Given the high prevalence of aging-associated cerebral small vessel disease in the general population, accurate detection of the related white matter hyperintensities (WMH) in large-scale magnetic resonance imaging (MRI) studies is of critical importance. The performance of currently available semi-automated and automated methods for WMH classification is hampered by their inherent dependence on MRI contrast parameters and long computational processing time. We sought to improve the accuracy and computational cost of automated WMH detection by creating a whole-brain deep learning-based framework: WHITE-Net. We use a 3D ResUNet architecture trained on manually segmented WMHs from fluid-attenuated inversion recovery MRI (n=141) and test its accuracy in a large-scale dataset (n=192). We demonstrate a good generalizability across WMH lesion loads, different MRI scanner vendors, field strengths, imaging protocols, and MR contrasts. The comparison to existing WMH segmentation tools shows a similar to superior accuracy performance at significantly lower computational cost. WHITE-Net tool performance makes it well-suited for application to large-scale MRI datasets, enabling the study of the aging brain while offering the advantage of detecting early or subtle WMH changes often missed by other methods.

The authors have declared no competing interest.

https://github.com/cathalacamille/WHITE-Net

Funding is supported by the Swiss National Science Foundation (project grants Nr. 213595,32003B_135679, 32003B_159780, 324730_192755 and CRSK-3_190185), ERA_NET iSEE and BrainTree projects. LREN is very grateful to the Roger De Spoelberch and Partridge Foundations for their generous financial support.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Ethics Commission of Canton de Vaud gave ethical approval for this work

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

Data of CoLaus|PsyCoLaus study used in this article cannot be fully shared as they contain potentially sensitive personal information on participants. According to the Ethics Committee for Research of the Canton of Vaud, sharing these data would be a violation of the Swiss legislation with respect to privacy protection. However, coded individual-level data that do not allow researchers to identify participants are available upon request to researchers who meet the criteria for data sharing of the CoLaus|PsyCoLaus Datacenter (CHUV, Lausanne, Switzerland). Any researcher affiliated to a public or private research institution who complies with the CoLaus|PsyCoLaus standards can submit a research application to research.colaus@chuv.ch or research.psycolaus@chuv.ch. Proposals will be evaluated by the Scientific Committee (SC) of the CoLaus|PsyCoLaus studies. Detailed instructions for gaining access to the CoLaus|PsyCoLaus data used in this study are available at www.colaus-psycolaus.ch/professionals/how-to-collaborate/. Data from WMH challenge are freely available at https://doi.org/10.34894/aecrsd (H. Kuijf et al., 2022). Code for the segmentation tool described in this article, WHITE-Net, is available on GitHub (https://github.com/cathalacamille/WHITE-Net).

https://doi.org/10.34894/aecrsd