Longitudinal Prediction of Postnatal Brain Magnetic Resonance Images via a Metamorphic Generative Adversarial Network.
Longitudinal Prediction of Postnatal Brain Magnetic Resonance Images via a Metamorphic Generative Adversarial Network.
复制标题
通过变形生成对抗网络对产后脑磁共振图像进行纵向预测。
DOI：
10.1016/j.patcog.2023.109715
复制
发表时间：
2023
影响因子：
8
通讯作者：
Yap,Pew-Thian
中科院分区：
文献类型：
--
作者：
Huang,Yunzhi;Ahmad,Sahar;Han,Luyi;Wang,Shuai;Wu,Zhengwang;Lin,Weili;Li,Gang;Wang,Li;Yap,Pew-Thian
在纵向研究中，由于受试者退出或扫描失败，扫描缺失是不可避免的。在本文中，我们提出了一个深度学习框架来预测从获得性扫描中缺失的扫描，以适应纵向婴儿研究。由于快速对比和结构变化，特别是在生命的第一年，婴儿脑MRI的预测是具有挑战性的。我们引入了一种可信赖的变质生成对抗网络（MGAN），用于将婴儿脑MRI从一个时间点翻译到另一个时间点。MGAN具有三个关键特征：(i)利用空间和频率信息进行图像转换，以保持细节映射；以质量为导向的学习战略，将注意力集中在具有挑战性的地区。（iii）改进图像内容平移的多尺度混合损失函数。实验结果表明，MGAN在准确预测组织对比度和解剖细节方面优于现有的gan。
Missing scans are inevitable in longitudinal studies due to either subject dropouts or failed scans. In this paper, we propose a deep learning framework to predict missing scans from acquired scans, catering to longitudinal infant studies. Prediction of infant brain MRI is challenging owing to the rapid contrast and structural changes particularly during the first year of life. We introduce a trustworthy metamorphic generative adversarial network (MGAN) for translating infant brain MRI from one time point to another. MGAN has three key features: (i) Image translation leveraging spatial and frequency information for detail-preserving mapping; (ii) Quality-guided learning strategy that focuses attention on challenging regions. (iii) Multi-scale hybrid loss function that improves translation of image contents. Experimental results indicate that MGAN outperforms existing GANs by accurately predicting both tissue contrasts and anatomical details.