Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Zepf, Kilian"'
We address the selection and evaluation of uncertain segmentation methods in medical imaging and present two case studies: prostate segmentation, illustrating that for minimal annotator variation simple deterministic models can suffice, and lung lesi
Externí odkaz:
http://arxiv.org/abs/2407.16367
Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set. However, in practice these annotations can differ systematically in the way they
Externí odkaz:
http://arxiv.org/abs/2303.15850
Autor:
Zepf, Kilian, Wanna, Selma, Miani, Marco, Moore, Juston, Frellsen, Jes, Hauberg, Søren, Warburg, Frederik, Feragen, Aasa
Image segmentation relies heavily on neural networks which are known to be overconfident, especially when making predictions on out-of-distribution (OOD) images. This is a common scenario in the medical domain due to variations in equipment, acquisit
Externí odkaz:
http://arxiv.org/abs/2303.13123
Autor:
Arnavaz, Kasra, Krause, Oswin, Zepf, Kilian, Krivokapic, Jelena M., Heilmann, Silja, Bærentzen, Jakob Andreas, Nyeng, Pia, Feragen, Aasa
Motivated by the challenging segmentation task of pancreatic tubular networks, this paper tackles two commonly encountered problems in biomedical imaging: Topological consistency of the segmentation, and expensive or difficult annotation. Our contrib
Externí odkaz:
http://arxiv.org/abs/2105.09737
Autor:
Zepf, Kilian, Wanna, Selma, Miani, Marco, Moore, Juston, Frellsen, Jes, Hauberg, Søren, Feragen, Aasa, Warburg, Frederik
Out of distribution (OOD) medical images are frequently encountered, e.g. because of site- or scanner differences, or image corruption. OOD images come with a risk of incorrect image segmentation, potentially negatively affecting downstream diagnoses
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ad6bd35f082a9d8152b2770e46a847e
http://arxiv.org/abs/2303.13123
http://arxiv.org/abs/2303.13123
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Zepf, K M, Petersen, E W & Feragen, A 2023, That Label's got Style: Handling Label Style Bias for Uncertain Image Segmentation . in Proceedings of Eleventh International Conference on Learning Representations . Eleventh International Conference on Learning Representations, Kigali, Rwanda, 01/05/2023 .
Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set. However, in practice these annotations can differ systematically in the way they
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1202::864dbe4db47f462399657c4f228cadf0
https://orbit.dtu.dk/en/publications/382cfc08-3fcd-45d7-9560-288307645585
https://orbit.dtu.dk/en/publications/382cfc08-3fcd-45d7-9560-288307645585