Transfer Learning for Lung Nodules Classification with CNN and Random Forest
-
Published:2023-11-03
Issue:1
Volume:32
Page:463-479
-
ISSN:2231-8526
-
Container-title:Pertanika Journal of Science and Technology
-
language:en
-
Short-container-title:JST
Author:
Yahya Saleh Abdulrazak,Ka Chin Chee,Ameera Rosdi Ros
Abstract
Machine learning and deep neural networks are improving various industries, including healthcare, which improves daily life. Deep neural networks, including Convolutional Neural Networks (CNNs), provide valuable insights and support in improving daily activities. In particular, CNNs enable the recognition and classification of images from CT and MRI scans and other tasks. However, training a CNN requires many datasets to attain optimal accuracy and performance, which is challenging in the medical field due to ethical worries, the lack of descriptive notes from experts and labeled data, and the overall scarcity of disease images. To overcome these challenges, this work proposes a hybrid CNN with transfer learning and a random forest algorithm for classifying lung cancer and non-cancer from CT scan images. This research aims include preprocessing lung nodular data, developing the proposed algorithm, and comparing its effectiveness with other methods. The findings indicate that the proposed hybrid CNN with transfer learning and random forest performs better than standard CNNs without transfer learning. This research demonstrates the potential of using machine learning algorithms in the healthcare industry, especially in disease detection and classification.
Publisher
Universiti Putra Malaysia
Subject
General Earth and Planetary Sciences,General Environmental Science
Reference36 articles.
1. Agarwal, A., Patni, K., & Rajeswari, D. (2021, July 8-10). Lung cancer detection and classification based on Alexnet CNN. [Paper presentation]. International Conference on Communication and Electronics System (ICCES 2021), Coimbatre, India. https://doi.org/10.1109/ICCES51350.2021.9489033 2. Ali, I., Hart, G. R., Gunabushanam, G., Liang, Y., Muhammad, W., Nartowt, B., Kane, M., Ma, X., & Deng, J. (2018). Lung nodule detection via deep reinforcement learning. Frontiers in Oncology, 8, 108. https://doi.org/10.3389/fonc.2018.00108 3. Alom, M. Z., Taha, T. M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M. S., Hasan, M., Essen, B. C. V., Awwal, A. A. S., & Asari, V. K. (2019). A state-of-the-art survey on deep learning theory and architectures. Electronics, 8(3), 292. https://doi.org/10.3390/electronics8030292 4. Anderson, J., Rainie, L., & Luchsinger, A. (2018, December 10). Artificial intelligence and the future of humans. Pew Research Center. chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/http://tony-silva.com/eslefl/miscstudent/downloadpagearticles/AIhumanfuture-pew.pdf 5. Arabahmadi, M., Farahbakhsh, R., & Rezazadeh, J. (2022). Deep learning for smart healthcare—A survey on brain tumor detection from medical imaging. Sensors, 22(5), 1960. https://doi.org/10.3390/s22051960
|
|