Limited-angle computed tomography with deep image and physics priors. Barutcu, S., Aslan, S., Katsaggelos, A. K., & Gürsoy, D. Scientific Reports, 11(1):17740, Nature Publishing Group UK London, sep, 2021. ![Limited-angle computed tomography with deep image and physics priors [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Computed tomography is a well-established x-ray imaging technique to reconstruct the three-dimensional structure of objects. It has been used extensively in a variety of fields, from diagnostic imaging to materials and biological sciences. One major challenge in some applications, such as in electron or x-ray tomography systems, is that the projections cannot be gathered over all the angles due to the sample holder setup or shape of the sample. This results in an ill-posed problem called the limited angle reconstruction problem. Typical image reconstruction in this setup leads to distortion and artifacts, thereby hindering a quantitative evaluation of the results. To address this challenge, we use a generative model to effectively constrain the solution of a physics-based approach. Our approach is self-training that can iteratively learn the nonlinear mapping from partial projections to the scanned object. Because our approach combines the data likelihood and image prior terms into a single deep network, it is computationally tractable and improves performance through an end-to-end training. We also complement our approach with total-variation regularization to handle high-frequency noise in reconstructions and implement a solver based on alternating direction method of multipliers. We present numerical results for various degrees of missing angle range and noise levels, which demonstrate the effectiveness of the proposed approach.
@article{barutcu2021limited,
abstract = {Computed tomography is a well-established x-ray imaging technique to reconstruct the three-dimensional structure of objects. It has been used extensively in a variety of fields, from diagnostic imaging to materials and biological sciences. One major challenge in some applications, such as in electron or x-ray tomography systems, is that the projections cannot be gathered over all the angles due to the sample holder setup or shape of the sample. This results in an ill-posed problem called the limited angle reconstruction problem. Typical image reconstruction in this setup leads to distortion and artifacts, thereby hindering a quantitative evaluation of the results. To address this challenge, we use a generative model to effectively constrain the solution of a physics-based approach. Our approach is self-training that can iteratively learn the nonlinear mapping from partial projections to the scanned object. Because our approach combines the data likelihood and image prior terms into a single deep network, it is computationally tractable and improves performance through an end-to-end training. We also complement our approach with total-variation regularization to handle high-frequency noise in reconstructions and implement a solver based on alternating direction method of multipliers. We present numerical results for various degrees of missing angle range and noise levels, which demonstrate the effectiveness of the proposed approach.},
author = {Barutcu, Semih and Aslan, Selin and Katsaggelos, Aggelos K. and G{\"{u}}rsoy, Doğa},
doi = {10.1038/s41598-021-97226-2},
issn = {2045-2322},
journal = {Scientific Reports},
month = {sep},
number = {1},
pages = {17740},
pmid = {34489500},
publisher = {Nature Publishing Group UK London},
title = {{Limited-angle computed tomography with deep image and physics priors}},
url = {https://www.nature.com/articles/s41598-021-97226-2},
volume = {11},
year = {2021}
}
Downloads: 0
{"_id":"Kbfu9wn5r2gjCqf7e","bibbaseid":"barutcu-aslan-katsaggelos-grsoy-limitedanglecomputedtomographywithdeepimageandphysicspriors-2021","author_short":["Barutcu, S.","Aslan, S.","Katsaggelos, A. K.","Gürsoy, D."],"bibdata":{"bibtype":"article","type":"article","abstract":"Computed tomography is a well-established x-ray imaging technique to reconstruct the three-dimensional structure of objects. It has been used extensively in a variety of fields, from diagnostic imaging to materials and biological sciences. One major challenge in some applications, such as in electron or x-ray tomography systems, is that the projections cannot be gathered over all the angles due to the sample holder setup or shape of the sample. This results in an ill-posed problem called the limited angle reconstruction problem. Typical image reconstruction in this setup leads to distortion and artifacts, thereby hindering a quantitative evaluation of the results. To address this challenge, we use a generative model to effectively constrain the solution of a physics-based approach. Our approach is self-training that can iteratively learn the nonlinear mapping from partial projections to the scanned object. Because our approach combines the data likelihood and image prior terms into a single deep network, it is computationally tractable and improves performance through an end-to-end training. We also complement our approach with total-variation regularization to handle high-frequency noise in reconstructions and implement a solver based on alternating direction method of multipliers. We present numerical results for various degrees of missing angle range and noise levels, which demonstrate the effectiveness of the proposed approach.","author":[{"propositions":[],"lastnames":["Barutcu"],"firstnames":["Semih"],"suffixes":[]},{"propositions":[],"lastnames":["Aslan"],"firstnames":["Selin"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]},{"propositions":[],"lastnames":["Gürsoy"],"firstnames":["Doğa"],"suffixes":[]}],"doi":"10.1038/s41598-021-97226-2","issn":"2045-2322","journal":"Scientific Reports","month":"sep","number":"1","pages":"17740","pmid":"34489500","publisher":"Nature Publishing Group UK London","title":"Limited-angle computed tomography with deep image and physics priors","url":"https://www.nature.com/articles/s41598-021-97226-2","volume":"11","year":"2021","bibtex":"@article{barutcu2021limited,\nabstract = {Computed tomography is a well-established x-ray imaging technique to reconstruct the three-dimensional structure of objects. It has been used extensively in a variety of fields, from diagnostic imaging to materials and biological sciences. One major challenge in some applications, such as in electron or x-ray tomography systems, is that the projections cannot be gathered over all the angles due to the sample holder setup or shape of the sample. This results in an ill-posed problem called the limited angle reconstruction problem. Typical image reconstruction in this setup leads to distortion and artifacts, thereby hindering a quantitative evaluation of the results. To address this challenge, we use a generative model to effectively constrain the solution of a physics-based approach. Our approach is self-training that can iteratively learn the nonlinear mapping from partial projections to the scanned object. Because our approach combines the data likelihood and image prior terms into a single deep network, it is computationally tractable and improves performance through an end-to-end training. We also complement our approach with total-variation regularization to handle high-frequency noise in reconstructions and implement a solver based on alternating direction method of multipliers. We present numerical results for various degrees of missing angle range and noise levels, which demonstrate the effectiveness of the proposed approach.},\nauthor = {Barutcu, Semih and Aslan, Selin and Katsaggelos, Aggelos K. and G{\\\"{u}}rsoy, Doğa},\ndoi = {10.1038/s41598-021-97226-2},\nissn = {2045-2322},\njournal = {Scientific Reports},\nmonth = {sep},\nnumber = {1},\npages = {17740},\npmid = {34489500},\npublisher = {Nature Publishing Group UK London},\ntitle = {{Limited-angle computed tomography with deep image and physics priors}},\nurl = {https://www.nature.com/articles/s41598-021-97226-2},\nvolume = {11},\nyear = {2021}\n}\n","author_short":["Barutcu, S.","Aslan, S.","Katsaggelos, A. K.","Gürsoy, D."],"key":"barutcu2021limited","id":"barutcu2021limited","bibbaseid":"barutcu-aslan-katsaggelos-grsoy-limitedanglecomputedtomographywithdeepimageandphysicspriors-2021","role":"author","urls":{"Paper":"https://www.nature.com/articles/s41598-021-97226-2"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["ePKPjG8C6yvpk4mEK","37Qfzv6wRptYkoSCL","zFPgsTDAW8aDnb5iN","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":[],"search_terms":["limited","angle","computed","tomography","deep","image","physics","priors","barutcu","aslan","katsaggelos","gürsoy"],"title":"Limited-angle computed tomography with deep image and physics priors","year":2021}