A Semi-Supervised Learning Framework to Leverage Proxy Information for Stroke MRI Analysis

Jennifer Polson, Haoyue Zhang, Kambiz Nael, Noriko Salamon, Bryan Yoo, Namkug Kim, Dong Wha Kang, William Speier, Corey W. Arnold

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Treating acute ischemic stroke (AIS) patients is a time-sensitive endeavor, as therapies target areas experiencing ischemia to prevent irreversible damage to brain tissue. Depending on how an AIS is progressing, thrombolytics such as tissue-plasminogen activator (tPA) may be administered within a short therapeutic window. The underlying conditions for optimal treatment are varied. While previous clinical guidelines only permitted tPA to be administered to patients with a known onset within 4.5 hours, clinical trials demonstrated that patients with signal intensity differences between diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) sequences in an MRI study can benefit from thrombolytic therapy. This intensity difference, known as DWI-FLAIR mismatch, is prone to high inter-reader variability. Thus, a paradigm exists where onset time serves as a weak proxy for DWI-FLAIR mismatch. In this study, we sought to detect DWI-FLAIR mismatch in an automated fashion, and we compared this to assessments done by three expert neuroradiologists. Our approach involved training a deep learning model on MRI to classify tissue clock and leveraging time clock as a weak proxy label to supplement training in a semi-supervised learning (SSL) framework. We evaluate our deep learning model by testing it on an unseen dataset from an external institution. In total, our proposed framework was able to improve detection of DWI-FLAIR mismatch, achieving a top ROC-AUC of 74.30%. Our study illustrated that incorporating clinical proxy information into SSL can improve model optimization by increasing the fidelity of unlabeled samples included in the training process.

Original languageEnglish (US)
Title of host publication43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2258-2261
Number of pages4
ISBN (Electronic)9781728111797
DOIs
StatePublished - 2021
Event43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021 - Virtual, Online, Mexico
Duration: Nov 1 2021Nov 5 2021

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Conference

Conference43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
Country/TerritoryMexico
CityVirtual, Online
Period11/1/2111/5/21

Keywords

  • Deep Learning
  • MRI
  • Semi-supervised Learning
  • Stroke

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint

Dive into the research topics of 'A Semi-Supervised Learning Framework to Leverage Proxy Information for Stroke MRI Analysis'. Together they form a unique fingerprint.

Cite this