VGG19 Network Assisted Joint Segmentation and Classification of Lung Nodules in CT Images

Muhammad Attique Khan; Venkatesan Rajinikanth; Suresh Chandra Satapathy; David Taniar; Jnyana Ranjan Mohanty; Usman Tariq; Robertas Damaševičius

doi:10.3390/diagnostics11122208

VGG19 Network Assisted Joint Segmentation and Classification of Lung Nodules in CT Images

Diagnostics (Basel). 2021 Nov 26;11(12):2208. doi: 10.3390/diagnostics11122208.

Authors

Muhammad Attique Khan¹, Venkatesan Rajinikanth², Suresh Chandra Satapathy³, David Taniar⁴, Jnyana Ranjan Mohanty⁵, Usman Tariq⁶, Robertas Damaševičius⁷

Affiliations

¹ Department of Computer Science, HITEC University, Taxila 47080, Pakistan.
² Department of Electronics and Instrumentation Engineering, St. Joseph's College of Engineering, Chennai, Tamilnadu 600119, India.
³ School of Computer Engineering, Kalinga Institute of Industrial Technology (Deemed to Be University), Bhubaneswar, Odisha 751024, India.
⁴ Faculty of Information Technology, Monash University, Clayton, VIC 3800, Australia.
⁵ School of Computer Applications, Kalinga Institute of Industrial Technology (Deemed to Be University), Bhubaneswar, Odisha 751024, India.
⁶ College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj 11942, Saudi Arabia.
⁷ Faculty of Applied Mathematics, Silesian University of Technology, 44-100 Gliwice, Poland.

Abstract

Pulmonary nodule is one of the lung diseases and its early diagnosis and treatment are essential to cure the patient. This paper introduces a deep learning framework to support the automated detection of lung nodules in computed tomography (CT) images. The proposed framework employs VGG-SegNet supported nodule mining and pre-trained DL-based classification to support automated lung nodule detection. The classification of lung CT images is implemented using the attained deep features, and then these features are serially concatenated with the handcrafted features, such as the Grey Level Co-Occurrence Matrix (GLCM), Local-Binary-Pattern (LBP) and Pyramid Histogram of Oriented Gradients (PHOG) to enhance the disease detection accuracy. The images used for experiments are collected from the LIDC-IDRI and Lung-PET-CT-Dx datasets. The experimental results attained show that the VGG19 architecture with concatenated deep and handcrafted features can achieve an accuracy of 97.83% with the SVM-RBF classifier.

Keywords: VGG-SegNet; deep learning; lung CT images; nodule detection; pre-trained VGG19.