Computerized Tomography Pulmonary Angiography Image Simulation using Cycle Generative Adversarial Network from Chest CT imaging in Pulmonary Embolism Patients

Abstract

This study primarily focused on developing a system to generate simulated computed tomography pulmonary angiography (CTPA) images for pulmonary embolism diagnosis and aiding medical practitioners gain a more intuitive understanding of the occurrence of pulmonary embolism (PE) in diagnosis. Compared to existing methods, this system provides a non-invasive and cost-effective way to identify patients with possible pulmonary embolism. The research methodology employed the use of CycleGAN architecture to simulate CTPA images and additional implement classifier modulus to enhance ability to restore pulmonary vessel features, using computed tomography (CT) images from 22 patients and their corresponding CTPA images as training data. The experimental and simulation results provide a new approach to clinical diagnosis, which can assist physicians in the complex screening process, allowing physicians to assess whether a patient needs to undergo detailed testing for CTPA, improving the speed of detection of PE and significantly reducing the number of undetected patients.