Naseem,R., Dar,A.H., Iqbal,U., Bajwa,K.B.
Abstract:
Lung segmentation is regarded as foundation for Computer Aided Diagnosis (CAD) of lung diseases. Computed Tomography scan and CAD facilitate researchers to implement and reveal cutting-edge image processing techniques for identifying lung cancer and likelihood of other lung diseases including bronchitis, emphysema. An automated lung segmentation scheme is proposed in this paper that segments lungs from other body organs contained in CT scan. The scheme uses Otsu algorithm and Connected Component Analysis algorithm for initial segmentation. To refine the initial results and avoid undersegmentation and oversegmentation, morphological operations alongwith bitwise logical AND, OR operations are applied. One of the challenges for lung segmentation algorithms is the overlap of left and right lungs. The algorithm uses otsu thresholding for segmenting conjoint of right and left lungs. Solution to this exceptional case is also proposed in which there is disjoint in a particular lung due to overlap of anatomical structures. To segment this type of lungs, the method computes centroid of objects. The proposed methodology is tested on the database of Cornell University, USA, which includes 15 test scans containing 2920 slices. The results indicate a successful segmentation of 2657 slices including left and right lung overlap case and the case in which lung is contained in parts.