Open Access iconOpen Access

ARTICLE

crossmark

Detection of Lung Nodules on X-ray Using Transfer Learning and Manual Features

Imran Arshad Choudhry*, Adnan N. Qureshi

Faculty of Information Technology, University of Central Punjab, Lahore, Pakistan

* Corresponding Author: Imran Arshad Choudhry. Email: email

Computers, Materials & Continua 2022, 72(1), 1445-1463. https://doi.org/10.32604/cmc.2022.025208

Abstract

The well-established mortality rates due to lung cancers, scarcity of radiology experts and inter-observer variability underpin the dire need for robust and accurate computer aided diagnostics to provide a second opinion. To this end, we propose a feature grafting approach to classify lung cancer images from publicly available National Institute of Health (NIH) chest X-Ray dataset comprised of 30,805 unique patients. The performance of transfer learning with pre-trained VGG and Inception models is evaluated in comparison against manually extracted radiomics features added to convolutional neural network using custom layer. For classification with both approaches, Support Vectors Machines (SVM) are used. The results from the 5-fold cross validation report Area Under Curve (AUC) of 0.92 and accuracy of 96.87% in detecting lung nodules with the proposed method. This is a plausible improvement against the observed accuracy of transfer learning using Inception (79.87%). The specificity of all methods is >99%, however, the sensitivity of the proposed method (97.24%) surpasses that of transfer learning approaches (<67%). Furthermore, it is observed that the true positive rate with SVM is highest at the same false-positive rate in experiments amongst Random Forests, Decision Trees, and K-Nearest Neighbor classifiers. Hence, the proposed approach can be used in clinical and research environments to provide second opinions very close to the experts’ intuition.

Keywords


Cite This Article

APA Style
Choudhry, I.A., Qureshi, A.N. (2022). Detection of lung nodules on x-ray using transfer learning and manual features. Computers, Materials & Continua, 72(1), 1445-1463. https://doi.org/10.32604/cmc.2022.025208
Vancouver Style
Choudhry IA, Qureshi AN. Detection of lung nodules on x-ray using transfer learning and manual features. Comput Mater Contin. 2022;72(1):1445-1463 https://doi.org/10.32604/cmc.2022.025208
IEEE Style
I.A. Choudhry and A.N. Qureshi, “Detection of Lung Nodules on X-ray Using Transfer Learning and Manual Features,” Comput. Mater. Contin., vol. 72, no. 1, pp. 1445-1463, 2022. https://doi.org/10.32604/cmc.2022.025208



cc Copyright © 2022 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1270

    View

  • 820

    Download

  • 0

    Like

Share Link