Background: Over the last few years, there has been increasing interest in the use of deep learning algorithms to assist with abnormality detection on medical images. Aim of this study was to investigate the performance of Artificial Intelligence on the detection of pathologies in chest radiographs compared with high resolution multi slice Computed Tomography. Methods: this prospective study was done on 200 cases, who underwent automatic detection of chest disease based on chest radiography in a comprehensive survey on computer-aided detection systems, focuses on the artificial intelligence technology applied in chest radiography to detect the presence of different pathologies, including pleural effusion, pneumothorax, pneumonia, pulmonary masses, and nodules in AP and PA -view chest radiographs using modern digital radiography. Using high resolution multi slice Computed Tomography (16/64/128 detector) for chest examination for abnormality detected by artificial intelligence technology. Axial scanning extending from base of the neck down below the diaphragm with coronal & sagittal reformate images. Results: The mean age of patients was 46.3 years. 123 patients (61.5 %) were males and 77 patients (38.5 %) were female. There was a statistically significant difference between CAD and MDCT diagnosed by radiologist according to sensitivity, p<0.001. Conclusion: In spite CAD system has established fair accuracy, the need of more accurate algorithm is necessary to determine if it can replicate MDCT and radiologist observation of abnormality on chest X-rays