Fighting the scanner effect in brain MRI segmentation with a progressive level-of-detail network trained on multi-site data

Svanera, M. , Savardi, M., Signoroni, A., Benini, S. and Muckli, L. (2024) Fighting the scanner effect in brain MRI segmentation with a progressive level-of-detail network trained on multi-site data. Medical Image Analysis, 93, 103090. (doi: 10.1016/j.media.2024.103090) (PMID:38241763)

Abstract

Many clinical and research studies of the human brain require accurate structural MRI segmentation. While traditional atlas-based methods can be applied to volumes from any acquisition site, recent deep learning algorithms ensure high accuracy only when tested on data from the same sites exploited in training (i.e., internal data). Performance degradation experienced on external data (i.e., unseen volumes from unseen sites) is due to the inter-site variability in intensity distributions, and to unique artefacts caused by different MR scanner models and acquisition parameters. To mitigate this site-dependency, often referred to as the scanner effect, we propose LOD-Brain, a 3D convolutional neural network with progressive levels-of-detail (LOD), able to segment brain data from any site. Coarser network levels are responsible for learning a robust anatomical prior helpful in identifying brain structures and their locations, while finer levels refine the model to handle site-specific intensity distributions and anatomical variations. We ensure robustness across sites by training the model on an unprecedentedly rich dataset aggregating data from open repositories: almost 27,000 T1w volumes from around 160 acquisition sites, at 1.5 - 3T, from a population spanning from 8 to 90 years old. Extensive tests demonstrate that LOD-Brain produces state-of-the-art results, with no significant difference in performance between internal and external sites, and robust to challenging anatomical variations. Its portability paves the way for large-scale applications across different healthcare institutions, patient populations, and imaging technology manufacturers. Code, model, and demo are available on the project website.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Svanera, Dr Michele and Savardi, Mr Mattia and Muckli, Professor Lars

Creator Roles

Svanera, M.: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – review and editing, Visualization
Savardi, M.: Conceptualization, Methodology, Software, Validation, Investigation, Writing – review and editing, Visualization
Muckli, L.: Resources, Funding acquisition

• Authors: Svanera, M., Savardi, M., Signoroni, A., Benini, S., and Muckli, L.
• College/School: College of Medical Veterinary and Life Sciences > School of Psychology & Neuroscience
• Journal Name: Medical Image Analysis
• Publisher: Elsevier
• ISSN: 1361-8415
• ISSN (Online): 1361-8423
• Published Online: 17 January 2024
• Copyright Holders: Copyright © 2024 The Authors
• First Published: First published in Medical Image Analysis 93:103090
• Publisher Policy: Reproduced under a Creative Commons licence

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
307180		Human Brain Project SGA_3	Lars Muckli	European Commission (EC)	945539	SPN - Centre for Cognitive Neuroimaging (CCNi)