mlsanityData to 7 Oct 2026

Interpretable Diabetic Retinopathy Diagnosis based on Biomarker Activation Map

arXiv 2212.06299 ↗First posted 13 Dec 2022eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning classifiers provide the most accurate means of automatically diagnosing diabetic retinopathy (DR) based on optical coherence tomography (OCT) and its angiography (OCTA). The power of these models is attributable in part to the inclusion of hidden layers that provide the complexity required to achieve a desired task. However, hidden layers also render algorithm outputs difficult to interpret. Here we introduce a novel biomarker activation map (BAM) framework based on generative adversarial learning that allows clinicians to verify and understand classifiers decision-making. A data set including 456 macular scans were graded as non-referable or referable DR based on current clinical standards. A DR classifier that was used to evaluate our BAM was first trained based on this data set. The BAM generation framework was designed by combing two U-shaped generators to provide meaningful interpretability to this classifier. The main generator was trained to take referable scans as input and produce an output that would be classified by the classifier as non-referable. The BAM is then constructed as the difference image between the output and input of the main generator. To ensure that the BAM only highlights classifier-utilized biomarkers an assistant generator was trained to do the opposite, producing scans that would be classified as referable by the classifier from non-referable scans. The generated BAMs highlighted known pathologic features including nonperfusion area and retinal fluid. A fully interpretable classifier based on these highlights could help clinicians better utilize and verify automated DR diagnosis.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 94 references that are in the map. First posted on arXiv 13 Dec 2022.

Builds on

43 of 94 references.

References · 43

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  9. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  10. 2014Conditional Generative Adversarial Netscited by 2,152
  11. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  12. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
31 more
  1. 2018Sanity Checks for Saliency Mapscited by 1,149
  2. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  3. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  4. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  5. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  6. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  7. 2017Deep Learning for Medical Image Analysiscited by 399
  8. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  9. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 295
  10. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  11. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  12. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  13. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  14. 2014Object Detectors Emerge in Deep Scene CNNscited by 178
  15. 2018Tell Me Where to Look: Guided Attention Inference Networkcited by 168
  16. 2018Visual Interpretability for Deep Learning: a Surveycited by 155
  17. 2018Explaining Explanations in AIcited by 136
  18. 2017Interpreting Deep Visual Representations via Network Dissectioncited by 103
  19. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  20. 2021Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methodscited by 83
  21. 2019Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networkscited by 49
  22. 2017Visual Feature Attribution using Wasserstein GANscited by 47
  23. 2017Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathycited by 42
  24. 2018Understanding Individual Decisions of CNNs via Contrastive Backpropagationcited by 40
  25. 2019Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagationcited by 29
  26. 2020Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorizationcited by 23
  27. 2020Pseudo-healthy synthesis with pathology disentanglement and adversarial learningcited by 19
  28. 2019Transfer Learning for Automated OCTA Detection of Diabetic Retinopathycited by 8
  29. 2015Good Colour Maps: How to Design Themcited by 6
  30. 2020Automated segmentation of retinal fluid volumes from structural and angiographic optical coherence tomography using deep learningcited by 6
  31. 2020DcardNet: Diabetic Retinopathy Classification at Multiple Levels Based on Structural and Angiographic Optical Coherence Tomographycited by 3

Built on by

Not cited yet.