% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Chatterjee:278930,
author = {Chatterjee, Soumick and Gaidzik, Franziska and Sciarra,
Alessandro and Mattern, Hendrik and Janiga, Gábor and
Speck, Oliver and Nürnberger, Andreas and Pathiraja,
Sahani},
title = {{PULAS}ki: {L}earning inter-rater variability using
statistical distances to improve probabilistic
segmentation.},
journal = {Medical image analysis},
volume = {103},
issn = {1361-8415},
address = {Amsterdam [u.a.]},
publisher = {Elsevier Science},
reportid = {DZNE-2025-00656},
pages = {103623},
year = {2025},
abstract = {In the domain of medical imaging, many supervised learning
based methods for segmentation face several challenges such
as high variability in annotations from multiple experts,
paucity of labelled data and class imbalanced datasets.
These issues may result in segmentations that lack the
requisite precision for clinical analysis and can be
misleadingly overconfident without associated uncertainty
quantification. This work proposes the PULASki method as a
computationally efficient generative tool for biomedical
image segmentation that accurately captures variability in
expert annotations, even in small datasets. This approach
makes use of an improved loss function based on statistical
distances in a conditional variational autoencoder structure
(Probabilistic UNet) , which improves learning of the
conditional decoder compared to the standard cross-entropy
particularly in class imbalanced problems. The proposed
method was analysed for two structurally different
segmentation tasks (intracranial vessel and multiple
sclerosis (MS) lesion) and compare our results to four
well-established baselines in terms of quantitative metrics
and qualitative output. These experiments involve
class-imbalanced datasets characterised by challenging
features, including suboptimal signal-to-noise ratios and
high ambiguity. Empirical results demonstrate the PULASKi
method outperforms all baselines at the $5\%$ significance
level. Our experiments are also of the first to present a
comparative study of the computationally feasible
segmentation of complex geometries using 3D patches and the
traditional use of 2D slices. The generated segmentations
are shown to be much more anatomically plausible than in the
2D case, particularly for the vessel task. Our method can
also be applied to a wide range of multi-label segmentation
tasks and is useful for downstream tasks such as hemodynamic
modelling (computational fluid dynamics and data
assimilation), clinical decision making, and treatment
planning.},
keywords = {Humans / Observer Variation / Magnetic Resonance Imaging:
methods / Algorithms / Image Interpretation,
Computer-Assisted: methods / Multiple Sclerosis: diagnostic
imaging / Supervised Machine Learning / Conditional VAE
(Other) / Distribution distance (Other) / Multiple sclerosis
segmentation (Other) / Probabilistic UNet (Other) / Vessel
segmentation (Other)},
cin = {AG Schreiber / AG Speck},
ddc = {610},
cid = {I:(DE-2719)1310010 / I:(DE-2719)1340009},
pnm = {353 - Clinical and Health Care Research (POF4-353)},
pid = {G:(DE-HGF)POF4-353},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:40367700},
doi = {10.1016/j.media.2025.103623},
url = {https://pub.dzne.de/record/278930},
}