Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment.
Anatomically interpretable deep learning of brain age captures domain-specific cognitive impairment.
复制标题
解剖学上可解释的脑年龄深度学习捕捉了特定领域的认知障碍。
DOI：
10.1073/pnas.2214634120
复制
发表时间：
2023-01-10
影响因子：
11.1
通讯作者：
Irimia, Andrei
中科院分区：
文献类型：
--
作者：
Yin, Chenzhong;Imms, Phoebe;Cheng, Mingxi;Amgalan, Anar;Chowdhury, Nahian F.;Massett, Roy J.;Chaudhari, Nikhil N.;Chen, Xinghe;Thompson, Paul M.;Bogdan, Paul;Irimia, Andrei
通过解剖磁共振图像的深度学习揭示的人类大脑的表型年龄反映了与认知衰退相关的结构变化模式。我们的可解释深度学习估计大脑年龄比迄今为止的任何其他方法都更准确。此外，与实足年龄相比，我们推断的大脑年龄与阿尔茨海默病的早期症状有更强的相关性。表达每个大脑区域对估计大脑年龄的重要性的地图揭示了男性和女性之间以及有认知障碍和无认知障碍的人之间神经衰老模式的差异。这些发现为早期识别阿尔茨海默病高风险人群提供了见解。根据磁共振成像（MRI）估计的实足年龄（CA）和生物脑年龄之间的差距反映了神经解剖学衰老的个体模式如何偏离其典型轨迹。MRI衍生的大脑年龄（BA）估计通常使用深度学习模型获得，这些模型在新数据上的表现可能相对较差，或者缺乏神经解剖学的可解释性。这项研究引入了一种卷积神经网络（CNN），在对4，681名认知正常（CN）参与者的MRI进行训练并对来自独立样本的1，170名CN参与者进行测试后估计BA。BA估计误差明显低于以往的研究。在个体和队列水平上，CNN提供了大脑老化模式的详细解剖图，揭示了轻度认知障碍（MCI，N = 351）和阿尔茨海默病（AD，N = 359）成年人的性别二态性和神经认知轨迹。 在MCI患者中（其中54%在MRI采集后10.9年内被诊断为痴呆），BA在捕获痴呆症状严重程度、功能障碍和执行功能方面明显优于CA。大脑老化中的性别二态性和偏侧化特征也映射到反映认知衰退的神经解剖学变化模式上。BA和神经认知测量之间的显着关联表明，所提出的框架可以映射，系统地，CN个人和MCI或AD参与者中与年龄相关的神经解剖学变化之间的关系。早期识别这种神经解剖学变化可以帮助根据AD风险筛选个体。
The phenotypic age of the human brain, as revealed via deep learning of anatomic magnetic resonance images, reflects patterns of structural change related to cognitive decline. Our interpretable deep learning estimates that the brain ages more accurately than any other approaches to date. Furthermore, compared to chronological age, our inferred brain ages are significantly more strongly associated with early signs of Alzheimer’s disease. Maps conveying the importance of each brain region for estimating brain age reveal differences in patterns of neurological aging between males and females and between persons with and without cognitive impairment. These findings provide insight into early identification of persons at high risk of Alzheimer’s disease. The gap between chronological age (CA) and biological brain age, as estimated from magnetic resonance images (MRIs), reflects how individual patterns of neuroanatomic aging deviate from their typical trajectories. MRI-derived brain age (BA) estimates are often obtained using deep learning models that may perform relatively poorly on new data or that lack neuroanatomic interpretability. This study introduces a convolutional neural network (CNN) to estimate BA after training on the MRIs of 4,681 cognitively normal (CN) participants and testing on 1,170 CN participants from an independent sample. BA estimation errors are notably lower than those of previous studies. At both individual and cohort levels, the CNN provides detailed anatomic maps of brain aging patterns that reveal sex dimorphisms and neurocognitive trajectories in adults with mild cognitive impairment (MCI, N = 351) and Alzheimer’s disease (AD, N = 359). In individuals with MCI (54% of whom were diagnosed with dementia within 10.9 y from MRI acquisition), BA is significantly better than CA in capturing dementia symptom severity, functional disability, and executive function. Profiles of sex dimorphism and lateralization in brain aging also map onto patterns of neuroanatomic change that reflect cognitive decline. Significant associations between BA and neurocognitive measures suggest that the proposed framework can map, systematically, the relationship between aging-related neuroanatomy changes in CN individuals and in participants with MCI or AD. Early identification of such neuroanatomy changes can help to screen individuals according to their AD risk.
登录
查看更多内容
DOI：
10.1523/jneurosci.2180-11.2011
发表时间：
2011-08-10
期刊：
The Journal of neuroscience : the official journal of the Society for Neuroscience
影响因子：
--
作者：
Glasser MF;Van Essen DC
通讯作者：
Van Essen DC
影响因子：
4.2
作者：
Biondo, Francesca;Jewell, Amelia;Pritchard, Megan;Aarsland, Dag;Steves, Claire J.;Mueller, Christoph;Cole, James H.
通讯作者：
Cole, James H.
DOI：
10.1016/j.compmedimag.2021.101939
发表时间：
2021-06-01
影响因子：
5.7
作者：
Besson, Pierre;Parrish, Todd;Bandt, S. Kathleen
通讯作者：
Bandt, S. Kathleen
DOI：
10.1111/j.2517-6161.1995.tb02031.x
发表时间：
1995-01-01
影响因子：
5.8
作者：
BENJAMINI, Y;HOCHBERG, Y
通讯作者：
HOCHBERG, Y
影响因子：
5.7
作者：
Fischl, Bruce
通讯作者：
Fischl, Bruce