TY - JOUR
T1 - VGG19 network assisted joint segmentation and classification of lung nodules in CT images
AU - Khan, Muhammad Attique
AU - Rajinikanth, Venkatesan
AU - Satapathy, Suresh Chandra
AU - Taniar, David
AU - Mohanty, Jnyana Ranjan
AU - Tariq, Usman
AU - Damaševičius, Robertas
N1 - Funding Information:
The authors of this paper would like to thank The Cancer Imaging Archive for sharing the clinical grade lung CT images for research purpose.
Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2021/12
Y1 - 2021/12
N2 - 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.
AB - 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.
KW - Deep learning
KW - Lung CT images
KW - Nodule detection
KW - Pre-trained VGG19
KW - VGG-SegNet
UR - http://www.scopus.com/inward/record.url?scp=85120313145&partnerID=8YFLogxK
U2 - 10.3390/diagnostics11122208
DO - 10.3390/diagnostics11122208
M3 - Article
AN - SCOPUS:85120313145
SN - 2075-4418
VL - 11
JO - Diagnostics
JF - Diagnostics
IS - 12
M1 - 2208
ER -