Classification of Lung Nodule Using Hybridized Deep Feature Technique
Deep learning techniques have become very popular among Artificial Intelligence (AI) techniques in many areas of life. Among many types of deep learning techniques, Convolutional Neural Networks (CNN) can be useful in image classification applications. In this work, a hybridized approach has been fo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
University of Tehran
2020-12-01
|
| Series: | Journal of Information Technology Management |
| Subjects: | |
| Online Access: | https://jitm.ut.ac.ir/article_79369_c5abf1274531aa0c9c8485bc78aee6ae.pdf |
| _version_ | 1818402492158836736 |
|---|---|
| author | Malin Bruntha Immanuel Alex Pandian Siril Sam Abraham |
| author_facet | Malin Bruntha Immanuel Alex Pandian Siril Sam Abraham |
| author_sort | Malin Bruntha |
| collection | DOAJ |
| description | Deep learning techniques have become very popular among Artificial Intelligence (AI) techniques in many areas of life. Among many types of deep learning techniques, Convolutional Neural Networks (CNN) can be useful in image classification applications. In this work, a hybridized approach has been followed to classify lung nodule as benign or malignant. This will help in early detection of lung cancer and help in the life expectancy of lung cancer patients thereby reducing the mortality rate by this deadly disease scourging the world. The hybridization has been carried out between handcrafted features and deep features. The machine learning algorithms such as SVM and Logistic Regression have been used to classify the nodules based on the features. The dimensionality reduction technique, Principle Component Analysis (PCA) has been introduced to improve the performance of hybridized features with SVM. The experiments have been carried out with 14 different methods. It has been found that GLCM + VGG19 + PCA + SVM outperformed all other models with an accuracy of 94.93%, sensitivity of 90.9%, specificity of 97.36% and precision of 95.44%. The F1 score was found to be 0.93 and the AUC was 0.9843. The False Positive Rate was found to be 2.637% and False Negative Rate was 9.09%. |
| first_indexed | 2024-12-14T08:09:13Z |
| format | Article |
| id | doaj.art-4f03a5115a7f4028a9b4e140992c374e |
| institution | Directory Open Access Journal |
| issn | 2008-5893 2423-5059 |
| language | fas |
| last_indexed | 2024-12-14T08:09:13Z |
| publishDate | 2020-12-01 |
| publisher | University of Tehran |
| record_format | Article |
| series | Journal of Information Technology Management |
| spelling | doaj.art-4f03a5115a7f4028a9b4e140992c374e2022-12-21T23:10:06ZfasUniversity of TehranJournal of Information Technology Management2008-58932423-50592020-12-0112Special Issue: The Importance of Human Computer Interaction: Challenges, Methods and Applications.10912810.22059/jitm.2020.7936979369Classification of Lung Nodule Using Hybridized Deep Feature TechniqueMalin Bruntha0Immanuel Alex Pandian1Siril Sam Abraham2Assistant Prof., Department of Electronics and Communication Engineering, Karunya Institute of Technology and Sciences, Coimbatore – 641114, Tamil Nadu, India.Assistant Prof., Department of Electronics and Communication Engineering, Karunya Institute of Technology and Sciences, Coimbatore – 641114, Tamil Nadu, India.Computer Vision Intern, Vasundharaa Geo Technologies, Pune, Maharashtra, India.Deep learning techniques have become very popular among Artificial Intelligence (AI) techniques in many areas of life. Among many types of deep learning techniques, Convolutional Neural Networks (CNN) can be useful in image classification applications. In this work, a hybridized approach has been followed to classify lung nodule as benign or malignant. This will help in early detection of lung cancer and help in the life expectancy of lung cancer patients thereby reducing the mortality rate by this deadly disease scourging the world. The hybridization has been carried out between handcrafted features and deep features. The machine learning algorithms such as SVM and Logistic Regression have been used to classify the nodules based on the features. The dimensionality reduction technique, Principle Component Analysis (PCA) has been introduced to improve the performance of hybridized features with SVM. The experiments have been carried out with 14 different methods. It has been found that GLCM + VGG19 + PCA + SVM outperformed all other models with an accuracy of 94.93%, sensitivity of 90.9%, specificity of 97.36% and precision of 95.44%. The F1 score was found to be 0.93 and the AUC was 0.9843. The False Positive Rate was found to be 2.637% and False Negative Rate was 9.09%.https://jitm.ut.ac.ir/article_79369_c5abf1274531aa0c9c8485bc78aee6ae.pdfcnntransfer learningglcmsvmpca |
| spellingShingle | Malin Bruntha Immanuel Alex Pandian Siril Sam Abraham Classification of Lung Nodule Using Hybridized Deep Feature Technique Journal of Information Technology Management cnn transfer learning glcm svm pca |
| title | Classification of Lung Nodule Using Hybridized Deep Feature Technique |
| title_full | Classification of Lung Nodule Using Hybridized Deep Feature Technique |
| title_fullStr | Classification of Lung Nodule Using Hybridized Deep Feature Technique |
| title_full_unstemmed | Classification of Lung Nodule Using Hybridized Deep Feature Technique |
| title_short | Classification of Lung Nodule Using Hybridized Deep Feature Technique |
| title_sort | classification of lung nodule using hybridized deep feature technique |
| topic | cnn transfer learning glcm svm pca |
| url | https://jitm.ut.ac.ir/article_79369_c5abf1274531aa0c9c8485bc78aee6ae.pdf |
| work_keys_str_mv | AT malinbruntha classificationoflungnoduleusinghybridizeddeepfeaturetechnique AT immanuelalexpandian classificationoflungnoduleusinghybridizeddeepfeaturetechnique AT sirilsamabraham classificationoflungnoduleusinghybridizeddeepfeaturetechnique |