MedUncertainty

Uncertainty in Medical Image Analysis

Benchmarks

• QUBIQ
• BraTS 2020 Task 3

Uncertainty Estimation Methods

|DATE|First Author|Title|Publication| |---|---|------------|---| |20200624|Florian Wenzel|Hyperparameter Ensembles for Robustness and Uncertainty Quantification (arxiv)|TBA| |20200610|Miguel Monteiro|Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty (arxiv) (pytorch)|TBA| |20191001|Charles Corbière|Addressing Failure Prediction by Learning Model Confidence (arxiv) (pytorch)|NeurlPS 2019| |20190821|Janis Postels|Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation (arxiv) (keras)|ICCV 2019| |20190725|Zach Eaton-Rosen|As easy as 1, 2... 4? Uncertainty in counting tasks for medical imaging (arxiv)|MICCAI 2019| |201906|Fredrik K. Gustafsson|Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision (arxiv) (project)|TBD| |20190606|Yaniv Ovadia|Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift (arxiv)|NeurlPS 2019| |201905|Simon Kohl|A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities (arxiv)|TBD| |201806|Zach Eaton-Rosen|Towards safe deep learning: accurately quantifying biomarker uncertainty in neural network predictions (arxiv)|MICCAI 2018| |201806|Simon Kohl|A Probabilistic U-Net for Segmentation of Ambiguous Images (arxiv) (spotlight) (tf) (re-pytorch) (YouTube)|NeurIPS 2018| |201703|Alex Kendall|What uncertainties do we need in Bayesian deep learning for computer vision? (arxiv)|NeurIPS 2017| |201612|Balaji Lakshminarayanan|Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (arxiv)|NeurIPS 2017| |20161201|Christian Rupprecht|(M-Heads) Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses (arxiv)|ICCV 2017| |201511|Alex Kendall|Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding (arxiv)| |201506|Yarin Gal|Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning (arxiv)|PMLR|

Uncertainty in Medical Image Analysis

|DATE|First Author|Title|Publication| |---|---|-------|---| |20200627|Yingda Xia|Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation|MedIA| |201909|Yuta Hiasa|Automated Muscle Segmentation from Clinical CT using Bayesian U-Net for Personalized Musculoskeletal Modeling|TMI| |20190728|Yongchan Kwon|Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation|Computational Statistics & Data Analysis| |20190715|Davood Karimi|Accurate and robust deep learning-based segmentation of the prostate clinical target volume in ultrasound images|Medical Image Analysis| |20190707|Alain Jungo|Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentation (arxiv) (pytorch)|MICCAI 2019| |20190703|Shi Hu|Supervised Uncertainty Quantification for Segmentation with Multiple Annotations (arxiv)|MICCAI 2019| |20190618|Florin C. Ghesu|Quantifying and Leveraging Classification Uncertainty for Chest Radiograph Assessment (arxiv) |MICCAI 2019| |20190607|Christian F. Baumgartner|PHiSeg: Capturing Uncertainty in Medical Image Segmentation (arxiv) (code)|MICCAI 2019| |20190605|Roger D. Soberanis-Mukul|An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation (arxiv)|TBD| |20190529|Philipp Seeböck|Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT (arxiv)|TMI| |20190529|Maithra Raghu|Direct Uncertainty Prediction for Medical Second Opinions (arxiv) (blog)|ICML 2019| |20190522|Rohit Jena|A Bayesian Neural Net to Segment Images with Uncertainty Estimates and Good Calibration|IPMI 2019| |201903|Huitong Pan|Prostate Segmentation from 3D MRI Using a Two-Stage Model and Variable-Input Based Uncertainty Measure (arxiv) |ISBI 2019| |201902|Guotai wang|Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks|Neurocomputing| |201901|José Ignacio Orlando|U2-Net: A Bayesian U-Net model with epistemic uncertainty feedback for photoreceptor layer segmentation in pathological OCT scans (arxiv) (Talk Slides)|ISBI 2019| |20180826|Leo Joskowicz|Automatic segmentation variability estimation with segmentation priors (Talk Slides)|Medical Image Analysis| |20180803|Tanya Nair|Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation (arxiv) (tf) (Talk slides) (YouTube)|MICCAI 2018 & Medical Image Analysis| |201807|Terrance DeVries|Leveraging Uncertainty Estimates for Predicting Segmentation Quality (arxiv)|TBD| |201806|[Felix Bragman](https://scholar.google.com/citations?use