000278930 001__ 278930
000278930 005__ 20250615001322.0
000278930 0247_ $$2doi$$a10.1016/j.media.2025.103623
000278930 0247_ $$2pmid$$apmid:40367700
000278930 0247_ $$2ISSN$$a1361-8415
000278930 0247_ $$2ISSN$$a1361-8431
000278930 0247_ $$2ISSN$$a1361-8423
000278930 0247_ $$2altmetric$$aaltmetric:158519381
000278930 037__ $$aDZNE-2025-00656
000278930 041__ $$aEnglish
000278930 082__ $$a610
000278930 1001_ $$aChatterjee, Soumick$$b0
000278930 245__ $$aPULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation.
000278930 260__ $$aAmsterdam [u.a.]$$bElsevier Science$$c2025
000278930 3367_ $$2DRIVER$$aarticle
000278930 3367_ $$2DataCite$$aOutput Types/Journal article
000278930 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1749737217_19459
000278930 3367_ $$2BibTeX$$aARTICLE
000278930 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000278930 3367_ $$00$$2EndNote$$aJournal Article
000278930 520__ $$aIn 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.
000278930 536__ $$0G:(DE-HGF)POF4-353$$a353 - Clinical and Health Care Research (POF4-353)$$cPOF4-353$$fPOF IV$$x0
000278930 588__ $$aDataset connected to CrossRef, PubMed, , Journals: pub.dzne.de
000278930 650_7 $$2Other$$aConditional VAE
000278930 650_7 $$2Other$$aDistribution distance
000278930 650_7 $$2Other$$aMultiple sclerosis segmentation
000278930 650_7 $$2Other$$aProbabilistic UNet
000278930 650_7 $$2Other$$aVessel segmentation
000278930 650_2 $$2MeSH$$aHumans
000278930 650_2 $$2MeSH$$aObserver Variation
000278930 650_2 $$2MeSH$$aMagnetic Resonance Imaging: methods
000278930 650_2 $$2MeSH$$aAlgorithms
000278930 650_2 $$2MeSH$$aImage Interpretation, Computer-Assisted: methods
000278930 650_2 $$2MeSH$$aMultiple Sclerosis: diagnostic imaging
000278930 650_2 $$2MeSH$$aSupervised Machine Learning
000278930 7001_ $$aGaidzik, Franziska$$b1
000278930 7001_ $$aSciarra, Alessandro$$b2
000278930 7001_ $$0P:(DE-2719)9002178$$aMattern, Hendrik$$b3$$udzne
000278930 7001_ $$aJaniga, Gábor$$b4
000278930 7001_ $$0P:(DE-2719)2810706$$aSpeck, Oliver$$b5$$udzne
000278930 7001_ $$0P:(DE-HGF)0$$aNürnberger, Andreas$$b6
000278930 7001_ $$aPathiraja, Sahani$$b7
000278930 773__ $$0PERI:(DE-600)1497450-2$$a10.1016/j.media.2025.103623$$gVol. 103, p. 103623 -$$p103623$$tMedical image analysis$$v103$$x1361-8415$$y2025
000278930 8564_ $$uhttps://pub.dzne.de/record/278930/files/DZNE-2025-00656%20SUP.pdf
000278930 8564_ $$uhttps://pub.dzne.de/record/278930/files/DZNE-2025-00656_Restricted.pdf
000278930 8564_ $$uhttps://pub.dzne.de/record/278930/files/DZNE-2025-00656%20SUP.pdf?subformat=pdfa$$xpdfa
000278930 8564_ $$uhttps://pub.dzne.de/record/278930/files/DZNE-2025-00656_Restricted.pdf?subformat=pdfa$$xpdfa
000278930 909CO $$ooai:pub.dzne.de:278930$$pVDB
000278930 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9002178$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b3$$kDZNE
000278930 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2810706$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b5$$kDZNE
000278930 9101_ $$0I:(DE-588)1065079516$$6P:(DE-HGF)0$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b6$$kDZNE
000278930 9131_ $$0G:(DE-HGF)POF4-353$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vClinical and Health Care Research$$x0
000278930 9141_ $$y2025
000278930 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bMED IMAGE ANAL : 2022$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-02
000278930 915__ $$0StatID:(DE-HGF)9910$$2StatID$$aIF >= 10$$bMED IMAGE ANAL : 2022$$d2025-01-02
000278930 9201_ $$0I:(DE-2719)1310010$$kAG Schreiber$$lMixed Cerebral Pathologies and Cognitive Aging$$x0
000278930 9201_ $$0I:(DE-2719)1340009$$kAG Speck$$lLinking Imaging Projects$$x1
000278930 980__ $$ajournal
000278930 980__ $$aVDB
000278930 980__ $$aI:(DE-2719)1310010
000278930 980__ $$aI:(DE-2719)1340009
000278930 980__ $$aUNRESTRICTED