JUMP: A joint multimodal registration pipeline for neuroimaging with minimal preprocessing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Casamitjana, Adria, Iglesias, Juan Eugenio, Tudela, Raul, Ninerola-Baizan, Aida, Sala-Llonch, Roser
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910307889184768
author Casamitjana, Adria
Iglesias, Juan Eugenio
Tudela, Raul
Ninerola-Baizan, Aida
Sala-Llonch, Roser
author_facet Casamitjana, Adria
Iglesias, Juan Eugenio
Tudela, Raul
Ninerola-Baizan, Aida
Sala-Llonch, Roser
contents We present a pipeline for unbiased and robust multimodal registration of neuroimaging modalities with minimal pre-processing. While typical multimodal studies need to use multiple independent processing pipelines, with diverse options and hyperparameters, we propose a single and structured framework to jointly process different image modalities. The use of state-of-the-art learning-based techniques enables fast inferences, which makes the presented method suitable for large-scale and/or multi-cohort datasets with a diverse number of modalities per session. The pipeline currently works with structural MRI, resting state fMRI and amyloid PET images. We show the predictive power of the derived biomarkers using in a case-control study and study the cross-modal relationship between different image modalities. The code can be found in https: //github.com/acasamitjana/JUMP.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14250
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle JUMP: A joint multimodal registration pipeline for neuroimaging with minimal preprocessing
Casamitjana, Adria
Iglesias, Juan Eugenio
Tudela, Raul
Ninerola-Baizan, Aida
Sala-Llonch, Roser
Computer Vision and Pattern Recognition
We present a pipeline for unbiased and robust multimodal registration of neuroimaging modalities with minimal pre-processing. While typical multimodal studies need to use multiple independent processing pipelines, with diverse options and hyperparameters, we propose a single and structured framework to jointly process different image modalities. The use of state-of-the-art learning-based techniques enables fast inferences, which makes the presented method suitable for large-scale and/or multi-cohort datasets with a diverse number of modalities per session. The pipeline currently works with structural MRI, resting state fMRI and amyloid PET images. We show the predictive power of the derived biomarkers using in a case-control study and study the cross-modal relationship between different image modalities. The code can be found in https: //github.com/acasamitjana/JUMP.
title JUMP: A joint multimodal registration pipeline for neuroimaging with minimal preprocessing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.14250