mlsanityData to 7 Oct 2026

Applications of interpretable deep learning in neuroimaging: a comprehensive review

arXiv 2406.17792 ↗First posted 30 May 2024eess.IV cs.CV q-bio.NCcited by 3

Not on the map. Why?

Abstract (arXiv)

Clinical adoption of deep learning models has been hindered, in part, because the black-box nature of neural networks leads to concerns regarding their trustworthiness and reliability. These concerns are particularly relevant in the field of neuroimaging due to the complex brain phenotypes and inter-subject heterogeneity often encountered. The challenge can be addressed by interpretable deep learning (iDL) methods that enable the visualisation and interpretation of the inner workings of deep learning models. This study systematically reviewed the literature on neuroimaging applications of iDL methods and critically analysed how iDL explanation properties were evaluated. Seventy-five studies were included, and ten categories of iDL methods were identified. We also reviewed five properties of iDL explanations that were analysed in the included studies: biological validity, robustness, continuity, selectivity, and downstream task performance. We found that the most popular iDL approaches used in the literature may be sub-optimal for neuroimaging data, and we discussed possible future directions for the field.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 97 of its 162 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

97 of 162 references.

References · 97

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  7. 2016Densely Connected Convolutional Networkscited by 6,691
  8. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  9. 2022Generative Adversarial Networkscited by 5,603
  10. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  11. 2017Squeeze-and-Excitation Networkscited by 4,763
  12. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
38 more
  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  4. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  6. 2017Non-local Neural Networkscited by 2,290
  7. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  9. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  10. 2018Sanity Checks for Saliency Mapscited by 1,149
  11. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  12. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  13. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
  14. 2019Attention is not Explanationcited by 916
  15. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  16. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  17. 2017Dynamic Routing Between Capsulescited by 689
  18. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  19. 2013Network In Networkcited by 600
  20. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  21. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  22. 2019Is Attention Interpretable?cited by 387
  23. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
  24. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  25. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  26. 2017The (Un)reliability of saliency methodscited by 331
  27. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
  28. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  29. 2022Diffusion Models for Medical Anomaly Detectioncited by 231
  30. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  31. 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 202
  32. 2019Causality matters in medical imagingcited by 193
  33. 2017The Shattered Gradients Problem: If resnets are the answer, then what is the question?cited by 156
  34. 2018Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networkscited by 146
  35. 2020Explainable deep learning models in medical image analysiscited by 111
  36. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  37. 2020CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentationcited by 79
  38. 2019Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networkscited by 65

50 most cited of 97 All 97 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Guidelines For The Choice Of The Baseline in XAI Attribution Methodscited by 1
  2. 2025X-SiT: Inherently Interpretable Surface Vision Transformers for Dementia Diagnosiscited by 1
  3. 2025Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identificationcited by 0