Lung segmentation in chest radiographs by fusing shape information in iterative thresholding

This study presents an algorithm for the segmentation of lung fields by fusing shape information priors into intensity-based thresholding in an iterative framework. The main contribution is to maximise information utilisation by effectively combining intensity information with shape priors. The global solution produced by the iterative binarisation is postprocessed using active shape model technique as a final fitting stage. Experimental results performed on publicly available database demonstrate the effectiveness of the algorithm in comparison with other algorithms.