Automated Detection of Ischemic Stroke and Subsequent Patient Triage in Routinely Acquired Head CT.
Tom FinckDavid SchinzLioba GrundlRami EisawyMehmet YiğitsoyJulia MoosbauerClaus ZimmerFranz PfisterBenedikt WiestlerPublished in: Clinical neuroradiology (2021)
Our study demonstrates the potential of a weakly supervised anomaly-detection tool to detect stroke findings in head CT. Definite classification into normal/pathological was made with high accuracy in > 2/3 of patients. Anomaly heatmaps further provide guidance towards pathologies, also in cases with inconclusive ratings.
Keyphrases
- machine learning
- computed tomography
- deep learning
- atrial fibrillation
- end stage renal disease
- image quality
- emergency department
- dual energy
- ejection fraction
- newly diagnosed
- loop mediated isothermal amplification
- optic nerve
- label free
- real time pcr
- prognostic factors
- magnetic resonance imaging
- case report
- positron emission tomography
- high throughput
- magnetic resonance
- blood brain barrier
- brain injury
- single cell
- patient reported
- subarachnoid hemorrhage