Fully automated lung segmentation from chest radiographs using SLICO superpixels

This project aims to create a computer-aided diagnosis (CAD) system that can be used to identify tuberculosis (TB) from chest radiographs (CXRs) and, in particular, to observe the progress of the disease where patients have had multiple images over a period of time. Such a CAD tool, if sufficiently automated could run in the background checking every CXR taken, regardless of whether the patient is a suspected carrier of TB. This paper outlines the first phase of the project: segmenting the lung region from a CXR. This is a challenge because of the variation in the appearance of the lung in different patients and even in images of the same patient.