Browsing by Author "Almekhlafi, Mohammed"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Acute Ischemic Stroke Analysis Using Deep Learning-based Image-to-image Translation
    (2023-08) Gutierrez Munoz, Jose Alejandro; Forkert, Nils Daniel; Pike, G. Bruce; Lee, Joon; LeVan, Pierre; Almekhlafi, Mohammed
    Acute ischemic stroke occurs due to the sudden occlusion of a cerebral artery, leading to a disruption in metabolic homeostasis and cell damage. Accurate diagnosis and informed treatment decision-making rely on clinical assessments accompanied by medical imaging. Deep learning methods offer the potential to enhance this decision-making by enabling complex pattern recognition. However, they often rely on large amounts of data, which poses a challenge in stroke centers due to the diverse range of imaging modalities employed. Moreover, specialized processing is often required for the meaningful interpretation of valuable imaging methods like perfusion imaging. Recent advancements in deep learning have made it easier to process and analyze perfusion data by predicting the follow-up tissue outcome. However, these models rely on manual binary lesion segmentations as prediction targets, which may hinder interpretability and limit the amount of available data. To address these limitations, the work described in this thesis utilizes a set of deep learning techniques known as image-to-image translation networks in two distinct ways. First, a method was developed to simulate computed tomography datasets based on magnetic resonance imaging scans and vice versa. The results showed that the proposed approach produces realistic outputs, effectively changing the modality while preserving stroke lesions and brain morphology in follow-up scans. This increases the availability of single-modality data and provides an alternative imaging option for follow-up stroke evaluation. Second, a method was developed to predict stroke tissue outcomes from perfusion scans, without relying on manual lesion segmentations and predicting the follow-up image instead. The results show that the proposed method is able to capture the effects of different treatments, highlighting its potential as a tool for treatment guidance or efficacy evaluation. In conclusion, the application of image-to-image generative modelling proves to be valuable for enhancing acute ischemic stroke analysis and care.
  • Thumbnail Image
    ItemOpen Access
    Technology Roadmapping for Stroke Patients Assessment: Hospitalization Phase and Home Monitoring
    (2023-12-20) Yankovyi, Illia; Yanushkevich, Svetlana; Almekhlafi, Mohammed; Pichardo, Samuel; Krishnamurthy, Diwakar; Uddin, Gias
    Stroke is a worldwide problem, with over 13.7 million new strokes each year and the second commonest cause of death in the world. If it is not fatal, a stroke can result in permanent disabilities, including paralysis, sensory impairment, slurred speech, loss of vision, and loss of motor functions. Stroke can occur among hospitalized patients and go unnoticed, which represents a missed opportunity. It should be discovered in a timely manner. This is the motivation of this study. The goal of this research is technology roadmapping for video monitoring of stroke patients during hospitalization and partially at rehabilitation time, using e-health. A distinguishing feature of this thesis is discovering future technology needed for monitoring stroke patients. The starting point of this research is an experimental exploration of the problem using a novel technique called experimental evaluation. At its core is a computational intelligence technique (in particular, deep learning network) that produces various technology-centric scenarios. The task of a human expert is to interpret these scenarios according to the technology roadmapping methodology. The primary end users of the proposed results are hospitals. However, an extension for the post-stroke rehabilitation is possible. To achieve this, a monitoring system can be integrated into e-health care based on a self-aware platform. Examples of such applications are reported in the contributed papers.
  • Thumbnail Image
    ItemOpen Access
    The Safety and Cost-Effectiveness of Carotid Angioplasty and Stenting in Calgary
    (2012-09-28) Almekhlafi, Mohammed; Hill, Michael D.
    Objectives To evaluate the safety and cost of carotid stenting in Calgary. Methods A cost-utility analysis from the perspective of the Canadian health care system was performed comparing stenting to endarterectomy using a decision analytic model. A prospective cohort study was done for trans cranial Doppler monitoring during stenting procedures. Findings were correlated with 24-hour MRI brain lesions using a binomial regression model. Results Stenting was more expensive than endarterectomy ($6106.84 incremental cost) and had a lower effectiveness (- 0.12 QALYs). Results were influenced by the procedure costs and were sensitive to patients’ characteristics. In 26 subjects who underwent stenting, MRI lesions were detected in 76%. Procedural monitoring showed a median of 224.5 emboli. Large emboli correlated with MRI lesions after adjusting for age and symptoms status. Conclusion To improve the outcomes of carotid stenting, research should aim to improve the procedure safety without increasing its costs.