Title :

A three-dimensional deep learning model for inter-site harmonization of structural MR images of the brain: Extensive validation with a multicenter dataset.

Author(s) :

Roca, Vincent [Auteur]
Plateformes Lilloises en Biologie et Santé - UAR 2014 - US 41 [PLBS]
Kuchcinski, Gregory [Auteur]
Lille Neurosciences & Cognition (LilNCog) - U 1172
Pruvo, Jean-Pierre [Auteur]
Lille Neurosciences & Cognition - U 1172 [LilNCog]
Manouvriez, Dorian [Auteur]
Plateformes Lilloises en Biologie et Santé - UAR 2014 - US 41 [PLBS]
Leclerc, Xavier [Auteur]
Lille Neurosciences & Cognition - U 1172 [LilNCog]
Lopes, Renaud [Auteur]
Lille Neurosciences & Cognition - U 1172 [LilNCog]

Journal title :

Heliyon

Abbreviated title :

Heliyon

Volume number :

9

Pages :

e22647

Publisher :

Elsevier

Publication date :

2023-12-19

ISSN :

2405-8440

HAL domain(s) :

Sciences du Vivant [q-bio]

English abstract : [en]

In multicenter MRI studies, pooling the imaging data can introduce site-related variabilities and can therefore bias the subsequent analyses. To harmonize the intensity distributions of brain MR images in a multicenter ...
Show more >In multicenter MRI studies, pooling the imaging data can introduce site-related variabilities and can therefore bias the subsequent analyses. To harmonize the intensity distributions of brain MR images in a multicenter dataset, unsupervised deep learning methods can be employed. Here, we developed a model based on cycle-consistent adversarial networks for the harmonization of T1-weighted brain MR images. In contrast to previous works, it was designed to process three-dimensional whole-brain images in a stable manner while optimizing computation resources. Using six different MRI datasets for healthy adults (n=1525 in total) with different acquisition parameters, we tested the model in (i) three pairwise harmonizations with site effects of various sizes, (ii) an overall harmonization of the six datasets with different age distributions, and (iii) a traveling-subject dataset. Our results for intensity distributions, brain volumes, image quality metrics and radiomic features indicated that the MRI characteristics at the various sites had been effectively homogenized. Next, brain age prediction experiments and the observed correlation between the gray-matter volume and age showed that thanks to an appropriate training strategy and despite biological differences between the dataset populations, the model reinforced biological patterns. Furthermore, radiologic analyses of the harmonized images attested to the conservation of the radiologic information in the original images. The robustness of the harmonization model (as judged with various datasets and metrics) demonstrates its potential for application in retrospective multicenter studies.Show less >

Language :

Anglais

Audience :

Internationale

Popular science :

Non

Administrative institution(s) :

Université de Lille
Inserm
CHU Lille

Collections :

• Lille Neurosciences & Cognition (LilNCog) - U 1172

Submission date :

2024-01-15T22:02:20Z
2024-09-18T06:26:32Z