Overview
To investigate the performance of enhanced computed tomography (CT) or magnetic resonance (MR) imaging by deep learning relative to conventional CT or MR imaging in brain stroke and vascular neurology. We expect that the deep enhanced imaging method can shorten the time stay in the imaging session of stroke patients, optimize the overall imaging quality and improve the patients' care in imaging session.
Description
Early diagnosis of cerebral infarction, detection of ischemic penumbra, evaluation of collateral circulation and identification of vascular lesions by imaging are critical for treatment decision and outcome improvement in cerebral stroke. Multimodal computed tomography (CT) and magnetic resonance (MR) imaging are most prevalent and accessible approaches in clinical scenarios. These two approaches are downgraded either by radiation exposure or long scanning time which may hinder the rapid treatment for patients. Deep learning has shown substantial achievements in medical imaging enhancement. The added value of deep learning method in stroke and vascular neurology has not been thoroughly validated. In this study, we aimed to investigate the performance of enhanced computed tomography (CT) or magnetic resonance (MR) imaging by deep learning relative to conventional CT or MR imaging in brain stroke and vascular neurology. We expect that the deep enhanced imaging method can shorten the time stay in the imaging session of stroke patients, optimize the overall imaging quality and improve the patients' care in imaging session.
Eligibility
Inclusion Criteria:
- suspecting to have experienced stroke or cerebral ischemia and needed to undergo brain imaging and vascular imaging including CT or MRI
- no history of kidney failure
- a minimum age of 18 years
- obtained written informed consent
Exclusion Criteria:
- severe movement artifacts
- incidental finding of tumor lesion or craniocerebral surgery history
- poor imaging failed to perform deep learning method
- women who pregnancy