Automatic Detection of Pulmonary Embolism from Computed Tomography Scans Using Deep Learning

Background and Aims: Pulmonary embolism (PE) is a sudden blockage of an artery in the lung, typically caused by a blood clot that has traveled from a deep vein. Early detection of deep vein thrombosis (DVT) and PE is crucial to prevent life-threatening complications. This study explores the application of deep learning techniques to improve computer-aided detection (CAD) of PE, demonstrating the potential of artificial intelligence in enhancing clinical workflows. PE poses significant diagnostic challenges, particularly with the increasing reliance on computed tomography pulmonary angiography (CTPA) scans. Early and accurate detection is vital for improving patient outcomes. This research seeks to address these challenges by integrating convolutional neural networks (CNNs) into the diagnostic process, leveraging classification-guided detection approaches to enhance sensitivity and reduce false positives in automated PE detection.

کلیدواژه ها:

Deep learning ، Artificial intelligence ، Computed Tomography ، Pulmonary Embolism ، Diagnosis