Toward Automated Classification of Pathological Transcranial Doppler Waveform Morphology via Spectral Clustering
| Autor: | Thomas Devlin, Kian Jalaleddini, Fabien Scalzo, Robert B. Hamilton, Samuel G. Thorpe, Amber Y. Dorn, Corey M. Thibeault, Nicolas Canac, Seth J. Wilk |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Male
Middle Cerebral Artery Physiology Ultrasonography Doppler Transcranial Cerebral arteries Blood Pressure 030204 cardiovascular system & hematology Pathology and Laboratory Medicine Vascular Medicine Brain Ischemia Machine Learning Automation Mathematical and Statistical Techniques 0302 clinical medicine Blood Flow Medicine and Health Sciences Cluster Analysis Mathematics Stenosis Multidisciplinary Spectral Clustering Arteries Middle Aged Spectral clustering Body Fluids Stroke Blood Neurology Cerebral blood flow Categorization Cerebrovascular Circulation Physical Sciences Hypertension Middle cerebral artery symbols Medicine Female Anatomy Doppler effect Research Article Statistical Distributions Cerebrovascular Diseases Science Feature vector Research and Analysis Methods 03 medical and health sciences symbols.namesake Signs and Symptoms Diagnostic Medicine medicine.artery medicine Humans Waveform Ischemic Stroke business.industry Biology and Life Sciences Pattern recognition Cerebral Arteries Probability Theory Statistical Dispersion Transcranial Doppler Determining the number of clusters in a data set Cardiovascular Anatomy Blood Vessels Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | PLoS ONE, Vol 15, Iss 2, p e0228642 (2020) PLoS ONE |
| DOI: | 10.1101/19003236 |
| Popis: | Cerebral Blood Flow Velocity waveforms acquired via Transcranial Doppler (TCD) can provide evidence for cerebrovascular occlusion and stenosis. Thrombolysis in Brain Ischemia (TIBI) flow grades are widely used for this purpose, but require subjective assessment by expert evaluators to be reliable. In this work we seek to determine whether TCD morphology can be objectively assessed using an unsupervised machine learning approach to waveform categorization. TCD beat waveforms were recorded at multiple depths from the Middle Cerebral Arteries of 106 subjects; 33 with CTA-confirmed Large Vessel Occlusion (LVO). From each waveform, three morphological variables were extracted, quantifying absolute peak onset, number/prominence of auxiliary peaks, and systolic canopy length. Spectral clustering identified groups implicit in the resultant three-dimensional feature space, with gap-statistic criteria establishing the optimal cluster number. We found that gap-statistic disparity was maximized at four clusters, referred to as flow types I, II, III, and IV. Types I and II were primarily composed of control subject waveforms, whereas types III and IV derived mainly from LVO patients. Cluster morphologies for types I and IV aligned clearly with Normal and Blunted TIBI flows, respectively. Types II and III represented commonly observed flow-types not delineated by TIBI, which nonetheless deviate quantifiably from normal and blunted flows. We conclude that important morphological variability exists beyond that currently quantified by TIBI in populations experiencing or at-risk for acute ischemic stroke, and posit that the observed flow-types provide the foundation for objective methods of real-time automated flow type classification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|