Scrolling 2D U-Net for the 3D segmentation of small vessels on 7T magnetic resonance angiography - ARAMISLAB - Algorithms, models and methods for images and signals of the human brain Access content directly
Preprints, Working Papers, ... Year : 2023

Scrolling 2D U-Net for the 3D segmentation of small vessels on 7T magnetic resonance angiography

Bruno Stankoff

Abstract

Advancements in 7T MRI have allowed for higher spatial image resolution and better signal-to-noise ratio for the visualization of small vessels in the brain. Given the current availability of data, most segmentation techniques in the field have focused on large blood vessel segmentation as opposed to small blood vessel extraction. Thus, there is a need to train effective small vessel segmentation tools with minimal data. In this paper, we propose a scrolling 2D U-Net that integrates information regarding the 3D volume while performing 2D segmentation. This approach was compared to the nnUnet – the state-of-the-art in segmentation models.
Fichier principal
Vignette du fichier
smileUHURA_report__track_changes_.pdf (136.5 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04090356 , version 1 (09-05-2023)

Licence

Attribution

Identifiers

  • HAL Id : hal-04090356 , version 1

Cite

Arya Yazdan-Panah, Rosana El Jurdi, Guanghui Fu, Janan Arslan, Romain Valabregue, et al.. Scrolling 2D U-Net for the 3D segmentation of small vessels on 7T magnetic resonance angiography. 2023. ⟨hal-04090356⟩
49 View
11 Download

Share

Gmail Facebook X LinkedIn More