Deep fusion of gray level co-occurrence matrices for lung nodule classification

• Published in: PloS one Vol. 17; no. 9; p. e0274516
• Main Authors: Saihood, Ahmed, Karshenas, Hossein, Nilchi, Ahmad Reza Naghsh
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 29.09.2022; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Biology and Life Sciences; Care and treatment; Classification; Computed tomography; Computer and Information Sciences; CT imaging; Deep learning; Diagnosis; Engineering and Technology; Evaluation; Health risks; Humans; Image classification; Image segmentation; Long short-term memory; Lung cancer; Lung diseases; Lung Neoplasms - diagnostic imaging; Lung Neoplasms - pathology; Lung nodules; Medical imaging; Medicine and Health Sciences; Methods; Neural networks; Nodules; Optimization; Patient outcomes; Physical Sciences; Research and Analysis Methods; Tomography, X-Ray Computed - methods; United States
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0274516

Lung cancer is a serious threat to human health, with millions dying because of its late diagnosis. The computerized tomography (CT) scan of the chest is an efficient method for early detection and classification of lung nodules. The requirement for high accuracy in analyzing CT scan images is a significant challenge in detecting and classifying lung cancer. In this paper, a new deep fusion structure based on the long short-term memory (LSTM) has been introduced, which is applied to the texture features computed from lung nodules through new volumetric grey-level-co-occurrence-matrices (GLCMs), classifying the nodules into benign, malignant, and ambiguous. Also, an improved Otsu segmentation method combined with the water strider optimization algorithm (WSA) is proposed to detect the lung nodules. WSA-Otsu thresholding can overcome the fixed thresholds and time requirement restrictions in previous thresholding methods. Extended experiments are used to assess this fusion structure by considering 2D-GLCM based on 2D-slices and approximating the proposed 3D-GLCM computations based on volumetric 2.5D-GLCMs. The proposed methods are trained and assessed through the LIDC-IDRI dataset. The accuracy, sensitivity, and specificity obtained for 2D-GLCM fusion are 94.4%, 91.6%, and 95.8%, respectively. For 2.5D-GLCM fusion, the accuracy, sensitivity, and specificity are 97.33%, 96%, and 98%, respectively. For 3D-GLCM, the accuracy, sensitivity, and specificity of the proposed fusion structure reached 98.7%, 98%, and 99%, respectively, outperforming most state-of-the-art counterparts. The results and analysis also indicate that the WSA-Otsu method requires a shorter execution time and yields a more accurate thresholding process.