mlsanityData to 14 Oct 2026

Redesigning Out-of-Distribution Detection on 3D Medical Images

arXiv 2308.07324 ↗First posted 7 Aug 2023eess.IV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Detecting out-of-distribution (OOD) samples for trusted medical image segmentation remains a significant challenge. The critical issue here is the lack of a strict definition of abnormal data, which often results in artificial problem settings without measurable clinical impact. In this paper, we redesign the OOD detection problem according to the specifics of volumetric medical imaging and related downstream tasks (e.g., segmentation). We propose using the downstream model's performance as a pseudometric between images to define abnormal samples. This approach enables us to weigh different samples based on their performance impact without an explicit ID/OOD distinction. We incorporate this weighting in a new metric called Expected Performance Drop (EPD). EPD is our core contribution to the new problem design, allowing us to rank methods based on their clinical impact. We demonstrate the effectiveness of EPD-based evaluation in 11 CT and MRI OOD detection challenges.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 15 of its 26 references that are in the map. First posted on arXiv 7 Aug 2023.

Builds on

15 of 26 references.

References · 15

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  4. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  5. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  6. 2017Selective Classification for Deep Neural Networkscited by 852
  7. 2019The Liver Tumor Segmentation Benchmark (LiTS)cited by 509
  8. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  9. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  10. 2020A Benchmark of Medical Out of Distribution Detectioncited by 40
  11. 2020Multiscale Score Matching for Out-of-Distribution Detectioncited by 36
  12. 2022Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantitiescited by 23
3 more
  1. 2022ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRIcited by 12
  2. 2023Limitations of Out-of-Distribution Detection in 3D Medical Image Segmentationcited by 11
  3. 2022Improving Uncertainty-based Out-of-Distribution Detection for Medical Image Segmentationcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2.

3 papers.

  1. 2023Segment Every Out-of-Distribution Objectcited by 21
  2. 2024Comparative Benchmarking of Failure Detection Methods in Medical Image Segmentation: Unveiling the Role of Confidence Aggregationcited by 12
  3. 2024Robustness Testing of Black-Box Models Against CT Degradation Through Test-Time Augmentationcited by 1