Bootstrap-Optimised Regularised Image Reconstruction for Emission Tomography.
Saved in:
| Title: | Bootstrap-Optimised Regularised Image Reconstruction for Emission Tomography. |
|---|---|
| Authors: | Reader, Andrew J.1 (AUTHOR) andrew.reader@kcl.ac.uk, Ellis, Sam1 (AUTHOR) |
| Source: | IEEE Transactions on Medical Imaging. Jun2020, Vol. 39 Issue 6, p2163-2175. 13p. |
| Subjects: | Positron emission tomography, Image reconstruction |
| Abstract: | In emission tomography, iterative image reconstruction from noisy measured data usually results in noisy images, and so regularisation is often used to compensate for noise. However, in practice, an appropriate, automatic and precise specification of the strength of regularisation for image reconstruction from a given noisy measured dataset remains unresolved. Existing approaches are either empirical approximations with no guarantee of generalisation, or else are computationally intensive cross-validation methods requiring full reconstructions for a limited set of preselected regularisation strengths. In contrast, we propose a novel methodology embedded within iterative image reconstruction, using one or more bootstrapped replicates of the measured data for precise optimisation of the regularisation. The approach uses a conventional unregularised iterative update of a current image estimate from the noisy measured data, and then also uses the bootstrap replicate to obtain a bootstrap update of the current image estimate. The method then seeks the regularisation hyperparameters which, when applied to the bootstrap update of the image, lead to a best fit of the regularised bootstrap update to the conventional measured data update. This corresponds to estimating the degree of regularisation needed in order to map the noisy update to a model of the mean of an ensemble of noisy updates. For a given regularised objective function (e.g. penalised likelihood), no hyperparameter selection or tuning is required. The method is demonstrated for positron emission tomography (PET) data at different noise levels, and delivers near-optimal reconstructions (in terms of reconstruction error) without any knowledge of the ground truth, nor any form of training data. [ABSTRACT FROM AUTHOR] |
| Copyright of IEEE Transactions on Medical Imaging is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 143613738 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Bootstrap-Optimised Regularised Image Reconstruction for Emission Tomography. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Reader%2C+Andrew+J%2E%22">Reader, Andrew J.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> andrew.reader@kcl.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Ellis%2C+Sam%22">Ellis, Sam</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Medical+Imaging%22">IEEE Transactions on Medical Imaging</searchLink>. Jun2020, Vol. 39 Issue 6, p2163-2175. 13p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Positron+emission+tomography%22">Positron emission tomography</searchLink><br /><searchLink fieldCode="DE" term="%22Image+reconstruction%22">Image reconstruction</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: In emission tomography, iterative image reconstruction from noisy measured data usually results in noisy images, and so regularisation is often used to compensate for noise. However, in practice, an appropriate, automatic and precise specification of the strength of regularisation for image reconstruction from a given noisy measured dataset remains unresolved. Existing approaches are either empirical approximations with no guarantee of generalisation, or else are computationally intensive cross-validation methods requiring full reconstructions for a limited set of preselected regularisation strengths. In contrast, we propose a novel methodology embedded within iterative image reconstruction, using one or more bootstrapped replicates of the measured data for precise optimisation of the regularisation. The approach uses a conventional unregularised iterative update of a current image estimate from the noisy measured data, and then also uses the bootstrap replicate to obtain a bootstrap update of the current image estimate. The method then seeks the regularisation hyperparameters which, when applied to the bootstrap update of the image, lead to a best fit of the regularised bootstrap update to the conventional measured data update. This corresponds to estimating the degree of regularisation needed in order to map the noisy update to a model of the mean of an ensemble of noisy updates. For a given regularised objective function (e.g. penalised likelihood), no hyperparameter selection or tuning is required. The method is demonstrated for positron emission tomography (PET) data at different noise levels, and delivers near-optimal reconstructions (in terms of reconstruction error) without any knowledge of the ground truth, nor any form of training data. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IEEE Transactions on Medical Imaging is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=143613738 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/TMI.2019.2956878 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 13 StartPage: 2163 Subjects: – SubjectFull: Positron emission tomography Type: general – SubjectFull: Image reconstruction Type: general Titles: – TitleFull: Bootstrap-Optimised Regularised Image Reconstruction for Emission Tomography. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Reader, Andrew J. – PersonEntity: Name: NameFull: Ellis, Sam IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2020 Type: published Y: 2020 Identifiers: – Type: issn-print Value: 02780062 Numbering: – Type: volume Value: 39 – Type: issue Value: 6 Titles: – TitleFull: IEEE Transactions on Medical Imaging Type: main |
| ResultId | 1 |
