Salvato in:
Dettagli Bibliografici
Autori principali: Grødem, Edvard O. S., Sederevičius, Donatas, Leonardsen, Esten H., MacIntosh, Bradley J., Bjørnerud, Atle, Schellhorn, Till, Sørensen, Øystein, Amlien, Inge, Garrido, Pablo F., Fjell, Anders M.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.14671
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915071178833920
author Grødem, Edvard O. S.
Sederevičius, Donatas
Leonardsen, Esten H.
MacIntosh, Bradley J.
Bjørnerud, Atle
Schellhorn, Till
Sørensen, Øystein
Amlien, Inge
Garrido, Pablo F.
Fjell, Anders M.
author_facet Grødem, Edvard O. S.
Sederevičius, Donatas
Leonardsen, Esten H.
MacIntosh, Bradley J.
Bjørnerud, Atle
Schellhorn, Till
Sørensen, Øystein
Amlien, Inge
Garrido, Pablo F.
Fjell, Anders M.
contents Longitudinal imaging allows for the study of structural changes over time. One approach to detecting such changes is by non-linear image registration. This study introduces Multi-Session Temporal Registration (MUSTER), a novel method that facilitates longitudinal analysis of changes in extended series of medical images. MUSTER improves upon conventional pairwise registration by incorporating more than two imaging sessions to recover longitudinal deformations. Longitudinal analysis at a voxel-level is challenging due to effects of a changing image contrast as well as instrumental and environmental sources of bias between sessions. We show that local normalized cross-correlation as an image similarity metric leads to biased results and propose a robust alternative. We test the performance of MUSTER on a synthetic multi-site, multi-session neuroimaging dataset and show that, in various scenarios, using MUSTER significantly enhances the estimated deformations relative to pairwise registration. Additionally, we apply MUSTER on a sample of older adults from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. The results show that MUSTER can effectively identify patterns of neuro-degeneration from T1-weighted images and that these changes correlate with changes in cognition, matching the performance of state of the art segmentation methods. By leveraging GPU acceleration, MUSTER efficiently handles large datasets, making it feasible also in situations with limited computational resources.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14671
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MUSTER: Longitudinal Deformable Registration by Composition of Consecutive Deformations
Grødem, Edvard O. S.
Sederevičius, Donatas
Leonardsen, Esten H.
MacIntosh, Bradley J.
Bjørnerud, Atle
Schellhorn, Till
Sørensen, Øystein
Amlien, Inge
Garrido, Pablo F.
Fjell, Anders M.
Computer Vision and Pattern Recognition
Numerical Analysis
Longitudinal imaging allows for the study of structural changes over time. One approach to detecting such changes is by non-linear image registration. This study introduces Multi-Session Temporal Registration (MUSTER), a novel method that facilitates longitudinal analysis of changes in extended series of medical images. MUSTER improves upon conventional pairwise registration by incorporating more than two imaging sessions to recover longitudinal deformations. Longitudinal analysis at a voxel-level is challenging due to effects of a changing image contrast as well as instrumental and environmental sources of bias between sessions. We show that local normalized cross-correlation as an image similarity metric leads to biased results and propose a robust alternative. We test the performance of MUSTER on a synthetic multi-site, multi-session neuroimaging dataset and show that, in various scenarios, using MUSTER significantly enhances the estimated deformations relative to pairwise registration. Additionally, we apply MUSTER on a sample of older adults from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. The results show that MUSTER can effectively identify patterns of neuro-degeneration from T1-weighted images and that these changes correlate with changes in cognition, matching the performance of state of the art segmentation methods. By leveraging GPU acceleration, MUSTER efficiently handles large datasets, making it feasible also in situations with limited computational resources.
title MUSTER: Longitudinal Deformable Registration by Composition of Consecutive Deformations
topic Computer Vision and Pattern Recognition
Numerical Analysis
url https://arxiv.org/abs/2412.14671