Automated Lung Nodule Detection in CT Images by Optimized CNN: Impact of Improved Whale Optimization Algorithm
Lung cancer is one of the leading causes of cancer-related deaths among individuals. It should be diagnosed at the early stages, otherwise it may lead to fatality due to its malicious nature. Early detection of the disease is very significant for patients’ survival, and it is a challenging issue. Therefore, a new model including the following stages: (1) image pre-processing, (2) segmentation, (3) proposed feature extraction and (4) classification is proposed. Initially, pre-processing takes place, where the input image undergoes specific pre-processing. The pre-processed images are then subjected to segmentation, which is carried out using the Otsu thresholding model. The third phase is feature extraction, where the major contribution is obtained. Specifically, 4D global local binary pattern (LBP) features are extracted. After their extracting, the features are subjected to classification, where the optimized convolutional neural network (CNN) model is exploited. For a more precise detection of a lung nodule, the filter size of a convolution layer, hidden unit in the fully connected layer and the activation function in CNN are tuned optimally by an improved whale optimization algorithm (WOA) called the whale with tri-level enhanced encircling behavior (WTEEB) model.
Keywordslung disease, pre-processing, segmentation, feature extraction, classification, performance,
References1. X. Li et al., Multi-resolution convolutional networks for chest X-ray radiograph based lung nodule detection, Artificial Intelligence in Medicine, 23: 101744, 2020, doi: 10.1016/j.artmed.2019.101744.
2. C.-F.J. Kuo et al., Automatic lung nodule detection system using image processing techniques in computed tomography, Biomedical Signal Processing and Control, 56: 101659, 2020, doi: 10.1016/j.bspc.2019.101659.
3. X. Xu et al., DeepLN: A framework for automatic lung nodule detection using multiresolution CT screening images, Knowledge-Based Systems, 189: 105128, 2019, doi: 10.1016/j.knosys.2019.105128.
4. Y. Gu et al., Automatic lung nodule detection using a 3D deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs, Computers in Biology and Medicine, 103: 220–231, 2018, doi: 10.1016/j.compbiomed.2018.10.011.
5. Q. Wang, F. Shen, L. Shen, J. Huang, W. Sheng, Lung nodule detection in CT images using a raw patch-based convolutional neural network, Journal of Digital Imaging, 32(6): 971–979, 2019, doi: 10.1007/s10278-019-00221-3.
6. M. Wozniak, D. Połap, G. Capizzi, G. Lo Sciuto, L. Kosmider, K. Frankiewicz, Small lung nodules detection based on local variance analysis and probabilistic neural network, Computer Methods and Programs in Biomedicine, 161: 173–180, 2018, doi: 10.1016/j.cmpb.2018.04.025.
7. W. Zuo, F. Zhou, Z. Li, L. Wang, Multi-resolution CNN and knowledge transfer for candidate classification in lung nodule detection, IEEE Access, 7: 32510–32521, 2019, doi:10.1109/ACCESS.2019.2903587.
8. H. Jiang, H. Ma, W. Qian, M. Gao Y. Li, An automatic detection system of lung nodule based on multigroup patch-based deep learning network, IEEE Journal of Biomedical and Health Informatics, 22(4): 1227–1237, 2018, doi: 10.1109/JBHI.2017.2725903.
9. E. Toes-Zoutendijk et al., Incidence of interval colorectal cancer after negative results from first-round fecal immunochemical screening tests, by cutoff value and participant sex and age, Clinical Gastroenterology and Hepatology, 18(7): 1493–1500, 2020, doi: 10.1016/j.cgh.2019.08.021.
10. A.J.M. Rombouts, N. Hugen, M.A.G. Elferink, P.M.P. Poortmans, I.D. Nagtegaal, J.H.W. de Wilt, Increased risk for second primary rectal cancer after pelvic radiation therapy, European Journal of Cancer, 124: 142–151, 2020, doi: 10.1016/j.ejca.2019.10.022.
11. Y. Yin et al., Tumor cell load and heterogeneity estimation from diffusion-weighted MRI calibrated with histological data: an example from lung cancer, IEEE Transactions on Medical Imaging, 37(1): 35–46, 2018, doi: 10.1109/TMI.2017.2698525.
12. J. Jiang et al., Multiple resolution residually connected feature streams for automatic lung tumor segmentation from CT images, IEEE Transactions on Medical Imaging, 38(1): 134–144, 2019, doi: 10.1109/TMI.2018.2857800.
13. P. Petousis, A. Winter, W. Speier, D.R. Aberle, W. Hsu, A.A.T. Bui, Using sequential decision making to improve lung cancer screening performance, IEEE Access, 7: 119403–119419, 2019, doi: 10.1109/ACCESS.2019.2935763.
