Abstract:
Game theory-inspired deep learning using a generative adversarial network provides an environment to competitively interact and accomplish a goal. In the context of medical imaging, most work has focused on achieving single tasks such as improving image resolution, segmenting images, and correcting motion artifacts. We developed a dual-objective adversarial learning framework that simultaneously 1) reconstructs higher quality brain magnetic resonance images (MRIs) that 2) retain disease-specific imaging features critical for predicting progression from mild cognitive impairment (MCI) to Alzheimer\'s disease (AD). We obtained 3-Tesla, T1-weighted brain MRIs of participants from the Alzheimer\'s Disease Neuroimaging Initiative (ADNI, N=342) and the National Alzheimer\'s Coordinating Center (NACC, N = 190) datasets. We simulated MRIs with missing data by removing 50% of sagittal slices from the original scans (i.e., diced scans). The generator was trained to reconstruct brain MRIs using the diced scans as input. We introduced a classifier into the GAN architecture to discriminate between stable (i.e., sMCI) and progressive MCI (i.e., pMCI) based on the generated images to facilitate encoding of disease-related information during reconstruction. The framework was trained using ADNI data and externally validated on NACC data. In the NACC cohort, generated images had better image quality than the diced scans (Structural similarity (SSIM) index: 0.553 ± 0.116 versus 0.348 ± 0.108). Furthermore, a classifier utilizing the generated images distinguished pMCI from sMCI more accurately than with the diced scans (F1-score: 0.634 ± 0.019 versus 0.573 ± 0.028). Competitive deep learning has potential to facilitate disease-oriented image reconstruction in those at risk of developing Alzheimer\'s disease.
摘要:
博弈论启发的深度学习使用生成对抗网络提供了一个竞争互动和实现目标的环境。在医学成像的背景下,大多数工作都集中在实现单一任务,如提高图像分辨率,分割图像,并校正运动伪影。我们开发了一个双目标对抗学习框架,该框架同时1)重建更高质量的脑磁共振图像(MRI),2)保留对预测轻度认知障碍(MCI)进展为阿尔茨海默病(AD)至关重要的疾病特异性成像特征。我们得到了3特斯拉,阿尔茨海默病神经影像学计划参与者的T1加权脑MRI(ADNI,N=342)和国家阿尔茨海默氏症协调中心(NACC,N=190)个数据集。我们通过从原始扫描中删除50%的矢状切片来模拟具有缺失数据的MRI(即,切块扫描)。使用切块扫描作为输入来训练生成器以重建脑MRI。我们在GAN架构中引入了一个分类器来区分稳定的(即,sMCI)和渐进式MCI(即,pMCI)基于生成的图像,以便在重建过程中对疾病相关信息进行编码。使用ADNI数据对框架进行了训练,并在NACC数据上进行了外部验证。在NACC队列中,生成的图像比切块扫描具有更好的图像质量(结构相似性(SSIM)指数:0.553±0.116vs.0.348±0.108).此外,利用生成图像的分类器比使用切块扫描更准确地区分pMCI和sMCI(F1分数:0.634±0.019对0.573±0.028).有竞争力的深度学习有可能促进那些有患阿尔茨海默病风险的人的面向疾病的图像重建。