Hybrid Atlas Building with Deep Registration Priors. Wu, N., Wang, J., Zhang, M., Zhang, G., Peng, Y., & Shen, C. In 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), pages 1–5, March, 2022. ISSN: 1945-8452doi abstract bibtex Registration-based atlas building often poses computational challenges in high-dimensional image spaces. In this paper, we introduce a novel hybrid atlas building algorithm that fast estimates atlas from large-scale image datasets with much reduced computational cost. In contrast to previous approaches that iteratively perform registration tasks between an estimated atlas and individual images, we propose to use learned priors of registration from pre-trained neural networks. This newly developed hybrid framework features several advantages of (i) providing an efficient way of atlas building without losing the quality of results, and (ii) offering flexibility in utilizing a wide variety of deep learning based registration methods. We demonstrate the effectiveness of this proposed model on 3D brain magnetic resonance imaging (MRI) scans.
@inproceedings{wu_hybrid_2022,
title = {Hybrid {Atlas} {Building} with {Deep} {Registration} {Priors}},
doi = {10.1109/ISBI52829.2022.9761670},
abstract = {Registration-based atlas building often poses computational challenges in high-dimensional image spaces. In this paper, we introduce a novel hybrid atlas building algorithm that fast estimates atlas from large-scale image datasets with much reduced computational cost. In contrast to previous approaches that iteratively perform registration tasks between an estimated atlas and individual images, we propose to use learned priors of registration from pre-trained neural networks. This newly developed hybrid framework features several advantages of (i) providing an efficient way of atlas building without losing the quality of results, and (ii) offering flexibility in utilizing a wide variety of deep learning based registration methods. We demonstrate the effectiveness of this proposed model on 3D brain magnetic resonance imaging (MRI) scans.},
booktitle = {2022 {IEEE} 19th {International} {Symposium} on {Biomedical} {Imaging} ({ISBI})},
author = {Wu, Nian and Wang, Jian and Zhang, Miaomiao and Zhang, Guixu and Peng, Yaxin and Shen, Chaomin},
month = mar,
year = {2022},
note = {ISSN: 1945-8452},
keywords = {Biological system modeling, Brain modeling, Buildings, Deep learning, Magnetic resonance imaging, Solid modeling, Three-dimensional displays},
pages = {1--5},
file = {已提交版本:C\:\\Users\\Nellie\\Zotero\\storage\\JCX66HPU\\Wu 等 - 2022 - Hybrid Atlas Building with Deep Registration Prior.pdf:application/pdf;IEEE Xplore Abstract Record:C\:\\Users\\Nellie\\Zotero\\storage\\RDLN33P4\\9761670.html:text/html},
}
Downloads: 0
{"_id":"MaK2HNFW3SZJ4yf4q","bibbaseid":"wu-wang-zhang-zhang-peng-shen-hybridatlasbuildingwithdeepregistrationpriors-2022","author_short":["Wu, N.","Wang, J.","Zhang, M.","Zhang, G.","Peng, Y.","Shen, C."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Hybrid Atlas Building with Deep Registration Priors","doi":"10.1109/ISBI52829.2022.9761670","abstract":"Registration-based atlas building often poses computational challenges in high-dimensional image spaces. In this paper, we introduce a novel hybrid atlas building algorithm that fast estimates atlas from large-scale image datasets with much reduced computational cost. In contrast to previous approaches that iteratively perform registration tasks between an estimated atlas and individual images, we propose to use learned priors of registration from pre-trained neural networks. This newly developed hybrid framework features several advantages of (i) providing an efficient way of atlas building without losing the quality of results, and (ii) offering flexibility in utilizing a wide