Self-Supervised Few-Shot Learning for Ischemic Stroke Lesion Segmentation
Permanent link
https://hdl.handle.net/10037/32754Date
2023-09-01Type
Journal articleTidsskriftartikkel
Peer reviewed
Author
Tomasetti, Luca; Hansen, Stine; Khanmohammadi, Mahdieh; Engan, Kjersti; Høllesli, Liv Jorunn; Kurz, Kathinka Dæhli; Kampffmeyer, Michael ChristianAbstract
Precise ischemic lesion segmentation plays an essential role in improving diagnosis and treatment planning for ischemic stroke, one of the prevalent diseases with the highest mortality rate. While numerous deep neural network approaches have recently been proposed to tackle this problem, these methods require large amounts of annotated regions during training, which can be impractical in the medical domain where annotated data is scarce. As a remedy, we present a prototypical few-shot segmentation approach for ischemic lesion segmentation using only one annotated sample during training. The proposed approach leverages a novel self-supervised training mechanism that is tailored to the task of ischemic stroke lesion segmentation by exploiting color-coded parametric maps generated from Computed Tomography Perfusion scans. We illustrate the benefits of our proposed training mechanism, leading to considerable improvements in performance in the few-shot setting. Given a single annotated patient, an average Dice score of 0.58 is achieved for the segmentation of ischemic lesions.
Publisher
IEEECitation
Tomasetti, Hansen, Khanmohammadi, Engan, Høllesli, Kurz, Kampffmeyer. Self-Supervised Few-Shot Learning for Ischemic Stroke Lesion Segmentation. IEEE International Symposium on Biomedical Imaging. 2023Metadata
Show full item recordCollections
Copyright 2023 The Author(s)