No Detail Found!

LCCNet: a deep learning based method for the identification of lungs cancer using CT scans

Author(s)
Kiran Khaliq Department of Computer Science, NFC Institute of Engineering and Technology Multan, Pakistan
Ahmed Naeem Department of Computer Science, NFC Institute of Engineering and Technology Multan, Pakistan
Naeem Aslam Department of Computer Science, NFC Institute of Engineering and Technology Multan, Pakistan
Abdul Malik Department of Mathematics and Statistics, Institute of Southern Punjab Multan, Pakistan
Kamran Abid Department of Computer Science, NFC Institute of Engineering and Technology Multan, Pakistan
Abstract
Lung cancer is a highly lethal disease affecting both males and females nowadays. It is essential to identify cancer accurately at the initial stage of lung cancer. However, accurately diagnosing cancer remains a challenging task for pathologists. Among the various techniques available, CT Scan plays a crucial role in the early identification and treatment of lung cancer. For the classification of lung cancer, lots of developing techniques are used in the medical research field. Unfortunately, these techniques achieve less classification accuracy due to poor learning rate, class imbalance, data overfitting, and vanishing gradient. It is essential to develop an accurate, faster, and well-organized system for the classification of lung cancer. To address these issues, an efficient framework called LCCNet is presented, which is transfer learning applied to the pre-trained Densely Connected Convolutional Networks (DenseNet-121) CNN model. LCCNet is used to accurately classify lung cancer. The most common transfer learning and data augmentation approaches are used to deal with a large dataset. LCCNet utilized CT Scans for the accurate classification of lung cancer. To assess the performance, the model utilizes various evaluation metrics such as accuracy, F1score, precision, and recall along with a confusion matrix to validate the efficiency of the model for lung cancer classification. Furthermore, this study also compares several current studies with the proposed LCCNet model in terms of accuracy measures, showing that the proposed LCCNet model attained the greatest accuracy of 99% when compared to the various existing research fields of study. To the best of our knowledge, the proposed methodology performs efficiently.
Publication Details
Page(s) 80-93
DOI DOI not available
Published Journal: VFAST Transactions on Software Engineering, Volume: 11, Issue: 2, Year: 2023

Request the full text from PASTIC

Keywords
deep learning, Lung Cancer, CNN, LCCNet
0

Citations

0

Downloads

28

Views