Show simple item record

dc.contributor.authorØstmo, Eirik Agnalt
dc.contributor.authorWickstrøm, Kristoffer
dc.contributor.authorRadiya, Keyur
dc.contributor.authorKampffmeyer, Michael
dc.contributor.authorJenssen, Robert
dc.date.accessioned2024-01-12T12:32:38Z
dc.date.available2024-01-12T12:32:38Z
dc.date.issued2023-10-23
dc.description.abstractDeep learning has the potential to revolutionize medical practice by automating and performing important tasks like detecting and delineating the size and locations of cancers in medical images. However, most deep learning models rely on augmentation techniques that treat medical images as natural images. For contrast-enhanced Computed Tomography (CT) images in particular, the signals producing the voxel intensities have physical meaning, which is lost during preprocessing and augmentation when treating such images as natural images. To address this, we propose a novel preprocessing and intensity augmentation scheme inspired by how radiologists leverage multiple viewing windows when evaluating CT images. Our proposed method, window shifting, randomly places the viewing windows around the region of interest during training. This approach improves liver lesion segmentation performance and robustness on images with poorly timed contrast agent. Our method outperforms classical intensity augmentations as well as the intensity augmentation pipeline of the popular nn-UNet on multiple datasets.en_US
dc.identifier.citationØstmo, Wickstrøm, Radiya, Kampffmeyer, Jenssen. View it like a radiologist: Shifted windows for deep learning augmentation of CT images. Machine Learning for Signal Processing. 2023en_US
dc.identifier.cristinIDFRIDAID 2168519
dc.identifier.doi10.1109/MLSP55844.2023.10285978
dc.identifier.issn1551-2541
dc.identifier.issn2378-928X
dc.identifier.urihttps://hdl.handle.net/10037/32447
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.journalMachine Learning for Signal Processing
dc.relation.projectIDNorges forskningsråd: 309439en_US
dc.relation.projectIDNorges forskningsråd: 315029en_US
dc.relation.projectIDNorges forskningsråd: 303514en_US
dc.relation.projectIDSigma2: NN8106Ken_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2023 The Author(s)en_US
dc.titleView it like a radiologist: Shifted windows for deep learning augmentation of CT imagesen_US
dc.type.versionacceptedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record