Developing AI Algorithms to Classify Pathologies in Chest X-Ray Images
View/
Open
Metadata
Show full item recordAbstract
Radiologists are in charge of detecting and diagnosing diseases by means of x-rays, Magnetic Resonance Imaging (MRIs), Computed Tomography (CT) scans, and other medical imaging techniques. Of these imaging techniques, chest x-rays are widely popular, as they can detect various diseases related to the heart and lungs. In Qatar, the majority of diseases detected by x-rays include COVID-19, Pneumonia, Tuberculosis (among immigrant workers), and lung cancer. While chest x-rays are really helpful in detecting these diseases, one of the biggest problems concerning the field of radiology is that radiologists often have trouble diagnosing the patient, even though they can detect that there is something wrong. As a result, they often have to repeat the x-ray, consult other doctors, or resort to other medical imaging techniques. Consequently, a lot of time is wasted and costs are amounted, meaning there is inefficiency in the system. Furthermore, exposing the patient to repeated scans is risky. An inefficient radiologist can lead to unsatisfied patients and a prolonged treatment plan. This can be dangerous, especially when the patient’s disease is high risk and requires an immediate response. In recent years, radiologists have begun to adopt Artificial Intelligence (AI) to help them resolve these inefficiencies by aiding them in the diagnosis of diseases. The purpose of this project is to create an AI algorithm that will help the radiologist to diagnose a patient based on a given image of a chest x-ray. The algorithm will be accessed through a graphical user interface (GUI), where the radiologist can input an image and get the diagnosis as an output. There are essentially two subsystems nested into one another: the AI algorithm and the GUI. The entire system shall be called Che-X-Ray.
Citation
Al-Subaie, Roda; Bouhali, Oumaima; Al-Nasr, Lolwa; Elgazar, Yara (2023). Developing AI Algorithms to Classify Pathologies in Chest X-Ray Images. Undergraduate Research Scholars Program. Available electronically from https : / /hdl .handle .net /1969 .1 /200300.