Optimization of Darknet-19 model for the early diagnosis of Covid-19 based on CXR images

Even after the pandemic, Covid-19 is still threatening lives and causing devastating losses to businesses. Thus, early Covid-19 diagnosis prevents the further spread of this epidemic and helps to quickly treat affected patients of coronavirus. Unlike Polymerase Chain Reaction (PCR) test, screening techniques based on Chest X-Ray (CXR) scan detect Covid-19 early even before the beginning of Covid-19 symptoms, also they are more effective and have higher detection rates. However, the CXR images suffer of some low visual quality which makes the CXR-based screening method time consuming due to the small number of radiologists. Therefore, in this paper, we propose an optimization technique for a recently developed intelligent classification system (Darknet-19) that assists radiologists in diagnosing coronavirus for patients using CXR images. In particular, our proposed optimization scheme consists first in a close-up dataset cleaning followed by advanced image enhancement as a preprocessing phase to the Darknet-19 classification model. Our experiments show that our proposed preprocessing optimization scheme improved the performance of the Darknet-19 model to reach an accuracy of 99.2%.