干旱区生态环境知识资源中心(Arid): Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models

Arid

DOI	10.1016/j.media.2022.102723
	Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models
	Pombo, Guilherme; Gray, Robert; Cardoso, M. Jorge; Ourselin, Sebastien; Rees, Geraint; Ashburner, John; Nachev, Parashkev
通讯作者	Pombo, G
来源期刊	MEDICAL IMAGE ANALYSIS
ISSN	1361-8415
EISSN	1361-8423
出版年	2023
卷号	84
英文摘要	We describe CounterSynth, a conditional generative model of diffeomorphic deformations that induce label driven, biologically plausible changes in volumetric brain images. The model is intended to synthesise counterfactual training data augmentations for downstream discriminative modelling tasks where fidelity is limited by data imbalance, distributional instability, confounding, or underspecification, and exhibits inequitable performance across distinct subpopulations.Focusing on demographic attributes, we evaluate the quality of synthesised counterfactuals with voxelbased morphometry, classification and regression of the conditioning attributes, and the Frechet inception distance. Examining downstream discriminative performance in the context of engineered demographic imbalance and confounding, we use UK Biobank and OASIS magnetic resonance imaging data to benchmark CounterSynth augmentation against current solutions to these problems. We achieve state-of-the-art improvements, both in overall fidelity and equity. The source code for CounterSynth is available at https: //github.com/guilherme-pombo/CounterSynth.
英文关键词	Counterfactuals Deep generative models Diffeomorphic deformations Discriminative models Data augmentation Fairness Equity Brain imaging
类型	Article
语种	英语
开放获取类型	Green Published, hybrid, Green Submitted
收录类别	SCI-E
WOS记录号	WOS:000912445400001
WOS关键词	VOXEL-BASED MORPHOMETRY ; ALZHEIMERS-DISEASE ; SEX-DIFFERENCES ; SEGMENTATION ; REGISTRATION
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging
WOS研究方向	Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/397821
推荐引用方式 GB/T 7714	Pombo, Guilherme,Gray, Robert,Cardoso, M. Jorge,et al. Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models[J],2023,84.
APA	Pombo, Guilherme.,Gray, Robert.,Cardoso, M. Jorge.,Ourselin, Sebastien.,Rees, Geraint.,...&Nachev, Parashkev.(2023).Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models.MEDICAL IMAGE ANALYSIS,84.
MLA	Pombo, Guilherme,et al."Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models".MEDICAL IMAGE ANALYSIS 84(2023).