Detection of pneumonia clouds in chest X-ray using image processing approach

Finding ways to automate diagnostics from medical images, has continuously been one of the most interesting areas of software development. This article presents a novel approach for detecting the presence of pneumonia clouds in chest X-rays (CXR) by using only Image processing techniques. For this, we have worked on 40 analog chest CXRs pertaining to Normal and Pneumonia infected patients. Indigenous algorithms have been developed for cropping and for extraction of the lung region from the images. To detect pneumonia clouds we have used Otsu thresholding which will segregate the healthy part of lung from the pneumonia infected cloudy regions. We are proposing to compute the ratio of area of healthy lung region to total lung region to establish a result. The task has been performed using Python and OpenCV as they are free, opensource tools and can be used by all, without any legality issues or cost implication.