Login / Register Submit Your Article
cover
Article Menu

Journal Browser
Vol. 6 (2024)
Vol. 5 (2023)
Vol. 4 (2022)
Vol. 3 (2021)
Vol. 2 (2020)
Vol. 1 (2019)
Open Access Journal Article

Enhancing Medical Image Classification with Transfer Learning Techniques

by Daniel Thomas 1,*
1
Daniel Thomas
*
Author to whom correspondence should be addressed.
TASC  2021, 19; 3(1), 19; https://doi.org/10.69610/j.tasc.20210517
Received: 18 March 2021 / Accepted: 16 April 2021 / Published Online: 17 May 2021
View Full-Text
Download PDF

Abstract

The field of medical image classification is rapidly evolving, especially with the increasing availability of large-scale datasets and advanced machine learning models. This paper focuses on enhancing the performance of medical image classification by leveraging transfer learning techniques. Transfer learning is a machine learning approach that utilizes knowledge gained from one problem to improve learning for similar but distinct problems. By transferring pre-trained models on large datasets to the medical domain, we aim to improve classification accuracy, reduce computational complexity, and mitigate the data scarcity issue often encountered in medical imaging. The study involves a comprehensive evaluation of various deep learning architectures, such as Convolutional Neural Networks (CNNs) and their variants, which are commonly used for image classification tasks. We explore different transfer learning strategies, including fine-tuning, distillation, and domain adaptation, and assess their impact on the classification accuracy for a range of medical image types, such as mammograms, MRI scans, and CT images. The results demonstrate that transfer learning can significantly improve the performance of medical image classification models, particularly when dealing with limited training data. Furthermore, we discuss the challenges and potential solutions for implementing transfer learning in the medical domain, including data privacy concerns and the need for robust evaluation metrics.

Keywords: Medical Image Classification, Transfer Learning, Deep Learning, Convolutional Neural Networks (CNNs), Domain Adaptation.;
Copyright: © 2021 by Thomas. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (Creative Commons Attribution 4.0 International License). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

Share and Cite

ACS Style
Thomas, D. Enhancing Medical Image Classification with Transfer Learning Techniques. Transactions on Applied Soft Computing, 2021, 3, 19. https://doi.org/10.69610/j.tasc.20210517
AMA Style
Thomas D. Enhancing Medical Image Classification with Transfer Learning Techniques. Transactions on Applied Soft Computing; 2021, 3(1):19. https://doi.org/10.69610/j.tasc.20210517
Chicago/Turabian Style
Thomas, Daniel 2021. "Enhancing Medical Image Classification with Transfer Learning Techniques" Transactions on Applied Soft Computing 3, no.1:19. https://doi.org/10.69610/j.tasc.20210517
APA style
Thomas, D. (2021). Enhancing Medical Image Classification with Transfer Learning Techniques. Transactions on Applied Soft Computing, 3(1), 19. https://doi.org/10.69610/j.tasc.20210517

Article Metrics

Article Access Statistics

References

  1. Burbules, N. C., & Callister, T. A. (2000). Watch IT: The Risks and Promises of Information Technologies for Education. Westview Press.
  2. Duda, R. O., Hart, P. E., & Stork, D. G. (2001). Pattern Classification (2nd ed.). John Wiley & Sons.
  3. Cover, T. M., & Hart, P. E. (1967). Neural Network, Perceptron, and the like. Proceedings of the IEEE, 55(11), 2278-2290.
  4. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).
  5. Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1442-1458.
  6. Awan, M. T., et al. (2016). Deep learning for mammography classification: A systematic review. IEEE Journal of Biomedical and Health Informatics, 20(3), 695-706.
  7. Li, G., et al. (2015). Automatic recognition of glioma on MR images using convolutional neural networks. IEEE Journal of Biomedical and Health Informatics, 19(5), 1609-1613.
  8. Wang, X., et al. (2016). Convolutional neural network-based CT image classification for lung diseases. IEEE Journal of Biomedical and Health Informatics, 20(5), 1406-1414.
  9. Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).
  10. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
  11. Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1502.01852.
  12. Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2016). How transferable are features in deep neural networks? In Advances in neural information processing systems (pp. 3320-3328).
  13. Shelhamer, E., Leung, T., & Deng, J. (2016). Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(4), 834-848.
  14. Tzeng, E., Hoffman, J., Saund, E., & Torr, P. H. (2017). Domain adaptation with consistent neural networks. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2056-2064).
  15. Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157-166.