Stroke Thrombus Segmentation on SWAN with Multi-Directional U-Nets

Jonathan Kobold 1 Vincent Vigneron 1 Hichem Maaref 1 Dominique Fourer 1 M Aghasaryan 2 C Alecu 2 N Chausson 2 Y L'hermitte 2 D. Smadja 2 E. Läng 3
1 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes
2 Centre Hospitalier Sud Francilien
3 UR - Universität Regensburg
Abstract : The thrombus causing a stroke can be seen on the susceptibility weighted angiography (SWAN) magnetic resonance imaging (MRI) sequence. But it is very small and hard to detect by humans. Up to date the thrombus is identified by trained human experts. But as stroke needs quick treatment, an automatic detection of the thrombus would be useful to speed up the diagnosis of acute stroke. We propose a method for automatic thrombus detection from SWAN using three separate U-Nets which work on the axial, coronal and sagittal planes.
Keywords : Stroke Thrombus Deep Learning MRI Automatic Segmentation
Document type :
Conference papers
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download
https://hal.archives-ouvertes.fr/hal-02334681
Contributor : Dominique Fourer <>
Submitted on : Sunday, October 27, 2019 - 11:13:59 AM
Last modification on : Friday, November 15, 2019 - 1:12:37 PM
Long-term archiving on: Tuesday, January 28, 2020 - 1:09:01 PM

File

tripleunet.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02334681, version 1

Collections

UNIV-EVRY | UNIV-PARIS-SACLAY | IBISC | IBISC-SIAM

Citation

Jonathan Kobold, Vincent Vigneron, Hichem Maaref, Dominique Fourer, M Aghasaryan, et al.. Stroke Thrombus Segmentation on SWAN with Multi-Directional U-Nets. 9th IEEE International Conference on Image Processing Theory, Tools and Applications (IPTA 2019), Nov 2019, Istanbul, Turkey. ⟨hal-02334681⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

44

Files downloads

28

Contact

Informations

CCSD