dc.contributor.author | Tomasetti, Luca | |
dc.contributor.author | Khanmohammadi, Mahdieh | |
dc.contributor.author | Engan, Kjersti | |
dc.contributor.author | Høllesli, Liv Jorunn | |
dc.contributor.author | Kurz, Kathinka Dæhli | |
dc.date.accessioned | 2022-04-29T09:26:00Z | |
dc.date.available | 2022-04-29T09:26:00Z | |
dc.date.created | 2022-04-26T16:27:05Z | |
dc.date.issued | 2022-03 | |
dc.identifier.citation | Tomasetti, L., Khanmohammadi, M., Engan, K., Høllesli, L.J., Kurz, K.D. (2022) Multi-input segmentation of damaged brain in acute ischemic stroke patients using slow fusion with skip connection. Proceedings of the Northern Lights Deep Learning Workshop 22, 3. | en_US |
dc.identifier.uri | https://hdl.handle.net/11250/2993371 | |
dc.description.abstract | Time is a fundamental factor during stroke treatments. A fast, automatic approach that segmentsthe ischemic regions helps treatment decisions. In clinical use today, a set of color-coded parametric maps generated from computed tomography perfusion (CTP) images are investigated manually to decide a treatment plan. We propose an automatic method based on a neural network using a set of parametric maps to segment the two ischemic regions (core and penumbra) in patients affected by acute ischemic stroke. Our model is based on a convolution-deconvolution bottleneck structure with multi-input and slow fusion. A loss function based on the focal Tversky index addresses the data imbalance issue. The proposed architecture demonstrates effective performance and results comparable to the ground truth annotated by neuroradiologists. A Dice coefficient of 0.81 for penumbra and 0.52 for core over the large vessel occlusion test set is achieved. The full implementation is available at: https://git.io/JtFGb. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Septentrio Academic Publishing | en_US |
dc.rights | Navngivelse 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/deed.no | * |
dc.subject | ischemic stroke | en_US |
dc.subject | slag | en_US |
dc.subject | image segmentation | en_US |
dc.title | Multi-input segmentation of damaged brain in acute ischemic stroke patients using slow fusion with skip connection | en_US |
dc.type | Peer reviewed | en_US |
dc.type | Journal article | en_US |
dc.description.version | publishedVersion | en_US |
dc.rights.holder | © 2022 Luca Tomasetti, Mahdieh Khanmohammadi, Kjersti Engan, Liv Jorunn Høllesli, Kathinka Dæhli Kurz | en_US |
dc.subject.nsi | VDP::Medisinske Fag: 700::Klinisk medisinske fag: 750::Nevrologi: 752 | en_US |
dc.subject.nsi | VDP::Teknologi: 500::Medisinsk teknologi: 620 | en_US |
dc.source.volume | 3 | en_US |
dc.source.journal | Proceedings of the Northern Lights Deep Learning Workshop | en_US |
dc.identifier.doi | 10.7557/18.6223 | |
dc.identifier.cristin | 2019280 | |
cristin.ispublished | true | |
cristin.fulltext | original | |
cristin.qualitycode | 1 | |