The most significant imaging technique for chest imaging has continued to be chest X-ray (CXR). In comparison to other imaging methods, which include computed tomography, chest X-ray is a cost-effective and easily available imaging method with a wide range of applications. It is distinguished by its short scan time and reduced dosage.A significant quantity of imaging sections and series are produced by thoracic computed topography (CT), that comprises twelve pairs of ribs with varying shapes. The process of sequentially evaluating all images, rib-by-rib and side-by-side, is both time-consuming and demanding. Chest computed topography has been found to have a misdiagnosis rate of 19.2 to 26.8% for any of the chest emergencies, some of that have the potential to result in severe consequences, regardless of the best human effort. Therefore, it is crucial to develop a machine learning identification system that assists radiologists in reducing the reading time, facilitating improved localization, and minimizing misdiagnosis. In radiology, artificial intelligence (AI) is utilized extensively. The deep learning algorithm of artificial intelligence shows excellent diagnostic precision and has the potential to enhance the speed and quality of image interpretation, as well as to increase the effectiveness of clinicians.