Generalized Probabilistic U-Net for medical image segementation

Ishaan Bhat, Josien P. W. Pluim, Hugo J. Kuijf
7/26/2022
cs.CVcs.LG

Official code: ishaanb92/GeneralizedProbabilisticUNet (16 stars, MIT, last commit 2024-03-13).

Abstract

We propose the Generalized Probabilistic U-Net, which extends the Probabilistic U-Net by allowing more general forms of the Gaussian distribution as the latent space distribution that can better approximate the uncertainty in the reference segmentations. We study the effect the choice of latent space distribution has on capturing the uncertainty in the reference segmentations using the LIDC-IDRI dataset. We show that the choice of distribution affects the sample diversity of the predictions and their overlap with respect to the reference segmentations. For the LIDC-IDRI dataset, we show that using a mixture of Gaussians results in a statistically significant improvement in the generalized energy distance (GED) metric with respect to the standard Probabilistic U-Net. We have made our implementation available at https://github.com/ishaanb92/GeneralizedProbabilisticUNet

View on arXivView PDF

Code Implementations(1)

ishaanb92/GeneralizedProbabilisticUNetOfficial100%
MIT

PyTorch model for the Generalized Probabilistic U-Net. For more details see: https://www.melba-journal.org/papers/2023:005.html

169PythonMay 19, 20222 years agoMIT

Similar Papers

Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging

86% match2023

Effect of latent space distribution on the segmentation of images with multiple annotations

86% match1 repo162023

Robust Conformal Volume Estimation in 3D Medical Images

83% match1 repo52024

On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation

83% match2023

Uncertainty-Error correlations in Evidential Deep Learning models for biomedical segmentation

82% match2024

Banach Wasserstein GAN

82% match1 repo312018

Cite this paper

@article{bhat2022generalized,
  title  = {Generalized Probabilistic U-Net for medical image segementation},
  author = {Ishaan Bhat and Josien P. W. Pluim and Hugo J. Kuijf},
  year   = {2022},
  eprint = {2207.12872},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.12872v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.12872.svg)](https://codeofpaper.com/paper/2207.12872)

Discussion