mlsanityData to 7 Oct 2026

Anatomical and Diagnostic Bayesian Segmentation in Prostate MRI -Should Different Clinical Objectives Mandate Different Loss Functions?

arXiv 2110.12889 ↗First posted 25 Oct 2021eess.IV cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We hypothesize that probabilistic voxel-level classification of anatomy and malignancy in prostate MRI, although typically posed as near-identical segmentation tasks via U-Nets, require different loss functions for optimal performance due to inherent differences in their clinical objectives. We investigate distribution, region and boundary-based loss functions for both tasks across 200 patient exams from the publicly-available ProstateX dataset. For evaluation, we conduct a thorough comparative analysis of model predictions and calibration, measured with respect to multi-class volume segmentation of the prostate anatomy (whole-gland, transitional zone, peripheral zone), as well as, patient-level diagnosis and lesion-level detection of clinically significant prostate cancer. Notably, we find that distribution-based loss functions (in particular, focal loss) are well-suited for diagnostic or panoptic segmentation tasks such as lesion detection, primarily due to their implicit property of inducing better calibration. Meanwhile, (with the exception of focal loss) both distribution and region/boundary-based loss functions perform equally well for anatomical or semantic segmentation tasks, such as quantification of organ shape, size and boundaries.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 12 of its 37 references that are in the map. First posted on arXiv 25 Oct 2021.

Builds on

12 of 37 references.

References · 12

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  3. 2019On the Convergence of Adam and Beyondcited by 834
  4. 2018Panoptic Segmentationcited by 796
  5. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  6. 2020Calibrating Deep Neural Networks using Focal Losscited by 353
  7. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 281
  8. 2018Boundary loss for highly unbalanced segmentationcited by 187
  9. 2019Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentationcited by 162
  10. 2019Supervised Uncertainty Quantification for Segmentation with Multiple Annotationscited by 42
  11. 2021End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effects of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reductioncited by 32
  12. 2017Adversarial Networks for the Detection of Aggressive Prostate Cancercited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 2; 2024: 1.

4 papers.

  1. 2023Understanding metric-related pitfalls in image analysis validationcited by 57
  2. 2021Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomographycited by 8
  3. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  4. 2023Uncertainty-Aware Semi-Supervised Learning for Prostate MRI Zonal Segmentationcited by 0