14. S.S. Alahmari, D. Cherezov, D.B. Goldgof, L.O. Hall, R.J. Gillies, M.B. Schabath, Delta radiomics improves pulmonary nodule malignancy prediction in lung cancer screening, IEEE Access, 6: 77796–77806, 2018, doi: 10.1109/ACCESS.2018.28841vif.
15. A. Tremblay et al., Application of lung-screening reporting and data system versus pancanadian early detection of lung cancer nodule risk calculation in the Alberta lung cancer screening study, Journal of the American College of Radiology, 16(10): 1425–1432, 2019, doi: 10.1016/j.jacr.2019.03.006.
16. Y. Xie, J. Zhang, Y. Xia, Semi-supervised adversarial model for benign–malignant lung nodule classification on chest CT, Medical Image Analysis, 57: 237–248, 2019, doi: 10.1016/j.media.2019.07.004.
17. H. Liu et al., A cascaded dual-pathway residual network for lung nodule segmentation in CT images, Physica Medica, 63: 112–121, 2019, doi: 10.1016/j.ejmp.2019.06.003.
18. V.K. Venugopal et al., Unboxing AI – Radiological insights into a deep neural network for lung nodule characterization, Academic Radiology, 27(1): 88–95, 2020, doi: 10.1016/j.acra.2019.09.015.
19. Y. Nomura et al., Effects of Iierative reconstruction algorithms on computer-assisted detection (CAD) software for lung nodules in ultra-low-dose CT for lung cancer screening, Academic Radiology, 24(2): 124–130, 2017, doi: 10.1016/j.acra.2016.09.023.
20. J. Gong, J.-Y. Liu, L.-J. Wang, B. Zheng, S.-D. Nie, Computer-aided detection of pulmonary nodules using dynamic self-adaptive template matching and a FLDA classifier, Physica Medica, 32(12): 1502–1509, 2016, doi: 10.1016/j.ejmp.2016.11.001.
21. I. Bonavita, X. Rafael-Palou, M. Ceresa, G. Piella, V. Ribas, M.A. González Ballester, Integration of convolutional neural networks for pulmonary nodule malignancy assessment in a lung cancer classification pipeline, Computer Methods and Programs in Biomedicine, 185: 105172, 2020, doi: 10.1016/j.cmpb.2019.105172.
22. N. Tajbakhsh, K. Suzuki, Comparing two classes of end-to-end machine-learning models in lung nodule detection and classification: MTANNs vs. CNNs, Pattern Recognition, 63: 476–486, 2017, doi: 10.1016/j.patcog.2016.09.029.
23. A.A.A. Setio et al., Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge, Medical Image Analysis, 42: 1–13, 2017, doi: 10.1016/j.media.2017.06.015.
24. M. Togaçar, B. Ergen, Z. Cömert, Detection of lung cancer on chest CT images using minimum redundancy maximum relevance feature selection method with convolutional neural networks, Biocybernetics and Biomedical Engineering, 40(1): 23–39, 2020, doi: 10.1016/j.bbe.2019.11.004.
25. S.K. Lakshmanaprabu, S.N. Mohanty, K. Shankar, N. Arunkumar, G. Ramirez, Optimal deep learning model for classification of lung cancer on CT images, Future Generation Computer Systems, 92: 374–382, 2019, doi: 10.1016/j.future.2018.10.009.
26. S. Mirjalili, A. Lewis, The whale optimization algorithm, Advances in Engineering Software, 95: 51–67, 2016, doi: 10.1016/j.advengsoft.2016.01.008.
27. J. Yousefi, Image binarization using Otsu thresholding algorithm, 2015, doi: 10.13140/RG.2.1.4758.9284.
28. C.E. Honeycutt, R. Plotnick, Image analysis techniques and gray-level co-occurrence matrices (GLCM) for calculating bioturbation indices and characterizing biogenic sedimentary structures, Computers & Geosciences, 34(11): 1461–1472, 2008, doi: 10.1016/j.cageo.2008.01.006.
29. S. van der Walt et al., scikit-image: image processing in Python, PeerJ, 2: e453, 2014, doi: 10.7717/peerj.453.
30. K. O’Shea, R. Nash, An introduction to convolutional neural networks, ArXiv e-prints, arXiv:1511.08458, 10 pages, 2015.
31. M.K. Tripathi, D.D. Maktedar, Optimized deep learning model for mango grading: Hybridizing lion plus firefly algorithm, IET Image Processing, 15 (9): 1940–1956, 2021, doi: 10.1049/ipr2.12163.
32. S. Kakad, S. Dhage, Cross domain-based ontology construction via Jaccard Semantic Similarity with hybrid optimization model, Expert Systems with Applications, 178: 115046, 2021, doi: 10.1016/j.eswa.2021.115046.