Momeni Saba, Fazlollahi Amir, Lebrat Leo, Yates Paul, Rowe Christopher, Gao Yongsheng, Liew Alan Wee-Chung, Salvado Olivier
Commonwealth Scientific and Industrial Research Organisation (CSIRO) Data61, Brisbane, QLD, Australia.
School of Engineering and Built Environment, Griffith University, Nathan, QLD, Australia.
Front Neurosci. 2021 Dec 16;15:778767. doi: 10.3389/fnins.2021.778767. eCollection 2021.
Cerebral microbleeds (CMB) are increasingly present with aging and can reveal vascular pathologies associated with neurodegeneration. Deep learning-based classifiers can detect and quantify CMB from MRI, such as susceptibility imaging, but are challenging to train because of the limited availability of ground truth and many confounding imaging features, such as vessels or infarcts. In this study, we present a novel generative adversarial network (GAN) that has been trained to generate three-dimensional lesions, conditioned by volume and location. This allows one to investigate CMB characteristics and create large training datasets for deep learning-based detectors. We demonstrate the benefit of this approach by achieving state-of-the-art CMB detection of real CMB using a convolutional neural network classifier trained on synthetic CMB. Moreover, we showed that our proposed 3D lesion GAN model can be applied on unseen dataset, with different MRI parameters and diseases, to generate synthetic lesions with high diversity and without needing laboriously marked ground truth.
脑微出血（CMB）随着年龄增长愈发常见，并且可能揭示与神经退行性变相关的血管病变。基于深度学习的分类器能够从磁共振成像（MRI）中检测并量化CMB，比如利用磁化率成像，但由于真实标注的有限可用性以及诸多混淆的成像特征（如血管或梗死灶），训练这类分类器颇具挑战性。在本研究中，我们提出了一种新型生成对抗网络（GAN），该网络已被训练用于生成三维病变，其条件是体积和位置。这使得人们能够研究CMB特征，并为基于深度学习的探测器创建大型训练数据集。我们通过使用在合成CMB上训练的卷积神经网络分类器，实现了对真实CMB的最先进检测，从而证明了这种方法的优势。此外，我们表明，我们提出的3D病变GAN模型可应用于未见数据集，这些数据集具有不同的MRI参数和疾病，以生成具有高度多样性且无需费力标记真实标注的合成病变。
