mlsanityData to 14 Oct 2026

Influence of Classification Task and Distribution Shift Type on OOD Detection in Fetal Ultrasound

arXiv 2509.18326 ↗First posted 22 Sep 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Reliable out-of-distribution (OOD) detection is important for safe deployment of deep learning models in fetal ultrasound amidst heterogeneous image characteristics and clinical settings. OOD detection relies on estimating a classification model's uncertainty, which should increase for OOD samples. While existing research has largely focused on uncertainty quantification methods, this work investigates the impact of the classification task itself. Through experiments with eight uncertainty quantification methods across four classification tasks, we demonstrate that OOD detection performance significantly varies with the task, and that the best task depends on the defined ID-OOD criteria; specifically, whether the OOD sample is due to: i) an image characteristic shift or ii) an anatomical feature shift. Furthermore, we reveal that superior OOD detection does not guarantee optimal abstained prediction, underscoring the necessity to align task selection and uncertainty strategies with the specific downstream application in medical image analysis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 28 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

18 of 28 references.

References · 18

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2019Learning Loss for Active Learningcited by 336
  5. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  6. 2015Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networkscited by 139
  7. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 104
  8. 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Taskscited by 78
  9. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 63
  10. 2023A Review of Uncertainty Estimation and its Application in Medical Imagingcited by 59
  11. 2023A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methodscited by 39
  12. 2021Confidence-based Out-of-Distribution Detection: A Comparative Study and Analysiscited by 34
6 more
  1. 2024Out-of-distribution Detection in Medical Image Analysis: A surveycited by 22
  2. 2023URL: A Representation Learning Benchmark for Transferable Uncertainty Estimatescited by 17
  3. 2021Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluationcited by 15
  4. 2022Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countriescited by 15
  5. 2023Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videoscited by 12
  6. 2022Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scorescited by 10

Built on by

Not cited yet.