High-precision position estimation in PET using artificial neural networks
Saved in:
| Title: | High-precision position estimation in PET using artificial neural networks |
|---|---|
| Authors: | Mateo, F. fermaji@upvnet.upv.es, Aliaga, R.J.1, Ferrando, N.1, Martínez, J.D.1, Herrero, V.1, Lerche, Ch.W.1, Colom, R.J.1, Monzó, J.M.1, Sebastiá, A.1, Gadea, R.1 |
| Source: | Nuclear Instruments & Methods in Physics Research Section A. Jun2009, Vol. 604 Issue 1/2, p366-369. 4p. |
| Subjects: | Positron emission tomography, Artificial neural networks, Photons, Nonlinear theories, Scintillators, Measurement errors, Estimation theory |
| Abstract: | Abstract: Traditionally, the most popular technique to predict the impact position of gamma photons on a PET detector has been Anger''s logic. However, it introduces nonlinearities that compress the light distribution, reducing the useful field of view and the spatial resolution, especially at the edges of the scintillator crystal. In this work, we make use of neural networks to address a bias-corrected position estimation from real stimulus obtained from a 2D PET system setup. The preprocessing and data acquisition were performed by separate custom boards, especially designed for this application. The results show that neural networks yield a more uniform field of view while improving the systematic error and the spatial resolution. Therefore, they stand as a better performing and readily available alternative to classic positioning methods. [Copyright &y& Elsevier] |
| Copyright of Nuclear Instruments & Methods in Physics Research Section A is the property of Elsevier B.V. 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: 40631823 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: High-precision position estimation in PET using artificial neural networks – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Mateo%2C+F%2E%22">Mateo, F.</searchLink><i> fermaji@upvnet.upv.es</i><br /><searchLink fieldCode="AR" term="%22Aliaga%2C+R%2EJ%2E%22">Aliaga, R.J.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Ferrando%2C+N%2E%22">Ferrando, N.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Martínez%2C+J%2ED%2E%22">Martínez, J.D.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Herrero%2C+V%2E%22">Herrero, V.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Lerche%2C+Ch%2EW%2E%22">Lerche, Ch.W.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Colom%2C+R%2EJ%2E%22">Colom, R.J.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Monzó%2C+J%2EM%2E%22">Monzó, J.M.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Sebastiá%2C+A%2E%22">Sebastiá, A.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Gadea%2C+R%2E%22">Gadea, R.</searchLink><relatesTo>1</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Nuclear+Instruments+%26+Methods+in+Physics+Research+Section+A%22">Nuclear Instruments & Methods in Physics Research Section A</searchLink>. Jun2009, Vol. 604 Issue 1/2, p366-369. 4p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Positron+emission+tomography%22">Positron emission tomography</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Photons%22">Photons</searchLink><br /><searchLink fieldCode="DE" term="%22Nonlinear+theories%22">Nonlinear theories</searchLink><br /><searchLink fieldCode="DE" term="%22Scintillators%22">Scintillators</searchLink><br /><searchLink fieldCode="DE" term="%22Measurement+errors%22">Measurement errors</searchLink><br /><searchLink fieldCode="DE" term="%22Estimation+theory%22">Estimation theory</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Abstract: Traditionally, the most popular technique to predict the impact position of gamma photons on a PET detector has been Anger''s logic. However, it introduces nonlinearities that compress the light distribution, reducing the useful field of view and the spatial resolution, especially at the edges of the scintillator crystal. In this work, we make use of neural networks to address a bias-corrected position estimation from real stimulus obtained from a 2D PET system setup. The preprocessing and data acquisition were performed by separate custom boards, especially designed for this application. The results show that neural networks yield a more uniform field of view while improving the systematic error and the spatial resolution. Therefore, they stand as a better performing and readily available alternative to classic positioning methods. [Copyright &y& Elsevier] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Nuclear Instruments & Methods in Physics Research Section A is the property of Elsevier B.V. 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=40631823 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.nima.2009.01.058 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 4 StartPage: 366 Subjects: – SubjectFull: Positron emission tomography Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: Photons Type: general – SubjectFull: Nonlinear theories Type: general – SubjectFull: Scintillators Type: general – SubjectFull: Measurement errors Type: general – SubjectFull: Estimation theory Type: general Titles: – TitleFull: High-precision position estimation in PET using artificial neural networks Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Mateo, F. – PersonEntity: Name: NameFull: Aliaga, R.J. – PersonEntity: Name: NameFull: Ferrando, N. – PersonEntity: Name: NameFull: Martínez, J.D. – PersonEntity: Name: NameFull: Herrero, V. – PersonEntity: Name: NameFull: Lerche, Ch.W. – PersonEntity: Name: NameFull: Colom, R.J. – PersonEntity: Name: NameFull: Monzó, J.M. – PersonEntity: Name: NameFull: Sebastiá, A. – PersonEntity: Name: NameFull: Gadea, R. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2009 Type: published Y: 2009 Identifiers: – Type: issn-print Value: 01689002 Numbering: – Type: volume Value: 604 – Type: issue Value: 1/2 Titles: – TitleFull: Nuclear Instruments & Methods in Physics Research Section A Type: main |
| ResultId | 1 |
