A skewed loss function for correcting predictive bias in brain age prediction

Wang, Hanzhi ORCID: https://orcid.org/0000-0002-7714-4606, Treder, Matthias ORCID: https://orcid.org/0000-0001-5955-2326, Marshall, David ORCID: https://orcid.org/0000-0003-2789-1395, Jones, Derek ORCID: https://orcid.org/0000-0003-4409-8049 and Li, Yuhua ORCID: https://orcid.org/0000-0003-2913-4478 2023. A skewed loss function for correcting predictive bias in brain age prediction. IEEE Transactions on Medical Imaging 42 (6) , pp. 1577-1589. 10.1109/TMI.2022.3231730

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (3MB) | Preview

Abstract

In neuroimaging, the difference between predicted brain age and chronological age, known as brain age delta, has shown its potential as a biomarker related to various pathological phenotypes. There is a frequently observed bias when estimating brain age delta using regression models. This bias manifests as an overestimation of brain age for young participants and an underestimation of brain age for older participants. Therefore, the brain age delta is negatively correlated with chronological age, which can be problematic when evaluating relationships between brain age delta and other age-associated variables. This paper proposes a novel bias correction method for regression models by introducing a skewed loss function to replace the normal symmetric loss function. The regression model then behaves differently depending on whether it makes overestimations or underestimations. Our approach works with any type of MR image and no specific preprocessing is required, as long as the image is sensitive to age-related changes. The proposed approach has been validated using three classic deep learning models, namely ResNet, VGG, and GoogleNet on publicly available neuroimaging aging datasets. It shows flexibility across different model architectures and different choices of hyperparameters. The corrected brain age delta from our approach then has no linear relationship with chronological age and achieves higher predictive accuracy than a commonly-used two-stage approach.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Advanced Research Computing @ Cardiff (ARCCA) Computer Science & Informatics Cardiff University Brain Research Imaging Centre (CUBRIC)
Subjects:	B Philosophy. Psychology. Religion > BF Psychology Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Uncontrolled Keywords:	brain age delta, deep learning, neuroimaging, skewed loss function, regression bias correction
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	0278-0062
Funders:	China Scholarship Council, Wellcome Trust
Date of First Compliant Deposit:	20 December 2022
Date of Acceptance:	18 December 2022
Last Modified:	01 Aug 2024 16:08
URI:	https://orca.cardiff.ac.uk/id/eprint/155040

Actions (repository staff only)

Edit Item