The major issue in the development of pattern recognition towards lung cancer classification is the formation of feature extraction process and the proposed classifier model. In the proposed approach, a self-regulated gray wolf optimizer based extreme learning machine classifier is proposed to carry out lung cancer classification along with the statistical feature extraction methods. Simulation shows that the proposed approach works well and produces higher classification accuracy than the conventional classifier methods. The modeled SelfRegulated Gray Wolf Optimizer (SRGWO) and Extreme Learning Machine (ELM) along with feature and segmentation process shows highest improvement in comparison with the other existing literature studies in neural networks. In particular, the significant finding of this work employing ELM, SRGWO and feature analysis validates the correlation of Computed Tomography (CT) measures as well as classification pathological parameters. Thus, the proposed SRGWO and ELM classifier is developed in the present approach for lung cancer classification of CT images reducing the computational cost and time of all the earlier classifiers and as well increasing the classification accuracy. On performing trial runs for the proposed SRGWO – ELM to compute the classification results for the considered real time and Lung Image Database Consortium (LIDC) lung images, it has been noted that at certain trials, the extreme learning machine neuronal classifier is noted to get stuck up with the local minima problem and it is necessary to restart the generation process to achieve classification solutions.