arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.04362cs.CVcs.LGstat.ML
收藏

一种基于结构脑图像的年龄预测的领域引导CNN结构

A Domain Guided CNN Architecture for Predicting Age from Structural Brain Images

University of Michigan(密歇根大学)

Pascal Sturmfels, Saige Rutherford, Mike Angstadt, Mark Peterson, Chandra Sripada, Jenna Wiens

摘要:

鉴于卷积神经网络(CNN)应用于自然图像的广泛成功,研究人员已经开始将其应用于神经成像数据。然而,迄今为止,对针对神经成像数据定制的新型CNN架构的探索受到限制。最近的几项工作未能利用大脑的3D结构,而是将大脑视为一组独立的2D切片。利用3D卷积的方法依赖于为自然2D图像中的对象识别任务开发的架构。这种架构对神经成像可能不适用的输入做出假设。例如,现有的架构假设大脑中的模式表现出平移不变性。然而,大脑中的模式可能具有不同的含义,这取决于它在大脑中的位置。有必要探索适合大脑图像的新架构。我们提出了两个简单的修改现有的CNN架构的基础上,大脑图像结构。应用于大脑年龄预测任务,我们的网络实现了1.4年的平均绝对误差(MAE),并且比CNN基线训练速度快30%,达到了1.6年的MAE。我们的研究结果表明,从自然图像开发模型中吸取的经验教训可能不会直接转移到神经成像任务中。相反,在这一领域的模式发展方面仍有大量未探索的问题,其答案可能与传统智慧不同。

英文摘要:

Given the wide success of convolutional neural networks (CNNs) applied to natural images, researchers have begun to apply them to neuroimaging data. To date, however, exploration of novel CNN architectures tailored to neuroimaging data has been limited. Several recent works fail to leverage the 3D structure of the brain, instead treating the brain as a set of independent 2D slices. Approaches that do utilize 3D convolutions rely on architectures developed for object recognition tasks in natural 2D images. Such architectures make assumptions about the input that may not hold for neuroimaging. For example, existing architectures assume that patterns in the brain exhibit translation invariance. However, a pattern in the brain may have different meaning depending on where in the brain it is located. There is a need to explore novel architectures that are tailored to brain images. We present two simple modifications to existing CNN architectures based on brain image structure. Applied to the task of brain age prediction, our network achieves a mean absolute error (MAE) of 1.4 years and trains 30% faster than a CNN baseline that achieves a MAE of 1.6 years. Our results suggest that lessons learned from developing models on natural images may not directly transfer to neuroimaging tasks. Instead, there remains a large space of unexplored questions regarding model development in this area, whose answers may differ from conventional wisdom.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