A patent was recently registered in the United States by Emirati researcher Dr. Fatima Taher, associate professor and assistant dean for research affairs at the College of Technical Innovation at Zayed University.
Dr. Taher developed a program that helps early detection of diseases related to cerebral blood vessels, based on a new algorithm technology that leverages on artificial intelligence and machine learning.
Cerebral vascular diseases are threatening the life of millions around the world and the diagnosis of such diseases have been a challenge over the years. Most physicians would agree that the most important step of recovery is obtaining early and the right diagnosis. If the illness is precisely identified, the most effective treatment can be given to patients.
“Analyzing cerebrovascular changes can significantly lead to not only detecting the presence of serious diseases, such as hypertension and dementia, but can also assist in tracking their progress,” Dr. Taher said. “Such analysis could be well performed using Time-of-Flight Magnetic Resonance Angiography (ToF–MRA) images, but this requires accurate segmentation of the cerebral vasculature from the surroundings. To achieve this goal, we propose a fully automated cerebral vasculature segmentation approach based on extracting both prior and current appearance features that have the ability to capture the appearance of macro and micro-vessels in ToF–MRA.”
She also mentioned through validating the accuracy of such an algorithm, they are able to test the proposed approach on in-vivo data using 200 data sets, which were qualitatively validated by a neuroradiology expert.
The researcher indicates that the proposed approach can be used to diagnose high blood pressure, strokes and an aneurysm, as the doctor can apply an early diagnosis on the patient’s possibility of any of these cerebrovascular diseases before his symptoms appear.
“For neurosurgeons, analyzing the brain scans manually takes a long time and a lot of effort especially when tracking a small vessel in the orthogonal view in order to be able to get a better picture of the vascular anatomy,” Dr. Taher said. “With the aid of bio-engineers and computer engineers, several computer aided diagnostic CAD systems have been developed to analyze cerebrovascular structures, taking into consideration that any CAD system needs accurate segmentation of the cerebrovasculature from the surroundings, and this is the main motivation behind developing our approach.”
The researcher stresses that the segmentation of the cerebrovascular structure is crucial since it helps in the diagnosis process, surgery planning, research, and monitoring. Moreover, the benefits of the segmentation of the cerebrovascular structure lay in its ability to improve the simulation of the blood flow and the visualization of the vessels in which each developed method solves a problem faced previously or triggers a specific region of the brain.
