期刊
MEDICAL IMAGE UNDERSTANDING AND ANALYSIS (MIUA 2021)
卷 12722, 期 -, 页码 350-360出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-80432-9_27
关键词
Generative adversarial network; Brain age regression; Data augmentation
This paper proposes a brain age estimation method based on generative adversarial network, which integrates a task-guided branch to improve model performance and achieves excellent results on a public dataset.
Brain age estimation based on magnetic resonance imaging (MRI) is an active research area in early diagnosis of some neurodegenerative diseases (e.g. Alzheimer, Parkinson, Huntington, etc.) for elderly people or brain underdevelopment for the young group. Deep learning methods have achieved the state-ofthe-art performance in many medical image analysis tasks, including brain age estimation. However, the performance and generalisability of the deep learning model are highly dependent on the quantity and quality of the training data set. Both collecting and annotating brain MRI data are extremely time-consuming. In this paper, to overcome the data scarcity problem, we propose a generative adversarial network (GAN) based image synthesis method. Different from the existing GAN-based methods, we integrate a task-guided branch (a regression model for age estimation) to the end of the generator in GAN. By adding a task-guided loss to the conventional GAN loss, the learned low-dimensional latent space and the synthesised images are more task-specific. It helps to boost the performance of the down-stream task by combining the synthesised images and real images for model training. The proposed methodwas evaluated on a public brainMRI data set for age estimation. Our proposed method outperformed (statistically significant) a deep convolutional neural network based regression model and the GAN-based image synthesismethod without the task-guided branch. More importantly, it enables the identification of age-related brain regions in the image space. The code is available on GitHub (https://github.com/ruizhe-l/tgb-gan).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据