Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
arXiv:2301.08525 · doi:10.1016/j.expneurol.2021.113608
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 (50)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Efficient Estimation of Word Representations in Vector Space
- Deep Learning in Neural Networks: An Overview
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- A Survey on Deep Learning in Medical Image Analysis
- Auto-Encoding Variational Bayes
- Distilling the Knowledge in a Neural Network
- Sequence to Sequence Learning with Neural Networks
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- TensorFlow: A system for large-scale machine learning
- Explaining and Harnessing Adversarial Examples
- Semi-Supervised Classification with Graph Convolutional Networks
- A Unified Approach to Interpreting Model Predictions
- Intriguing properties of neural networks
- Geometric deep learning: going beyond Euclidean data
- Axiomatic Attribution for Deep Networks
- Learning Important Features Through Propagating Activation Differences
- VoxelMorph: A Learning Framework for Deformable Medical Image Registration
- An overview of deep learning in medical imaging focusing on MRI
- Neural Architecture Search: A Survey
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- Understanding Black-box Predictions via Influence Functions
- Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Assessing and tuning brain decoders: cross-validation, caveats, and guidelines
- Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation
- Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease
- Deep Learning in Alzheimer's disease: Diagnostic Classification and Prognostic Prediction using Neuroimaging Data
- The Loss Surfaces of Multilayer Networks
- Visualizing the Loss Landscape of Neural Nets
- Sanity Checks for Saliency Maps
- Predicting Alzheimer's disease: a neuroimaging study with 3D convolutional neural networks
- "Why Should I Trust You?": Explaining the Predictions of Any Classifier
- Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification
- Learning how to explain neural networks: PatternNet and PatternAttribution
- Structural neuroimaging as clinical predictor: a review of machine learning applications
- Discovering Hidden Factors of Variation in Deep Networks
- Systematic Misestimation of Machine Learning Performance in Neuroimaging Studies of Depression
- TADPOLE Challenge: Prediction of Longitudinal Evolution in Alzheimer's Disease
- Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer's Disease
- Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects
- Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis
- Deep Learning for Neuroimaging-based Diagnosis and Rehabilitation of Autism Spectrum Disorder: A Review
- PHOTONAI -- A Python API for Rapid Machine Learning Model Development
- Towards Alzheimer's Disease Classification through Transfer Learning
- Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker
- Residual and Plain Convolutional Neural Networks for 3D Brain MRI Classification
- 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