Prediction of Lung Cancer Using FSSO Optimization and Deep Learning based CNN Algorithm
Main Article Content
Abstract
Lung cancer is the uncontrollable growth of cells within the lungs. Commonly cancer occurs in both male and female. This causes a significant breathing problem in both inhaling and exhales a part of the chest. Earlier identification of cancer is the best way for reducing mortality rate. And also identification of lung cancer is the challenging task for every researchers and doctors. In this study, we proposed the deep learning based convolutional neural network (CNN) for classification and prediction of lung cancer in earlier stage. By improving the classification accuracy, we using different significant methods as averaging histogram equalization (AVHEQ) for pre-processing to enhance and remove the noise from the dataset image , social spider optimization algorithm (FSSO) for segment the cancer affected region and extraction technique for extracted the affected region from entire image. Finally the deep learning classifier model to predict the lung cancer in earlier stage. In this model, LIDC-IDRI dataset is used to analyse the results. And also we compare the different machine learning classifier model with deep learning method. The performance of the proposed model is calculated by using different parametric measures. Finally the deep learning model achieve the better classification accuracy than other compared machine learning classifier.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.