Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections.
Saved in:
| Title: | Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections. |
|---|---|
| Authors: | Iglesias, Juan Eugenio1 e.iglesias@ucl.ac.uk, Modat, Marc1, Peter, Loïc2, Stevens, Allison3, Annunziata, Roberto1, Vercauteren, Tom1,2, Lein, Ed4, Fischl, Bruce3,5, Ourselin, Sebastien1,2 |
| Source: | Medical Image Analysis. Dec2018, Vol. 50, p127-144. 18p. |
| Subjects: | Magnetic resonance imaging, Probabilistic databases, Bayesian analysis, Information theory, Applied mathematics |
| Abstract: | Highlights • A framework to jointly estimate registration and synthesis, without training data Uncertainty of each component considered when estimating the parameters of the other. • Principled framework enables seamless integration of manually placed landmarks. • More accurate and robust than mutual information in histology-MR registration. • Compelling results in synthetic (ADNI, MRI-MRI) and real data (Allen, histology-MRI). Graphical abstract Image, graphical abstract Abstract Nonlinear registration of 2D histological sections with corresponding slices of MRI data is a critical step of 3D histology reconstruction algorithms. This registration is difficult due to the large differences in image contrast and resolution, as well as the complex nonrigid deformations and artefacts produced when sectioning the sample and mounting it on the glass slide. It has been shown in brain MRI registration that better spatial alignment across modalities can be obtained by synthesising one modality from the other and then using intra-modality registration metrics, rather than by using information theory based metrics to solve the problem directly. However, such an approach typically requires a database of aligned images from the two modalities, which is very difficult to obtain for histology and MRI. Here, we overcome this limitation with a probabilistic method that simultaneously solves for deformable registration and synthesis directly on the target images, without requiring any training data. The method is based on a probabilistic model in which the MRI slice is assumed to be a contrast-warped, spatially deformed version of the histological section. We use approximate Bayesian inference to iteratively refine the probabilistic estimate of the synthesis and the registration, while accounting for each other's uncertainty. Moreover, manually placed landmarks can be seamlessly integrated in the framework for increased performance and robustness. Experiments on a synthetic dataset of MRI slices show that, compared with mutual information based registration, the proposed method makes it possible to use a much more flexible deformation model in the registration to improve its accuracy, without compromising robustness. Moreover, our framework also exploits information in manually placed landmarks more efficiently than mutual information: landmarks constrain the deformation field in both methods, but in our algorithm, it also has a positive effect on the synthesis – which further improves the registration. We also show results on two real, publicly available datasets: the Allen and BigBrain atlases. In both of them, the proposed method provides a clear improvement over mutual information based registration, both qualitatively (visual inspection) and quantitatively (registration error measured with pairs of manually annotated landmarks). [ABSTRACT FROM AUTHOR] |
| Copyright of Medical Image Analysis 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: 132606956 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Iglesias%2C+Juan+Eugenio%22">Iglesias, Juan Eugenio</searchLink><relatesTo>1</relatesTo><i> e.iglesias@ucl.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Modat%2C+Marc%22">Modat, Marc</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Peter%2C+Loïc%22">Peter, Loïc</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Stevens%2C+Allison%22">Stevens, Allison</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Annunziata%2C+Roberto%22">Annunziata, Roberto</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Vercauteren%2C+Tom%22">Vercauteren, Tom</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AR" term="%22Lein%2C+Ed%22">Lein, Ed</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Fischl%2C+Bruce%22">Fischl, Bruce</searchLink><relatesTo>3,5</relatesTo><br /><searchLink fieldCode="AR" term="%22Ourselin%2C+Sebastien%22">Ourselin, Sebastien</searchLink><relatesTo>1,2</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Medical+Image+Analysis%22">Medical Image Analysis</searchLink>. Dec2018, Vol. 50, p127-144. 18p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Magnetic+resonance+imaging%22">Magnetic resonance imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Probabilistic+databases%22">Probabilistic databases</searchLink><br /><searchLink fieldCode="DE" term="%22Bayesian+analysis%22">Bayesian analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Information+theory%22">Information theory</searchLink><br /><searchLink fieldCode="DE" term="%22Applied+mathematics%22">Applied mathematics</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights • A framework to jointly estimate registration and synthesis, without training data Uncertainty of each component considered when estimating the parameters of the other. • Principled framework enables seamless integration of manually placed landmarks. • More accurate and robust than mutual information in histology-MR registration. • Compelling results in synthetic (ADNI, MRI-MRI) and real data (Allen, histology-MRI). Graphical abstract Image, graphical abstract Abstract Nonlinear registration of 2D histological sections with corresponding slices of MRI data is a critical step of 3D histology reconstruction algorithms. This registration is difficult due to the large differences in image contrast and resolution, as well as the complex nonrigid deformations and artefacts produced when sectioning the sample and mounting it on the glass slide. It has been shown in brain MRI registration that better spatial alignment across modalities can be obtained by synthesising one modality from the other and then using intra-modality registration metrics, rather than by using information theory based metrics to solve the problem directly. However, such an approach typically requires a database of aligned images from the two modalities, which is very difficult to obtain for histology and MRI. Here, we overcome this limitation with a probabilistic method that simultaneously solves for deformable registration and synthesis directly on the target images, without requiring any training data. The method is based on a probabilistic model in which the MRI slice is assumed to be a contrast-warped, spatially deformed version of the histological section. We use approximate Bayesian inference to iteratively refine the probabilistic estimate of the synthesis and the registration, while accounting for each other's uncertainty. Moreover, manually placed landmarks can be seamlessly integrated in the framework for increased performance and robustness. Experiments on a synthetic dataset of MRI slices show that, compared with mutual information based registration, the proposed method makes it possible to use a much more flexible deformation model in the registration to improve its accuracy, without compromising robustness. Moreover, our framework also exploits information in manually placed landmarks more efficiently than mutual information: landmarks constrain the deformation field in both methods, but in our algorithm, it also has a positive effect on the synthesis – which further improves the registration. We also show results on two real, publicly available datasets: the Allen and BigBrain atlases. In both of them, the proposed method provides a clear improvement over mutual information based registration, both qualitatively (visual inspection) and quantitatively (registration error measured with pairs of manually annotated landmarks). [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Medical Image Analysis 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=132606956 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.media.2018.09.002 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 18 StartPage: 127 Subjects: – SubjectFull: Magnetic resonance imaging Type: general – SubjectFull: Probabilistic databases Type: general – SubjectFull: Bayesian analysis Type: general – SubjectFull: Information theory Type: general – SubjectFull: Applied mathematics Type: general Titles: – TitleFull: Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Iglesias, Juan Eugenio – PersonEntity: Name: NameFull: Modat, Marc – PersonEntity: Name: NameFull: Peter, Loïc – PersonEntity: Name: NameFull: Stevens, Allison – PersonEntity: Name: NameFull: Annunziata, Roberto – PersonEntity: Name: NameFull: Vercauteren, Tom – PersonEntity: Name: NameFull: Lein, Ed – PersonEntity: Name: NameFull: Fischl, Bruce – PersonEntity: Name: NameFull: Ourselin, Sebastien IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 12 Text: Dec2018 Type: published Y: 2018 Identifiers: – Type: issn-print Value: 13618415 Numbering: – Type: volume Value: 50 Titles: – TitleFull: Medical Image Analysis Type: main |
| ResultId | 1 |
