method with the conventional algorithms and showed an evidently and statistically better performance (p < 0.03).

@inproceedings{
 title = {Atrial Fibrosis Quantiﬁcation Based on Maximum Likelihood Estimator of Multivariate Images},
 type = {inproceedings},
 year = {2018},
 pages = {604-612},
 volume = {11073 LNCS},
 websites = {http://dx.doi.org/10.1007/978-3-030-00937-3_69},
 publisher = {Springer International Publishing},
 id = {047bb17f-bf09-38c3-be4f-702aaff8adfa},
 created = {2024-01-13T08:14:14.165Z},
 file_attached = {true},
 profile_id = {d5b9f595-4104-33d2-b640-e84dee1b7ded},
 last_modified = {2024-01-13T08:18:35.734Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 source_type = {CONF},
 private_publication = {false},
 abstract = {We present a fully-automated segmentation and quantification of the left atrial (LA) fibrosis and scars combining two cardiac MRIs, one is the target late gadolinium-enhanced (LGE) image, and the other is an anatomical MRI from the same acquisition session. We formulate the joint distribution of images using a multivariate mixture model (MvMM), and employ the maximum likelihood estimator (MLE) for texture classification of the images simultaneously. The MvMM can also embed transformations assigned to the images to correct the misregistration. The iterated conditional mode algorithm is adopted for optimization. This method first extracts the anatomical shape of the LA, and then estimates a prior probability map. It projects the resulting segmentation onto the LA surface, for quantification and analysis of scarring. We applied the proposed method to 36 clinical data sets and obtained promising results (Accuracy: 0.809±150, Dice: 0.556±187). We compared the method with the conventional algorithms and showed an evidently and statistically better performance (p < 0.03).},
 bibtype = {inproceedings},
 author = {Wu, Fuping and Yang, Guang and Li, Lei and Xu, Lingchao and Wong, Tom and Mohiaddin, Raad and Firmin, David and Keegan, Jennifer and Zhuang, Xiahai and Yang, Guang and Wong, Tom and Mohiaddin, Raad and Firmin, David and Keegan, Jennifer and Xu, Lingchao and Zhuang, Xiahai},
 doi = {10.1007/978-3-030-00937-3_69},
 booktitle = {Medical Image Computing and Computer Assisted Intervention (MICCAI 2018)}
}

