1. A Machine Learning Approach for Classifying Ischemic Stroke Onset Time From Imaging
- Author
-
King Chung Ho, Haoyue Zhang, William Speier, Suzie El-Saden, Corey W. Arnold, and Fabien Scalzo
- Subjects
Computer science ,MR perfusion imaging ,medicine.medical_treatment ,computer.software_genre ,030218 nuclear medicine & medical imaging ,Brain Ischemia ,Engineering ,0302 clinical medicine ,Stroke ,screening and diagnosis ,Radiological and Ultrasound Technology ,medicine.diagnostic_test ,stroke onset time ,Brain ,Thrombolysis ,Magnetic Resonance Imaging ,Computer Science Applications ,Detection ,Nuclear Medicine & Medical Imaging ,Networking and Information Technology R&D (NITRD) ,Biomedical Imaging ,Algorithms ,4.2 Evaluation of markers and technologies ,acute ischemic stroke ,Feature extraction ,Bioengineering ,Machine learning ,Article ,03 medical and health sciences ,Text mining ,Deep Learning ,Robustness (computer science) ,Information and Computing Sciences ,Medical imaging ,medicine ,Humans ,Electrical and Electronic Engineering ,Acute stroke ,autoencoder ,business.industry ,Deep learning ,Neurosciences ,Magnetic resonance imaging ,medicine.disease ,Brain Disorders ,4.1 Discovery and preclinical testing of markers and technologies ,Stroke treatment ,Ischemic stroke ,Artificial intelligence ,business ,computer ,Classifier (UML) ,Software - Abstract
Current clinical practice relies on clinical history to determine the time since stroke (TSS) onset. Imaging-based determination of acute stroke onset time could provide critical information to clinicians in deciding stroke treatment options, such as thrombolysis. The patients with unknown or unwitnessed TSS are usually excluded from thrombolysis, even if their symptoms began within the therapeutic window. In this paper, we demonstrate a machine learning approach for TSS classification using routinely acquired imaging sequences. We develop imaging features from the magnetic resonance (MR) images and train machine learning models to classify the TSS. We also propose a deep-learning model to extract hidden representations for the MR perfusion-weighted images and demonstrate classification improvement by incorporating these additional deep features. The cross-validation results show that our best classifier achieved an area under the curve of 0.765, with a sensitivity of 0.788 and a negative predictive value of 0.609, outperforming existing methods. We show that the features generated by our deep-learning algorithm correlate with the MR imaging features, and validate the robustness of the model on imaging parameter variations (e.g., year of imaging). This paper advances magnetic resonance imaging analysis one-step-closer to an operational decision support tool for stroke treatment guidance.
- Published
- 2019