Doctor of Philosophy
Stroke is a pervasive, devastating disease and remains one of the most challenging conditions to treat. In particular, risk of recurrence is dramatically heightened after a primary stroke and requires urgent preventative therapy to effectively mitigate. However, the appropriate preventative therapy depends on the underlying source of the stroke, known as etiology, which is challenging to determine promptly. Current diagnostic tests for determining etiology underwhelm in both sensitivity and specificity, and in as much as 35% of cases etiology is never determined. In ischemic stroke, the composition of the occluding thrombus, specifically its red blood cell (RBC) content, has been shown to be indicative of etiology but remains largely ignored within clinical practice. Currently, composition can only be quantified through histological analysis, an involved process that can be completed in only the minority of cases where a thrombus has been physically retrieved from the patient during treatment.
The goal of this thesis is to develop a quantitative MR imaging method which is capable of non-invasive prediction of ischemic stroke etiology through assessment of thrombus RBC content. To achieve this goal, we employed quantitative MR parameters that are sensitive to both RBC content and oxygenation, R2* and quantitative susceptibility mapping (QSM), as well as fat fraction (FF) mapping, and evaluated the ability of modern artificial intelligence techniques to form predictions of RBC content and etiology based on these quantitative MR parameters alone and in combination with patient clinical data.
First, we performed an in vitro blood clot imaging experiment, which sought to explicitly define the relationship between clot RBC content, oxygenation and our quantitative MR parameters. We show that both R2* and QSM are sensitive to RBC content and oxygenation, as expected, and that the relationship between R2* and QSM can be used to predict clot RBC content independent of oxygenation status, a necessary step for stroke thrombus characterization where oxygenation is an unknown quantity.
Second, we trained a deep convolutional neural network to predict histological RBC content from ex vivo MR images of ischemic stroke thrombi. We demonstrate that a convolutional neural network is capable of RBC content prediction with 66% accuracy and 8% mean absolute error when trained on a limited thrombus dataset, and that prediction accuracy can be improved to up to 74% through data augmentation.
Finally, we used a random forest classifier to predict clinical stroke etiology using the same ex vivo thrombus MR image dataset. Here, quantitative thrombus R2*, QSM and FF image texture features were used to train the classifier, and we demonstrate that this method is capable of accurate etiology prediction from thrombus texture information alone (accuracy = 67%, area under the curve (AUC) = 0.68), but that when combined with patient clinical data the performance of the classifier improves dramatically to an accuracy and AUC of 93% and 0.89, respectively.
Together, the works presented in this thesis offer extensive ex vivo evidence that quantitative MR imaging is capable of effective stroke thrombus etiology characterization. Such a technique could enable clinical consideration of thrombus composition and bolster stroke etiology determination, thereby improving the management and care of acute ischemic stroke patients.
Summary for Lay Audience
Stroke is a devastating and prevalent disease. One of the largest challenges in stroke treatment is rapidly determining the cause, or etiology, of the stroke so that the risk recurrence can be mitigated. Currently, diagnostic tests for etiology determination are slow and unreliable, and in about one third of patients etiology is never determined. In ischemic stroke, thrombus composition, specifically red blood cell (RBC) content, has been shown through histological analysis to be predictive of stroke etiology. However, histological analysis is too slow to be performed in an acute clinical setting; non-invasive imaging techniques capable of rapid stroke etiology prediction hold immediate value in stroke care. Currently existing techniques use qualitative metrics and have produced underwhelming performance; the goal of this thesis was to develop a quantitative MR imaging method capable of accurate acute ischemic stroke etiology prediction.
In this thesis, I use the quantitative MR parameters R2*, quantitative susceptibility mapping (QSM) and fat fraction (FF) to characterize stroke thrombi. First, I showed that R2* and QSM can be used to derive a relationship with RBC content in blood clots in vitro. Following this, I applied deep learning to quantitative ex vivo thrombus MR images to predict histological thrombus RBC content. Finally, I used machine learning applied to texture features extracted from thrombus R2*, QSM and FF maps to predict stroke etiology using a random forest classifier. Separate models were built using patient clinical data and the combined set of thrombus texture and clinical data features. I found that the model built from imaging information alone was able to predict stroke etiology with comparable accuracy to previous qualitative models, but that when combined with patient clinical data the model’s performance far exceeded that of previously derived predictors and generated highly accurate predictions of stroke etiology in an independent test set. The works presented in this thesis offer extensive ex vivo evidence that quantitative MR imaging is capable of effective stroke thrombus etiology characterization. If implemented clinically, such a technique could enable consideration of thrombus composition and bolster stroke etiology determination, thereby improving management and care of acute ischemic stroke patients.
Christiansen, Spencer D., "Ischemic Stroke Thrombus Characterization through Quantitative Magnetic Resonance Imaging" (2021). Electronic Thesis and Dissertation Repository. 7737.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.