AUTHORS: Klug J, Leclerc G, Dirren E, Preti MG, Van De Ville D, Carrera E

Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, 12658: 168-180, March 2021

ABSTRACT

Perfusion CT is widely used in acute ischemic stroke to determine eligibility for acute treatment, by defining an ischemic core and penumbra. In this work, we propose a novel way of building on prior information for the automatic prediction and segmentation of stroke lesions. To this end, we reformulate the task to identify differences from a prior segmentation by extending a three-dimensional Attention Gated Unet with a skip connection allowing only an unchanged prior to bypass most of the network. We show that this technique improves results obtained by a baseline Attention Gated Unet on both the Geneva Stroke Dataset and the ISLES 2018 dataset.

Download PDF

BibTex

Module: