Conference
A recurrent network for segmenting the thrombus on brain MRI in patients with hyper-acute ischemic stroke
| Τίτλος: | A recurrent network for segmenting the thrombus on brain MRI in patients with hyper-acute ischemic stroke |
|---|---|
| Συγγραφείς: | Vargas Ibarra, Sofia, Vigneron, Vincent, Maaref, Hichem, Kobold, Jonathan, Garcia-Salicetti, Sonia, Chausson, Nicolas, Smadja, Didier, L'Hermitte, Yann |
| Συνεισφορές: | Informatique, BioInformatique, Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE)-Université Paris-Saclay, Institut Polytechnique de Paris (IP Paris), Département Electronique et Physique (TSP - EPH), Télécom SudParis (TSP), Institut Mines-Télécom Paris (IMT)-Institut Polytechnique de Paris (IP Paris)-Institut Mines-Télécom Paris (IMT)-Institut Polytechnique de Paris (IP Paris), ARMEDIA (ARMEDIA-SAMOVAR), Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (SAMOVAR), Institut Mines-Télécom Paris (IMT)-Institut Polytechnique de Paris (IP Paris)-Institut Mines-Télécom Paris (IMT)-Institut Polytechnique de Paris (IP Paris)-Télécom SudParis (TSP), Centre Hospitalier Sud Francilien - Centre Hospitalier d'Evry (CHSF), Medical Imaging with Deep Learning Foundation |
| Πηγή: | MIDL 2024: 7th International Conference on Medical Imaging with Deep Learning ; 7th International Conference on Medical Imaging with Deep Learning (MIDL 2024) ; https://univ-evry.hal.science/hal-04939296 ; 7th International Conference on Medical Imaging with Deep Learning (MIDL 2024), Medical Imaging with Deep Learning Foundation, Jul 2024, Paris, France. pp.657--671 ; https://2024.midl.io/scientific-program |
| Στοιχεία εκδότη: | CCSD |
| Έτος έκδοσης: | 2024 |
| Θεματικοί όροι: | deep learning, hyperacute stroke, lesion, MRI modalities, spatial recurrence, thrombus, brain imagery, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
| Θέμα γεωγραφικό: | Paris, France |
| Περιγραφή: | International audience ; In the stroke workflow, timely decision-making is crucial. Identifying, localizing, and measuring occlusive arterial thrombi during initial imaging is a critical step that triggers the choice of therapeutic treatment for optimizing vascular re-canalization. We present a recurrent model that segments the thrombus in patients suffering from a hyper-acute stroke. A cross-attention module is defined to merge the diffusion and susceptibility-weighted modalities available in magnetic resonance imaging (MRI), which are fed to a modified version of convolutional long-short-term memory (CLSTM). It detects almost all the thrombi with a Dice higher than 0.6. The lesion segmentation prediction reduces the false positives to almost zero and the performance is comparable between distal and proximal occlusions. |
| Τύπος εγγράφου: | conference object |
| Γλώσσα: | English |
| Διαθεσιμότητα: | https://univ-evry.hal.science/hal-04939296 https://univ-evry.hal.science/hal-04939296v1/document https://univ-evry.hal.science/hal-04939296v1/file/Midl_2024_publi%C3%A9.pdf |
| Rights: | https://creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/OpenAccess |
| Αριθμός Καταχώρησης: | edsbas.D2F47B65 |
| Βάση Δεδομένων: | BASE |
καταχωρήστε σχόλιο πρώτοι!