Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

Abstract

By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first give an introduction into methodological key concepts and resulting methodological promises including representation and transfer learning, as well as modelling domain-specific priors. After reviewing recent applications within neuroimaging-based psychiatric research, such as the diagnosis of psychiatric diseases, delineation of disease subtypes, normative modeling, and the development of neuroimaging biomarkers, we discuss current challenges. This includes for example the difficulty of training models on small, heterogeneous and biased data sets, the lack of validity of clinical labels, algorithmic bias, and the influence of confounding variables.

References in corpus (18)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Distilling the Knowledge in a Neural Network
• Sequence to Sequence Learning with Neural Networks
• Explaining and Harnessing Adversarial Examples
• Semi-Supervised Classification with Graph Convolutional Networks
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• The Loss Surfaces of Multilayer Networks
• Predicting Alzheimer's disease: a neuroimaging study with 3D convolutional neural networks
• Discovering Hidden Factors of Variation in Deep Networks
• Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects
• Towards Alzheimer's Disease Classification through Transfer Learning
• Residual and Plain Convolutional Neural Networks for 3D Brain MRI Classification
• Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker
• NEURO-DRAM: a 3D recurrent visual attention model for interpretable neuroimaging classification
• Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction
• Harnessing spatial homogeneity of neuroimaging data: patch individual filter layers for CNNs