Probabilistic modeling of anatomical variability using a low dimensional parameterization of diffeomorphisms
© 2017 Elsevier B.V. We present an efficient probabilistic model of anatomical variability in a linear space of initial velocities of diffeomorphic transformations and demonstrate its benefits in clinical studies of brain anatomy. To overcome the computational challenges of the high dimensional defo...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2021
|
| Online Access: | https://hdl.handle.net/1721.1/135723 |
| _version_ | 1826196535288791040 |
|---|---|
| author | Zhang, Miaomiao Wells, William M Golland, Polina |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Zhang, Miaomiao Wells, William M Golland, Polina |
| author_sort | Zhang, Miaomiao |
| collection | MIT |
| description | © 2017 Elsevier B.V. We present an efficient probabilistic model of anatomical variability in a linear space of initial velocities of diffeomorphic transformations and demonstrate its benefits in clinical studies of brain anatomy. To overcome the computational challenges of the high dimensional deformation-based descriptors, we develop a latent variable model for principal geodesic analysis (PGA) based on a low dimensional shape descriptor that effectively captures the intrinsic variability in a population. We define a novel shape prior that explicitly represents principal modes as a multivariate complex Gaussian distribution on the initial velocities in a bandlimited space. We demonstrate the performance of our model on a set of 3D brain MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our model yields a more compact representation of group variation at substantially lower computational cost than the state-of-the-art method such as tangent space PCA (TPCA) and probabilistic principal geodesic analysis (PPGA) that operate in the high dimensional image space. |
| first_indexed | 2024-09-23T10:28:53Z |
| format | Article |
| id | mit-1721.1/135723 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:28:53Z |
| publishDate | 2021 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1357232023-02-17T18:43:36Z Probabilistic modeling of anatomical variability using a low dimensional parameterization of diffeomorphisms Zhang, Miaomiao Wells, William M Golland, Polina Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory © 2017 Elsevier B.V. We present an efficient probabilistic model of anatomical variability in a linear space of initial velocities of diffeomorphic transformations and demonstrate its benefits in clinical studies of brain anatomy. To overcome the computational challenges of the high dimensional deformation-based descriptors, we develop a latent variable model for principal geodesic analysis (PGA) based on a low dimensional shape descriptor that effectively captures the intrinsic variability in a population. We define a novel shape prior that explicitly represents principal modes as a multivariate complex Gaussian distribution on the initial velocities in a bandlimited space. We demonstrate the performance of our model on a set of 3D brain MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our model yields a more compact representation of group variation at substantially lower computational cost than the state-of-the-art method such as tangent space PCA (TPCA) and probabilistic principal geodesic analysis (PPGA) that operate in the high dimensional image space. 2021-10-27T20:29:00Z 2021-10-27T20:29:00Z 2017 2019-05-29T18:16:51Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/135723 en 10.1016/J.MEDIA.2017.06.013 Medical Image Analysis Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV PMC |
| spellingShingle | Zhang, Miaomiao Wells, William M Golland, Polina Probabilistic modeling of anatomical variability using a low dimensional parameterization of diffeomorphisms |
| title | Probabilistic modeling of anatomical variability using a low dimensional parameterization of diffeomorphisms |
| title_full | Probabilistic modeling of anatomical variability using a low dimensional parameterization of diffeomorphisms |
| title_fullStr | Probabilistic modeling of anatomical variability using a low dimensional parameterization of diffeomorphisms |
| title_full_unstemmed | Probabilistic modeling of anatomical variability using a low dimensional parameterization of diffeomorphisms |
| title_short | Probabilistic modeling of anatomical variability using a low dimensional parameterization of diffeomorphisms |
| title_sort | probabilistic modeling of anatomical variability using a low dimensional parameterization of diffeomorphisms |
| url | https://hdl.handle.net/1721.1/135723 |
| work_keys_str_mv | AT zhangmiaomiao probabilisticmodelingofanatomicalvariabilityusingalowdimensionalparameterizationofdiffeomorphisms AT wellswilliamm probabilisticmodelingofanatomicalvariabilityusingalowdimensionalparameterizationofdiffeomorphisms AT gollandpolina probabilisticmodelingofanatomicalvariabilityusingalowdimensionalparameterizationofdiffeomorphisms |