%0 Journal Article
%T Statistical Feature-based Neural Network Approach for the Detection of Lung Cancer in Chest X-Ray Images K.
%A K.A.G. Udeshani
%A R.G.N. Meegama & T.G.I. Fernando
%J International Journal of Image Processing
%D 2011
%I Computer Science Journals
%X Lung cancer, if detected successfully at early stages, enables many treatment options,reduced risk of invasive surgery and increased survival rate. This paper presents a novelapproach to detect lung cancer from raw chest X-ray images. At the first stage, we use apipeline of image processing routines to remove noise and segment the lung from otheranatomical structures in the chest X-ray and extract regions that exhibit shape characteristicsof lung nodules. Subsequently, first and second order statistical texture features areconsidered as the inputs to train a neural network to verify whether a region extracted in thefirst stage is a nodule or not . The proposed approach detected nodules in the diseased areaof the lung with an accuracy of 96% using the pixel-based technique while the feature-basedtechnique produced an accuracy of 88%.
%K Lung Nodule
%K Computer Assisted Diagnostic
%K Artificial Neural Network
%K Chest Radiography
%K Medical Imaging
%U http://cscjournals.org/csc/manuscript/Journals/IJIP/volume5/Issue4/IJIP-425.pdf