Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) approaches for brain imaging data analysis. However, their conclusions are often based on pre-engineered features depriving DL of its main advantage — representation learning. We conduct a large-scale systematic comparison profiled in multiple classification and regression tasks on structural MRI images and show the importance of representation learning for DL. Results show that if trained following prevalent DL practices, DL methods have the potential to scale particularly well and substantially improve compared to SML methods, while also presenting a lower asymptotic complexity in relative computational time, despite being more complex. We also demonstrate that DL embeddings span comprehensible task-specific projection spectra and that DL consistently localizes task-discriminative brain biomarkers. Our findings highlight the presence of nonlinearities in neuroimaging data that DL can exploit to generate superior task-discriminative representations for characterizing the human brain.

最近的批判性评论不利地将深度学习（DL）与标准机器学习（SML）方法进行了脑成像数据分析。但是，他们的结论通常基于预先设计的功能，这剥夺了DL的主要优势-表示学习。我们在结构MRI图像上的多个分类和回归任务中进行了大规模的系统比较，并显示了学习学习对DL的重要性。结果表明，如果按照流行的DL习惯进行训练，与SML方法相比，DL方法具有特别好地扩展和显着改善的潜力，尽管相对更为复杂，但在相对的计算时间上也呈现出较低的渐近复杂性。我们还证明了DL嵌入跨越了可理解的特定于任务的投影光谱，并且DL始终位于可区分任务的大脑生物标记物上。我们的发现凸显了DL可以利用其在神经影像数据中存在非线性，从而生成用于区分人脑的出色任务区分性表示形式。