mlsanityData to 14 Oct 2026

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

arXiv 2301.08525 ↗First posted 20 Jan 2023cs.LG eess.IV q-bio.NCcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 74 of its 289 references that are in the map. First posted on arXiv 20 Jan 2023.

Builds on

74 of 289 references.

References · 74

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  8. 2016Densely Connected Convolutional Networkscited by 6,720
  9. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  10. 2013Intriguing properties of neural networkscited by 5,155
  11. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  12. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
38 more
  1. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  2. 2014Going Deeper with Convolutionscited by 4,241
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  9. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  10. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  11. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  12. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  13. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  14. 2018Sanity Checks for Saliency Mapscited by 1,156
  15. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
  16. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  17. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  18. 2014Deep Learning in Neural Networks: An Overviewcited by 770
  19. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 662
  20. 2018A Survey on Deep Transfer Learningcited by 419
  21. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  22. 2014The Loss Surfaces of Multilayer Networkscited by 280
  23. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  24. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 222
  25. 2016Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Predictioncited by 217
  26. 2018Universality of Deep Convolutional Neural Networkscited by 176
  27. 2018An overview of deep learning in medical imaging focusing on MRIcited by 140
  28. 2016Unsupervised domain adaptation in brain lesion segmentation with adversarial networkscited by 125
  29. 2019Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluationcited by 107
  30. 2018Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Diseasecited by 99
  31. 2015A Deeper Look at Dataset Biascited by 87
  32. 2017Learning how to explain neural networks: PatternNet and PatternAttributioncited by 84
  33. 2016Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarkercited by 72
  34. 2017Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentationcited by 66
  35. 2017Towards better understanding of gradient-based attribution methods for Deep Neural Networkscited by 54
  36. 2017Residual and Plain Convolutional Neural Networks for 3D Brain MRI Classificationcited by 48
  37. 2017Cross-validation failure: small sample sizes lead to large error barscited by 43
  38. 2019Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effectscited by 43

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 1; 2026: 1.

4 papers.

  1. 2024Machine Learning and Theory Ladenness -- A Phenomenological Accountcited by 3
  2. 2023DeepRepViz: Identifying Confounders in Deep Learning Model Predictionscited by 2
  3. 2025Learning from Heterogeneous Structural MRI via Collaborative Domain Adaptation for Late-Life Depression Assessmentcited by 0
  4. 2026ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely oncited by 0