mlsanityData to 7 Oct 2026

Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models

arXiv 2211.06250 ↗First posted 11 Nov 2022eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Trusting the predictions of deep learning models in safety critical settings such as the medical domain is still not a viable option. Distentangled uncertainty quantification in the field of medical imaging has received little attention. In this paper, we study disentangled uncertainties in image to image translation tasks in the medical domain. We compare multiple uncertainty quantification methods, namely Ensembles, Flipout, Dropout, and DropConnect, while using CycleGAN to convert T1-weighted brain MRI scans to T2-weighted brain MRI scans. We further evaluate uncertainty behavior in the presence of out of distribution data (Brain CT and RGB Face Images), showing that epistemic uncertainty can be used to detect out of distribution inputs, which should increase reliability of model outputs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 48 references that are in the map. First posted on arXiv 11 Nov 2022.

Builds on

34 of 48 references.

References · 34

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  7. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  8. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  9. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  10. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 426
  11. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
  12. 2016Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentationcited by 263
22 more
  1. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  2. 2017Image De-raining Using a Conditional Generative Adversarial Networkcited by 197
  3. 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 161
  4. 2018MedGAN: Medical Image Translation using GANscited by 152
  5. 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
  6. 2015Brain Tumor Segmentation with Deep Neural Networkscited by 137
  7. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  8. 2019DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networkscited by 92
  9. 2017Deep MR to CT Synthesis using Unpaired Datacited by 86
  10. 2019A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Taskscited by 62
  11. 2019Unsupervised Medical Image Translation Using Cycle-MedGANcited by 44
  12. 2018Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentationcited by 36
  13. 2017Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolutioncited by 29
  14. 2019Intracranial Hemorrhage Segmentation Using Deep Convolutional Modelcited by 29
  15. 2018Dist-GAN: An Improved GAN using Distance Constraintscited by 26
  16. 2019Combining Noise-to-Image and Image-to-Image GANs: Brain MR Image Augmentation for Tumor Detectioncited by 23
  17. 2018Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNITcited by 18
  18. 2021Uncertainty-Guided Progressive GANs for Medical Image Translationcited by 16
  19. 2019Robust Super-Resolution GAN, with Manifold-based and Perception Losscited by 15
  20. 2019Unsupervised Adversarial Correction of Rigid MR Motion Artifactscited by 11
  21. 2021A Mixed-Supervision Multilevel GAN Framework for Image Quality Enhancementcited by 11
  22. 2021Uncertainty-aware Generalized Adaptive CycleGANcited by 3

Built on by

Not cited yet.