Deep learning in neuroimaging data analysis: Applications, challenges, and solutions

Abstract

Methods for the analysis of neuroimaging data have advanced significantly since the beginning of neuroscience as a scientific discipline. Today, sophisticated statistical procedures allow us to examine complex multivariate patterns, however most of them are still constrained by assuming inherent linearity of neural processes. Here, we discuss a group of machine learning methods, called deep learning, which have drawn much attention in and outside the field of neuroscience in recent years and hold the potential to surpass the mentioned limitations. Firstly, we describe and explain the essential concepts in deep learning: the structure and the computational operations that allow deep models to learn. After that, we move to the most common applications of deep learning in neuroimaging data analysis: prediction of outcome, interpretation of internal representations, generation of synthetic data and segmentation. In the next section we present issues that deep learning poses, which concerns multidimensionality and multimodality of data, overfitting and computational cost, and propose possible solutions. Lastly, we discuss the current reach of DL usage in all the common applications in neuroimaging data analysis, where we consider the promise of multimodality, capability of processing raw data, and advanced visualization strategies. We identify research gaps, such as focusing on a limited number of criterion variables and the lack of a well-defined strategy for choosing architecture and hyperparameters. Furthermore, we talk about the possibility of conducting research with constructs that have been ignored so far or/and moving toward frameworks, such as RDoC, the potential of transfer learning and generation of synthetic data.

Dense attention network identifies EEG abnormalities during working memory performance of patients with schizophrenia

“…Furthermore, the two highest peaks in The DAN attention value vector were found to overlap with the significant main effect of group found in time-frequency ROIs in the alpha band during task preparation and memory retrieval phases. Based on this congruence, we can conclude with high confidence ( 81 ) that the DAN model’s decision to classify subjects as patients or controls is based on the same aspects of the data that were revealed by the time-frequency analysis. Given that the detected abnormalities are oscillatory in nature and the DAN algorithm partially operates by convolution ( 82 ), it might have been specially suited to detect oscillatory signatures in the EEG.…”

Unveiling the neurotechnology landscape. Scientific advancements innovations and major trends

“…Deep learning neuroimaging is the ability to learn highly complex and non-linear patterns from neuroimaging data (see e.g. Avberšek and Repovš, 2022, for a survey). Cognitive neuroscience aims to understand how the brain functions and achieves performance, by studying the biological processes that underlie human cognition, especially through the relation between brain structures, activity, and cognitive functions (see e.g.…”

Task-guided Generative Adversarial Networks for Synthesizing and Augmenting Structural Connectivity Matrices for Connectivity-Based Prediction

“…However, such manipulations are inapplicable to the matrix-shaped data of brain functional and structural connectivity because their shape was constrained by the order of brain regions. In recent years, data augmentation methods using generative models have been proposed [11], [12], [13], [14], [15], [16], [17]. In these methods, generative augmentation models approximate the distribution of a given dataset and synthesize new samples with similar characteristics to the original dataset.…”