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

arXiv: https://arxiv.org/abs/2107.05975 · HTML: https://mlsanity.com/paper/2107.05975/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 13 Jul 2021.

## Builds on (most cited first, 19 of 19)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation](https://mlsanity.com/paper/1911.13273/) (2019)
- [MosMedData: Chest CT Scans With COVID-19 Related Findings Dataset](https://mlsanity.com/paper/2005.06465/) (2020)
- [Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty](https://mlsanity.com/paper/2006.06015/) (2020)
- [Assessing Reliability and Challenges of Uncertainty Estimations for Medical Image Segmentation](https://mlsanity.com/paper/1907.03338/) (2019)
- [Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift](https://mlsanity.com/paper/1908.01098/) (2019)
- [Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects](https://mlsanity.com/paper/1910.04597/) (2019)
- [Understanding Intra-Class Knowledge Inside CNN](https://mlsanity.com/paper/1507.02379/) (2015)

## Built on by (most cited first, 19 of 19)

- [Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis](https://mlsanity.com/paper/2210.03736/) (2022)
- [ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation](https://mlsanity.com/paper/2401.08501/) (2024)
- [Out-of-distribution Detection in Medical Image Analysis: A survey](https://mlsanity.com/paper/2404.18279/) (2024)
- [Efficient Bayesian Uncertainty Estimation for nnU-Net](https://mlsanity.com/paper/2212.06278/) (2022)
- [ECONet: Efficient Convolutional Online Likelihood Network for Scribble-based Interactive Segmentation](https://mlsanity.com/paper/2201.04584/) (2022)
- [A Dempster-Shafer approach to trustworthy AI with application to fetal brain MRI segmentation](https://mlsanity.com/paper/2204.02779/) (2022)
- [Task-agnostic Continual Hippocampus Segmentation for Smooth Population Shifts](https://mlsanity.com/paper/2208.03206/) (2022)
- [Dimensionality Reduction for Improving Out-of-Distribution Detection in Medical Image Segmentation](https://mlsanity.com/paper/2308.03723/) (2023)
- [Improved post-hoc probability calibration for out-of-domain MRI segmentation](https://mlsanity.com/paper/2208.02870/) (2022)
- [Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification](https://mlsanity.com/paper/2411.07097/) (2024)
- [Adaptive Multi-scale Online Likelihood Network for AI-assisted Interactive Segmentation](https://mlsanity.com/paper/2303.13696/) (2023)
- [Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation](https://mlsanity.com/paper/2403.02311/) (2024)
- [Dimensionality Reduction and Nearest Neighbors for Improving Out-of-Distribution Detection in Medical Image Segmentation](https://mlsanity.com/paper/2408.02761/) (2024)
- [Quality monitoring of federated Covid-19 lesion segmentation](https://mlsanity.com/paper/2112.08974/) (2021)
- [Identifying and Combating Bias in Segmentation Networks by leveraging multiple resolutions](https://mlsanity.com/paper/2206.14919/) (2022)
- [Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation task](https://mlsanity.com/paper/2309.06807/) (2023)
- [Modality-Independent Explainable Detection of Inaccurate Organ Segmentations Using Denoising Autoencoders](https://mlsanity.com/paper/2504.12203/) (2025)
- [Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shift](https://mlsanity.com/paper/2608.18193/) (2026)
- [Applications of Neural Cellular Automata: State of the Art, Challenges and Opportunities](https://mlsanity.com/paper/2609.24595/) (2026)

## 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.