Automatic detection of solitary pulmonary nodules using superpixels segmentation based iterative clustering approach

Abstract

Lung disease is the premier cause of cancer deaths all over the world. The lung cancer diagnosis is mediocre at an early stage since it is impotent by the radiologist. Various investigations conducted so far manifest clearly that the nodule segmentation algorithms are inefficient. Thus, this investigation has centralized superpixels segmentation based iterative clustering (CSSBIC) and a sophisticated optimization approach for detailed segmentation of pulmonary nodules. The supreme intent of this research paper is the enhancement of lung CT images to identify the tumor effectively and small-scale anomalous nodules segmentation in the lung area. The initial phase an-isotropic diffusion with masking (AIDME) enhancement techniques which can eliminate the noise discern in the images. The next step is to apply the centralized superpixels segmentation based iterative clustering (CSSBIC) algorithm by using an improved picture sequence nodule for abnormal lung tissue prediction. The lung nodule is essentially retrieved using a GWO, based on deep learning techniques, with advanced ONN (ONN) and advanced CNN (CNN). The average time for segmenting the Nodule Slice order is 1.06 s. The best classification accuracy is 97% via GWO based advanced one nearest neighbour (AONN) and 97.6% by GWO based advanced convolutional neural network (ACNN) classifier.