A feature extraction model for assessing the growth of lung cancer in Computer Aided Diagnosis

Computer Aided Diagnosis (CAD) system provides medical assistance by scanning digital images from computer tomography (CT) for suspicious masses and highlights the noticeable segments like presence of tumours, neural blockage etc. This paper, presents a scheme to improve the efficiency of existing CAD systems by proposing a feature extraction model which is carried out in two phases. First phase carries out image pre-processing, edge based segmentation using Snake algorithm and its corresponding database is prepared based on the contour features of the lung. In second phase, the Region of Interest nodules (ROI) are extracted from numerous dataset and its features are calculated and stored in a database in terms of a metric. Finally, the assessment of tumour growth and the reduction in non-pathological area during subsequent periods of cancer are carried out using a nearest neighbour (NN) rule based on features extracted during both phases. Experimental results demonstrate the proposed scheme can help radiologist to improve the diagnosis efficiency by calculating the quantity of tumour growth in each stage accurately.