Downloads: 0

{"_id":"6Drppc6JxwmjjJtCx","bibbaseid":"wu-yang-li-xu-wong-mohiaddin-firmin-keegan-etal-atrialfibrosisquanticationbasedonmaximumlikelihoodestimatorofmultivariateimages-2018","author_short":["Wu, F.","Yang, G.","Li, L.","Xu, L.","Wong, T.","Mohiaddin, R.","Firmin, D.","Keegan, J.","Zhuang, X.","Yang, G.","Wong, T.","Mohiaddin, R.","Firmin, D.","Keegan, J.","Xu, L.","Zhuang, X."],"bibdata":{"title":"Atrial Fibrosis Quantiﬁcation Based on Maximum Likelihood Estimator of Multivariate Images","type":"inproceedings","year":"2018","pages":"604-612","volume":"11073 LNCS","websites":"http://dx.doi.org/10.1007/978-3-030-00937-3_69","publisher":"Springer International Publishing","id":"047bb17f-bf09-38c3-be4f-702aaff8adfa","created":"2024-01-13T08:14:14.165Z","file_attached":"true","profile_id":"d5b9f595-4104-33d2-b640-e84dee1b7ded","last_modified":"2024-01-13T08:18:35.734Z","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"source_type":"CONF","private_publication":false,"abstract":"We present a fully-automated segmentation and quantification of the left atrial (LA) fibrosis and scars combining two cardiac MRIs, one is the target late gadolinium-enhanced (LGE) image, and the other is an anatomical MRI from the same acquisition session. We formulate the joint distribution of images using a multivariate mixture model (MvMM), and employ the maximum likelihood estimator (MLE) for texture classification of the images simultaneously. The MvMM can also embed transformations assigned to the images to correct the misregistration. The iterated conditional mode algorithm is adopted for optimization. This method first extracts the anatomical shape of the LA, and then estimates a prior probability map. It projects the resulting segmentation onto the LA surface, for quantification and analysis of scarring. We applied the proposed method to 36 clinical data sets and obtained promising results (Accuracy: 0.809±150, Dice: 0.556±187). We compared the method with the conventional algorithms and showed an evidently and statistically better performance (p < 0.03).","bibtype":"inproceedings","author":"Wu, Fuping and Yang, Guang and Li, Lei and Xu, Lingchao and Wong, Tom and Mohiaddin, Raad and Firmin, David and Keegan, Jennifer and Zhuang, Xiahai and Yang, Guang and Wong, Tom and Mohiaddin, Raad and Firmin, David and Keegan, Jennifer and Xu, Lingchao and Zhuang, Xiahai","doi":"10.1007/978-3-030-00937-3_69","booktitle":"Medical Image Computing and Computer Assisted Intervention (MICCAI 2018)","bibtex":"@inproceedings{\n title = {Atrial Fibrosis Quantiﬁcation Based on Maximum Likelihood Estimator of Multivariate Images},\n type = {inproceedings},\n year = {2018},\n pages = {604-612},\n volume = {11073 LNCS},\n websites = {http://dx.doi.org/10.1007/978-3-030-00937-3_69},\n publisher = {Springer International Publishing},\n id = {047bb17f-bf09-38c3-be4f-702aaff8adfa},\n created = {2024-01-13T08:14:14.165Z},\n file_attached = {true},\n profile_id = {d5b9f595-4104-33d2-b640-e84dee1b7ded},\n last_modified = {2024-01-13T08:18:35.734Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n source_type = {CONF},\n private_publication = {false},\n abstract = {We present a fully-automated segmentation and quantification of the left atrial (LA) fibrosis and scars combining two cardiac MRIs, one is the target late gadolinium-enhanced (LGE) image, and the other is an anatomical MRI from the same acquisition session. We formulate the joint distribution of images using a multivariate mixture model (MvMM), and employ the maximum likelihood estimator (MLE) for texture classification of the images simultaneously. The MvMM can also embed transformations assigned to the images to correct the misregistration. The iterated conditional mode algorithm is adopted for optimization. This method first extracts the anatomical shape of the LA, and then estimates a prior probability map. It projects the resulting segmentation onto the LA surface, for quantification and analysis of scarring. We applied the proposed method to 36 clinical data sets and obtained promising results (Accuracy: 0.809±150, Dice: 0.556±187). We compared the method with the conventional algorithms and showed an evidently and statistically better performance (p < 0.03).},\n bibtype = {inproceedings},\n author = {Wu, Fuping and Yang, Guang and Li, Lei and Xu, Lingchao and Wong, Tom and Mohiaddin, Raad and Firmin, David and Keegan, Jennifer and Zhuang, Xiahai and Yang, Guang and Wong, Tom and Mohiaddin, Raad and Firmin, David and Keegan, Jennifer and Xu, Lingchao and Zhuang, Xiahai},\n doi = {10.1007/978-3-030-00937-3_69},\n booktitle = {Medical Image Computing and Computer Assisted Intervention (MICCAI 2018)}\n}","author_short":["Wu, F.","Yang, G.","Li, L.","Xu, L.","Wong, T.","Mohiaddin, R.","Firmin, D.","Keegan, J.","Zhuang, X.","Yang, G.","Wong, T.","Mohiaddin, R.","Firmin, D.","Keegan, J.","Xu, L.","Zhuang, X."],"urls":{"Paper":"https://bibbase.org/service/mendeley/d5b9f595-4104-33d2-b640-e84dee1b7ded/file/539f80f3-caf6-4197-4c9d-3ecfc332d6fb/Wu2018_Chapter_AtrialFibrosisQuantificationBa.pdf.pdf","Website":"http://dx.doi.org/10.1007/978-3-030-00937-3_69"},"biburl":"https://bibbase.org/service/mendeley/d5b9f595-4104-33d2-b640-e84dee1b7ded","bibbaseid":"wu-yang-li-xu-wong-mohiaddin-firmin-keegan-etal-atrialfibrosisquanticationbasedonmaximumlikelihoodestimatorofmultivariateimages-2018","role":"author","metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/d5b9f595-4104-33d2-b640-e84dee1b7ded","dataSources":["ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["atrial","fibrosis","quanti","cation","based","maximum","likelihood","estimator","multivariate","images","wu","yang","li","xu","wong","mohiaddin","firmin","keegan","zhuang","yang","wong","mohiaddin","firmin","keegan","xu","zhuang"],"title":"Atrial Fibrosis Quantiﬁcation Based on Maximum Likelihood Estimator of Multivariate Images","year":2018}