variety of deep learning based registration methods. We demonstrate the effectiveness of this proposed model on 3D brain magnetic resonance imaging (MRI) scans.","booktitle":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","author":[{"propositions":[],"lastnames":["Wu"],"firstnames":["Nian"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Jian"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Miaomiao"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Guixu"],"suffixes":[]},{"propositions":[],"lastnames":["Peng"],"firstnames":["Yaxin"],"suffixes":[]},{"propositions":[],"lastnames":["Shen"],"firstnames":["Chaomin"],"suffixes":[]}],"month":"March","year":"2022","note":"ISSN: 1945-8452","keywords":"Biological system modeling, Brain modeling, Buildings, Deep learning, Magnetic resonance imaging, Solid modeling, Three-dimensional displays","pages":"1–5","file":"已提交版本:C\\:\\\\Users\\\\Nellie\\\\Zotero\\\\storage\\\\JCX66HPU\\\\Wu 等 - 2022 - Hybrid Atlas Building with Deep Registration Prior.pdf:application/pdf;IEEE Xplore Abstract Record:C\\:\\\\Users\\\\Nellie\\\\Zotero\\\\storage\\\\RDLN33P4\\\\9761670.html:text/html","bibtex":"@inproceedings{wu_hybrid_2022,\n\ttitle = {Hybrid {Atlas} {Building} with {Deep} {Registration} {Priors}},\n\tdoi = {10.1109/ISBI52829.2022.9761670},\n\tabstract = {Registration-based atlas building often poses computational challenges in high-dimensional image spaces. In this paper, we introduce a novel hybrid atlas building algorithm that fast estimates atlas from large-scale image datasets with much reduced computational cost. In contrast to previous approaches that iteratively perform registration tasks between an estimated atlas and individual images, we propose to use learned priors of registration from pre-trained neural networks. This newly developed hybrid framework features several advantages of (i) providing an efficient way of atlas building without losing the quality of results, and (ii) offering flexibility in utilizing a wide variety of deep learning based registration methods. We demonstrate the effectiveness of this proposed model on 3D brain magnetic resonance imaging (MRI) scans.},\n\tbooktitle = {2022 {IEEE} 19th {International} {Symposium} on {Biomedical} {Imaging} ({ISBI})},\n\tauthor = {Wu, Nian and Wang, Jian and Zhang, Miaomiao and Zhang, Guixu and Peng, Yaxin and Shen, Chaomin},\n\tmonth = mar,\n\tyear = {2022},\n\tnote = {ISSN: 1945-8452},\n\tkeywords = {Biological system modeling, Brain modeling, Buildings, Deep learning, Magnetic resonance imaging, Solid modeling, Three-dimensional displays},\n\tpages = {1--5},\n\tfile = {已提交版本:C\\:\\\\Users\\\\Nellie\\\\Zotero\\\\storage\\\\JCX66HPU\\\\Wu 等 - 2022 - Hybrid Atlas Building with Deep Registration Prior.pdf:application/pdf;IEEE Xplore Abstract Record:C\\:\\\\Users\\\\Nellie\\\\Zotero\\\\storage\\\\RDLN33P4\\\\9761670.html:text/html},\n}\n","author_short":["Wu, N.","Wang, J.","Zhang, M.","Zhang, G.","Peng, Y.","Shen, C."],"key":"wu_hybrid_2022","id":"wu_hybrid_2022","bibbaseid":"wu-wang-zhang-zhang-peng-shen-hybridatlasbuildingwithdeepregistrationpriors-2022","role":"author","urls":{},"keyword":["Biological system modeling","Brain modeling","Buildings","Deep learning","Magnetic resonance imaging","Solid modeling","Three-dimensional displays"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/on2svFZk8LwancEEZ","dataSources":["6ETR8Q8Mso6FT38Ap","ZWoJukbiBS56zsRXZ","3m3a7a7gLpQAQmzWn","RdCtR4E9cywXyWJzh"],"keywords":["biological system modeling","brain modeling","buildings","deep learning","magnetic resonance imaging","solid modeling","three-dimensional displays"],"search_terms":["hybrid","atlas","building","deep","registration","priors","wu","wang","zhang","zhang","peng","shen"],"title":"Hybrid Atlas Building with Deep Registration Priors","year":2022}