Automated Segmentation of the Left Atrium from 3D Late Gadolinium Enhancement Imaging using Deep Learning. Gunasekaran, S., Hwang, J., Shen, D., Katsaggelos, A., Elbaz, M. S M, Passman, R., & Kim, D. In 2021 ISMRM & SMRT, 2021. ![Automated Segmentation of the Left Atrium from 3D Late Gadolinium Enhancement Imaging using Deep Learning [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Left atrial (LA) late gadolinium enhancement (LGE) imaging is essential for detecting fibrosis in patients with atrial fibrillation. Unfortunately, slow manual segmentation of LA LGE limits its use in the clinic. The purpose of this study was to develop a fully automated segmentation method for LA LGE images with deep learning. We tested two different U-net architectures that used either 2D or 3D image inputs for training. Our results demonstrate that 3D inputs are superior to 2D, and the 3D U-Net is a promising method to explore further for clinical translation of LA LGE fibrosis quantification.
@inproceedings{Suvai,
abstract = {Left atrial (LA) late gadolinium enhancement (LGE) imaging is essential for detecting fibrosis in patients with atrial fibrillation. Unfortunately, slow manual segmentation of LA LGE limits its use in the clinic. The purpose of this study was to develop a fully automated segmentation method for LA LGE images with deep learning. We tested two different U-net architectures that used either 2D or 3D image inputs for training. Our results demonstrate that 3D inputs are superior to 2D, and the 3D U-Net is a promising method to explore further for clinical translation of LA LGE fibrosis quantification.},
author = {Gunasekaran, Suvai and Hwang, Julia and Shen, Daming and Katsaggelos, Aggelos and Elbaz, Mohammed S M and Passman, Rod and Kim, Daniel},
booktitle = {2021 ISMRM & SMRT},
title = {{Automated Segmentation of the Left Atrium from 3D Late Gadolinium Enhancement Imaging using Deep Learning}},
url = {https://archive.ismrm.org/2021/2669.html},
year = {2021}
}
Downloads: 0
{"_id":"szAyNfZrWDRAr2wfi","bibbaseid":"gunasekaran-hwang-shen-katsaggelos-elbaz-passman-kim-automatedsegmentationoftheleftatriumfrom3dlategadoliniumenhancementimagingusingdeeplearning-2021","author_short":["Gunasekaran, S.","Hwang, J.","Shen, D.","Katsaggelos, A.","Elbaz, M. S M","Passman, R.","Kim, D."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"Left atrial (LA) late gadolinium enhancement (LGE) imaging is essential for detecting fibrosis in patients with atrial fibrillation. Unfortunately, slow manual segmentation of LA LGE limits its use in the clinic. The purpose of this study was to develop a fully automated segmentation method for LA LGE images with deep learning. We tested two different U-net architectures that used either 2D or 3D image inputs for training. Our results demonstrate that 3D inputs are superior to 2D, and the 3D U-Net is a promising method to explore further for clinical translation of LA LGE fibrosis quantification.","author":[{"propositions":[],"lastnames":["Gunasekaran"],"firstnames":["Suvai"],"suffixes":[]},{"propositions":[],"lastnames":["Hwang"],"firstnames":["Julia"],"suffixes":[]},{"propositions":[],"lastnames":["Shen"],"firstnames":["Daming"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos"],"suffixes":[]},{"propositions":[],"lastnames":["Elbaz"],"firstnames":["Mohammed","S","M"],"suffixes":[]},{"propositions":[],"lastnames":["Passman"],"firstnames":["Rod"],"suffixes":[]},{"propositions":[],"lastnames":["Kim"],"firstnames":["Daniel"],"suffixes":[]}],"booktitle":"2021 ISMRM & SMRT","title":"Automated Segmentation of the Left Atrium from 3D Late Gadolinium Enhancement Imaging using Deep Learning","url":"https://archive.ismrm.org/2021/2669.html","year":"2021","bibtex":"@inproceedings{Suvai,\nabstract = {Left atrial (LA) late gadolinium enhancement (LGE) imaging is essential for detecting fibrosis in patients with atrial fibrillation. Unfortunately, slow manual segmentation of LA LGE limits its use in the clinic. The purpose of this study was to develop a fully automated segmentation method for LA LGE images with deep learning. We tested two different U-net architectures that used either 2D or 3D image inputs for training. Our results demonstrate that 3D inputs are superior to 2D, and the 3D U-Net is a promising method to explore further for clinical translation of LA LGE fibrosis quantification.},\nauthor = {Gunasekaran, Suvai and Hwang, Julia and Shen, Daming and Katsaggelos, Aggelos and Elbaz, Mohammed S M and Passman, Rod and Kim, Daniel},\nbooktitle = {2021 ISMRM & SMRT},\ntitle = {{Automated Segmentation of the Left Atrium from 3D Late Gadolinium Enhancement Imaging using Deep Learning}},\nurl = {https://archive.ismrm.org/2021/2669.html},\nyear = {2021}\n}\n","author_short":["Gunasekaran, S.","Hwang, J.","Shen, D.","Katsaggelos, A.","Elbaz, M. S M","Passman, R.","Kim, D."],"key":"Suvai","id":"Suvai","bibbaseid":"gunasekaran-hwang-shen-katsaggelos-elbaz-passman-kim-automatedsegmentationoftheleftatriumfrom3dlategadoliniumenhancementimagingusingdeeplearning-2021","role":"author","urls":{"Paper":"https://archive.ismrm.org/2021/2669.html"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":[],"search_terms":["automated","segmentation","left","atrium","late","gadolinium","enhancement","imaging","using","deep","learning","gunasekaran","hwang","shen","katsaggelos","elbaz","passman","kim"],"title":"Automated Segmentation of the Left Atrium from 3D Late Gadolinium Enhancement Imaging using Deep Learning","year":2021}