Exploring the performance of implicit neural representations for brain image registration
Abstract Pairwise image registration is a necessary prerequisite for brain image comparison and data integration in neuroscience and radiology. In this work, we explore the efficacy of implicit neural representations (INRs) in improving the performance of brain image registration in magnetic resonan...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-44517-5 |
| _version_ | 1797453340563472384 |
|---|---|
| author | Michal Byra Charissa Poon Muhammad Febrian Rachmadi Matthias Schlachter Henrik Skibbe |
| author_facet | Michal Byra Charissa Poon Muhammad Febrian Rachmadi Matthias Schlachter Henrik Skibbe |
| author_sort | Michal Byra |
| collection | DOAJ |
| description | Abstract Pairwise image registration is a necessary prerequisite for brain image comparison and data integration in neuroscience and radiology. In this work, we explore the efficacy of implicit neural representations (INRs) in improving the performance of brain image registration in magnetic resonance imaging. In this setting, INRs serve as a continuous and coordinate based approximation of the deformation field obtained through a multi-layer perceptron. Previous research has demonstrated that sinusoidal representation networks (SIRENs) surpass ReLU models in performance. In this study, we first broaden the range of activation functions to further investigate the registration performance of implicit networks equipped with activation functions that exhibit diverse oscillatory properties. Specifically, in addition to the SIRENs and ReLU, we evaluate activation functions based on snake, sine+, chirp and Morlet wavelet functions. Second, we conduct experiments to relate the hyper-parameters of the models to registration performance. Third, we propose and assess various techniques, including cycle consistency loss, ensembles and cascades of implicit networks, as well as a combined image fusion and registration objective, to enhance the performance of implicit registration networks beyond the standard approach. The investigated implicit methods are compared to the VoxelMorph convolutional neural network and to the symmetric image normalization (SyN) registration algorithm from the Advanced Normalization Tools (ANTs). Our findings not only highlight the remarkable capabilities of implicit networks in addressing pairwise image registration challenges, but also showcase their potential as a powerful and versatile off-the-shelf tool in the fields of neuroscience and radiology. |
| first_indexed | 2024-03-09T15:21:24Z |
| format | Article |
| id | doaj.art-68545162600c4474837a154457350816 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:21:24Z |
| publishDate | 2023-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-68545162600c4474837a1544573508162023-11-26T12:47:46ZengNature PortfolioScientific Reports2045-23222023-10-0113111310.1038/s41598-023-44517-5Exploring the performance of implicit neural representations for brain image registrationMichal Byra0Charissa Poon1Muhammad Febrian Rachmadi2Matthias Schlachter3Henrik Skibbe4RIKEN Center for Brain ScienceRIKEN Center for Brain ScienceRIKEN Center for Brain ScienceRIKEN Center for Brain ScienceRIKEN Center for Brain ScienceAbstract Pairwise image registration is a necessary prerequisite for brain image comparison and data integration in neuroscience and radiology. In this work, we explore the efficacy of implicit neural representations (INRs) in improving the performance of brain image registration in magnetic resonance imaging. In this setting, INRs serve as a continuous and coordinate based approximation of the deformation field obtained through a multi-layer perceptron. Previous research has demonstrated that sinusoidal representation networks (SIRENs) surpass ReLU models in performance. In this study, we first broaden the range of activation functions to further investigate the registration performance of implicit networks equipped with activation functions that exhibit diverse oscillatory properties. Specifically, in addition to the SIRENs and ReLU, we evaluate activation functions based on snake, sine+, chirp and Morlet wavelet functions. Second, we conduct experiments to relate the hyper-parameters of the models to registration performance. Third, we propose and assess various techniques, including cycle consistency loss, ensembles and cascades of implicit networks, as well as a combined image fusion and registration objective, to enhance the performance of implicit registration networks beyond the standard approach. The investigated implicit methods are compared to the VoxelMorph convolutional neural network and to the symmetric image normalization (SyN) registration algorithm from the Advanced Normalization Tools (ANTs). Our findings not only highlight the remarkable capabilities of implicit networks in addressing pairwise image registration challenges, but also showcase their potential as a powerful and versatile off-the-shelf tool in the fields of neuroscience and radiology.https://doi.org/10.1038/s41598-023-44517-5 |
| spellingShingle | Michal Byra Charissa Poon Muhammad Febrian Rachmadi Matthias Schlachter Henrik Skibbe Exploring the performance of implicit neural representations for brain image registration Scientific Reports |
| title | Exploring the performance of implicit neural representations for brain image registration |
| title_full | Exploring the performance of implicit neural representations for brain image registration |
| title_fullStr | Exploring the performance of implicit neural representations for brain image registration |
| title_full_unstemmed | Exploring the performance of implicit neural representations for brain image registration |
| title_short | Exploring the performance of implicit neural representations for brain image registration |
| title_sort | exploring the performance of implicit neural representations for brain image registration |
| url | https://doi.org/10.1038/s41598-023-44517-5 |
| work_keys_str_mv | AT michalbyra exploringtheperformanceofimplicitneuralrepresentationsforbrainimageregistration AT charissapoon exploringtheperformanceofimplicitneuralrepresentationsforbrainimageregistration AT muhammadfebrianrachmadi exploringtheperformanceofimplicitneuralrepresentationsforbrainimageregistration AT matthiasschlachter exploringtheperformanceofimplicitneuralrepresentationsforbrainimageregistration AT henrikskibbe exploringtheperformanceofimplicitneuralrepresentationsforbrainimageregistration |