Cardiac aging synthesis from cross-sectional data with conditional generative adversarial networks.
Cardiac aging synthesis from cross-sectional data with conditional generative adversarial networks.
复制标题
DOI：
10.3389/fcvm.2022.983091
复制
发表时间：
2022
影响因子：
3.6
通讯作者：
Lekadir, Karim
中科院分区：
文献类型：
--
作者：
Campello, Victor M.;Xia, Tian;Liu, Xiao;Sanchez, Pedro;Martin-Isla, Carlos;Petersen, Steffen E.;Segui, Santi;Tsaftaris, Sotirios A.;Lekadir, Karim
年龄对健康有重要影响，了解年龄在人体中的表现是潜在干预的第一步。这对心脏健康尤为重要，因为年龄是心血管疾病发展的主要风险因素。年龄进程的数据驱动建模已在面部或大脑老化等多种应用中成功进行。虽然纵向数据是训练深度学习模型的首选，但收集这样的数据集通常非常昂贵，特别是在医学成像中。在这项工作中，提出了一种条件生成对抗网络，通过仅使用横截面数据来合成心脏扫描的旧版本和新版本。我们用来自英国生物库的14，000多个不同的扫描来训练我们的模型。诱导的修改主要集中在室间隔和主动脉，这与心脏老化的现有文献一致。我们通过测量图像质量来评估结果，使用预先训练的回归量预测年龄的平均绝对误差，并展示了合成数据在平衡有偏数据集方面的应用。结果表明，所提出的方法是能够模拟现实的变化，在心脏只使用横截面数据，这些数据可以用来纠正数据集中的年龄偏差。
Age has important implications for health, and understanding how age manifests in the human body is the first step for a potential intervention. This becomes especially important for cardiac health, since age is the main risk factor for development of cardiovascular disease. Data-driven modeling of age progression has been conducted successfully in diverse applications such as face or brain aging. While longitudinal data is the preferred option for training deep learning models, collecting such a dataset is usually very costly, especially in medical imaging. In this work, a conditional generative adversarial network is proposed to synthesize older and younger versions of a heart scan by using only cross-sectional data. We train our model with more than 14,000 different scans from the UK Biobank. The induced modifications focused mainly on the interventricular septum and the aorta, which is consistent with the existing literature in cardiac aging. We evaluate the results by measuring image quality, the mean absolute error for predicted age using a pre-trained regressor, and demonstrate the application of synthetic data for counter-balancing biased datasets. The results suggest that the proposed approach is able to model realistic changes in the heart using only cross-sectional data and that these data can be used to correct age bias in a dataset.
登录
查看更多内容
影响因子：
2.8
作者：
BENJAMIN, EJ;LEVY, D;SUTTON, MS
通讯作者：
SUTTON, MS
A3GAN：用于人脸老化的属性感知注意力生成对抗网络
DOI：
10.1109/tifs.2021.3065499
发表时间：
2021-01-01
影响因子：
6.8
作者：
Liu, Yunfan;Li, Qi;Tan, Tieniu
通讯作者：
Tan, Tieniu
影响因子：
37.8
作者：
Lakatta, EG
通讯作者：
Lakatta, EG
影响因子：
--
作者：
Steenman, Marja;Lande, Gilles
通讯作者：
Lande, Gilles
影响因子：
10.9
作者：
Ravi D;Blumberg SB;Ingala S;Barkhof F;Alexander DC;Oxtoby NP;Alzheimer’s Disease Neuroimaging Initiative
通讯作者：
Alzheimer’s Disease Neuroimaging Initiative