mlsanityData to 7 Oct 2026

Detecting when pre-trained nnU-Net models fail silently for Covid-19 lung lesion segmentation

arXiv 2107.05975 ↗First posted 13 Jul 2021eess.IV cs.CV cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Automatic segmentation of lung lesions in computer tomography has the potential to ease the burden of clinicians during the Covid-19 pandemic. Yet predictive deep learning models are not trusted in the clinical routine due to failing silently in out-of-distribution (OOD) data. We propose a lightweight OOD detection method that exploits the Mahalanobis distance in the feature space. The proposed approach can be seamlessly integrated into state-of-the-art segmentation pipelines without requiring changes in model architecture or training procedure, and can therefore be used to assess the suitability of pre-trained models to new data. We validate our method with a patch-based nnU-Net architecture trained with a multi-institutional dataset and find that it effectively detects samples that the model segments incorrectly.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 13 Jul 2021.

Builds on

19 of 28 references.

References · 19

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  10. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  11. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  12. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 281
7 more
  1. 2019Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentationcited by 162
  2. 2020MosMedData: Chest CT Scans With COVID-19 Related Findings Datasetcited by 103
  3. 2020Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertaintycited by 100
  4. 2019Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentationcited by 75
  5. 2019Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shiftcited by 54
  6. 2019Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effectscited by 40
  7. 2015Understanding Intra-Class Knowledge Inside CNNcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 3; 2024: 5; 2025: 1; 2026: 2.

19 papers.

Sort:

  1. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 62
  2. 2024ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentationcited by 25
  3. 2024Out-of-distribution Detection in Medical Image Analysis: A surveycited by 22
  4. 2022Efficient Bayesian Uncertainty Estimation for nnU-Netcited by 19
  5. 2022ECONet: Efficient Convolutional Online Likelihood Network for Scribble-based Interactive Segmentationcited by 11
  6. 2022A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentationcited by 11
  7. 2022Task-agnostic Continual Hippocampus Segmentation for Smooth Population Shiftscited by 6
  8. 2023Dimensionality Reduction for Improving Out-of-Distribution Detection in Medical Image Segmentationcited by 6
  9. 2022Improved post-hoc probability calibration for out-of-domain MRI segmentationcited by 5
  10. 2024Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantificationcited by 4
  11. 2023Adaptive Multi-scale Online Likelihood Network for AI-assisted Interactive Segmentationcited by 3
  12. 2024Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentationcited by 1
7 more
  1. 2024Dimensionality Reduction and Nearest Neighbors for Improving Out-of-Distribution Detection in Medical Image Segmentationcited by 1
  2. 2021Quality monitoring of federated Covid-19 lesion segmentationcited by 0
  3. 2022Identifying and Combating Bias in Segmentation Networks by leveraging multiple resolutionscited by 0
  4. 2023Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation taskcited by 0
  5. 2025Modality-Independent Explainable Detection of Inaccurate Organ Segmentations Using Denoising Autoencoderscited by 0
  6. 2026Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shiftcited by 0
  7. 2026Applications of Neural Cellular Automata: State of the Art, Challenges and Opportunitiescited by 0