File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Modularized data-driven reconstruction framework for nonideal focal spot effect elimination in computed tomography

TitleModularized data-driven reconstruction framework for nonideal focal spot effect elimination in computed tomography
Authors
Keywordsfocal spot
computed tomography
deep learning
image reconstruction
x-ray
Issue Date2021
Citation
Medical Physics, 2021, v. 48 n. 5, p. 2245-2257 How to Cite?
AbstractPurpose: High-performance computed tomography (CT) plays a vital role in clinical decision-making. However, the performance of CT imaging is adversely affected by the nonideal focal spot size of the x-ray source or degraded by an enlarged focal spot size due to aging. In this work, we aim to develop a deep learning-based strategy to mitigate the problem so that high spatial resolution CT images can be obtained even in the case of a nonideal x-ray source. Methods: To reconstruct high-quality CT images from blurred sinograms via joint image and sinogram learning, a cross-domain hybrid model is formulated via deep learning into a modularized data-driven reconstruction (MDR) framework. The proposed MDR framework comprises several blocks, and all the blocks share the same network architecture and network parameters. In essence, each block utilizes two sub-models to generate an estimated blur kernel and a high-quality CT image simultaneously. In this way, our framework generates not only a final high-quality CT image but also a series of intermediate images with gradually improved anatomical details, enhancing the visual perception for clinicians through the dynamic process. We used simulated training datasets to train our model in an end-to-end manner and tested our model on both simulated and realistic experimental datasets. Results: On the simulated testing datasets, our approach increases the information fidelity criterion (IFC) by up to 34.2%, the universal quality index (UQI) by up to 20.3%, the signal-to-noise (SNR) by up to 6.7%, and reduces the root mean square error (RMSE) by up to 10.5% as compared with FBP. Compared with the iterative deconvolution method (NSM), MDR increases IFC by up to 24.7%, UQI by up to 16.7%, SNR by up to 6.0%, and reduces RMSE by up to 9.4%. In the modulation transfer function (MTF) experiment, our method improves the MTF by 34.5% and MTF by 18.7% as compared with FBP, Similarly remarkably, our method improves MTF by 14.3% and MTF by 0.9% as compared with NSM. Also, our method shows better imaging results in the edge of bony structures and other tiny structures in the experiments using phantom consisting of ham and a bottle of peanuts. Conclusions: A modularized data-driven CT reconstruction framework is established to mitigate the blurring effect caused by a nonideal x-ray source with relatively large focal spot. The proposed method enables us to obtain high-resolution images with less ideal x-ray source. 50% 10% 50% 10%
Persistent Identifierhttp://hdl.handle.net/10722/299628
ISSN
2020 Impact Factor: 4.071
2020 SCImago Journal Rankings: 1.473
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhang, Zhicheng-
dc.contributor.authorYu, Lequan-
dc.contributor.authorZhao, Wei-
dc.contributor.authorXing, Lei-
dc.date.accessioned2021-05-21T03:34:49Z-
dc.date.available2021-05-21T03:34:49Z-
dc.date.issued2021-
dc.identifier.citationMedical Physics, 2021, v. 48 n. 5, p. 2245-2257-
dc.identifier.issn0094-2405-
dc.identifier.urihttp://hdl.handle.net/10722/299628-
dc.description.abstractPurpose: High-performance computed tomography (CT) plays a vital role in clinical decision-making. However, the performance of CT imaging is adversely affected by the nonideal focal spot size of the x-ray source or degraded by an enlarged focal spot size due to aging. In this work, we aim to develop a deep learning-based strategy to mitigate the problem so that high spatial resolution CT images can be obtained even in the case of a nonideal x-ray source. Methods: To reconstruct high-quality CT images from blurred sinograms via joint image and sinogram learning, a cross-domain hybrid model is formulated via deep learning into a modularized data-driven reconstruction (MDR) framework. The proposed MDR framework comprises several blocks, and all the blocks share the same network architecture and network parameters. In essence, each block utilizes two sub-models to generate an estimated blur kernel and a high-quality CT image simultaneously. In this way, our framework generates not only a final high-quality CT image but also a series of intermediate images with gradually improved anatomical details, enhancing the visual perception for clinicians through the dynamic process. We used simulated training datasets to train our model in an end-to-end manner and tested our model on both simulated and realistic experimental datasets. Results: On the simulated testing datasets, our approach increases the information fidelity criterion (IFC) by up to 34.2%, the universal quality index (UQI) by up to 20.3%, the signal-to-noise (SNR) by up to 6.7%, and reduces the root mean square error (RMSE) by up to 10.5% as compared with FBP. Compared with the iterative deconvolution method (NSM), MDR increases IFC by up to 24.7%, UQI by up to 16.7%, SNR by up to 6.0%, and reduces RMSE by up to 9.4%. In the modulation transfer function (MTF) experiment, our method improves the MTF by 34.5% and MTF by 18.7% as compared with FBP, Similarly remarkably, our method improves MTF by 14.3% and MTF by 0.9% as compared with NSM. Also, our method shows better imaging results in the edge of bony structures and other tiny structures in the experiments using phantom consisting of ham and a bottle of peanuts. Conclusions: A modularized data-driven CT reconstruction framework is established to mitigate the blurring effect caused by a nonideal x-ray source with relatively large focal spot. The proposed method enables us to obtain high-resolution images with less ideal x-ray source. 50% 10% 50% 10%-
dc.languageeng-
dc.relation.ispartofMedical Physics-
dc.subjectfocal spot-
dc.subjectcomputed tomography-
dc.subjectdeep learning-
dc.subjectimage reconstruction-
dc.subjectx-ray-
dc.titleModularized data-driven reconstruction framework for nonideal focal spot effect elimination in computed tomography-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1002/mp.14785-
dc.identifier.pmid33595900-
dc.identifier.scopuseid_2-s2.0-85102815065-
dc.identifier.volume48-
dc.identifier.issue5-
dc.identifier.spage2245-
dc.identifier.epage2257-
dc.identifier.isiWOS:000631484300001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats