Automatic Detection of Segmentation and Advanced Classification Algorithm

Abstract

The lung cancer prediction is mediocre at an early stage as it is impotent by the radiologist. Various investigations done so far manifest clearly that the nodule segmentation algorithms are ineffectual. Thus, this investigation has centralized super pixels segmentation based iterative clustering (SSBIC) and advanced optimization method for precise segmentation of pulmonary nodules. The supreme intent of this research paper is the enhancement of lung CT images to recognize the tumor efficiently and small-scale anomalous nodules segmentation in the lung region. The initial step ADF with unsharp masking enhancement techniques which can eradicate the noise discern in the images. In the subsequent step the Super pixel Segmentation Based Iterative Clustering (SSBIC) algorithm is implemented in an enhanced nodule image sequence for abnormal lung tissue prediction. Ultimately, the lung nodule images are procured by utilizing an Advanced GWO with ONN (AGWO-ONN) and deep learning based Advanced GWO with CNN (AGWO-CNN). Average segmentation time for nodule slice order is 1.06s. The highest classification accuracy is 97% by the Advanced GWO with ONN (AGWO-ONN) method and 97.6% by the Advanced GWO with CNN (AGWO-CNN) method.