Bat-inspired Metaheuristic Convolutional Neural Network Algorithms for CAD-based Lung Cancer Prediction

P. Priyadharshini; B.S.E. Zoraida

doi:10.6180/jase.202102_24(1).0008

Bat-inspired Metaheuristic Convolutional Neural Network Algorithms for CAD-based Lung Cancer Prediction

Computer Science and Information Engineering

P. Priyadharshini This email address is being protected from spambots. You need JavaScript enabled to view it.¹ and B. S. E. Zoraida¹

¹Department of Computer Science and Engineering, Bharathidasan University, Tiruchirappalli, India.

Received: June 2, 2020
Accepted: July 1, 2020
Publication Date: February 1, 2021

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202102_24(1).0008

ABSTRACT

In this real-world, lung cancer (LC) is the foremost reason for mortality in both mankind in the present time, with an inspiring figure of around five million deaths every year. Computer tomography (CT) can deliver valuable information when diagnosing lung illnesses. The chief goal of this work is to identify cancer nodules in the lungs from a given input image of the lungs and to organize LC and its harshness. To locate cancer nodules in the lungs, Fuzzy c-means (FCM) based segmentation is used. In this paper, a BAT optimization-based learning rate modified Convolutional Neural Network algorithm is introduced to effectively predict lung cancer. Additionally, to improve the proposed classification performance, input image is decomposed with support of the Discrete Wavelet Transform (DWT). With is used to decompose the image into four sub-bands, in such case we considered the Low (LL) band image. And then segmented images are split into two groups of images, which are used for the training and testing process. the proposed scheme has validated with the help of the LIDC-IDRI publically available dataset. They are studied by applying a convolutional neural network, and instantly trained neural network for predicting LC. In the end, the system efficiency is checked by using MATLAB tool to obtain the results of this model. In this experimentation, we achieved the accuracy of 97.43 % with a minimum classification error of 2.57 % in lung cancer prediction. This method is used to diagnose lung cancer correctly, and also this method may also overcome the previous drawbacks in the lung cancer diagnosis method.

Keywords: Fuzzy c-means (FCM), Computer Tomography (CT), Convolutional Neural Network (CNN), BAT optimization algorithm, Discrete Wavelet Transform, and LC Prediction

REFERENCES

[1] Mahdi Mohammadian, Hamid Salehiniya, Azam Safari, Khadijah Allah Bakeshei, Fatemeh Allah Bakeshei, and Abdollah Mohammadian-Hafshejani. Disparity and trends in the incidence and mortality of lung cancer in the world. Biomedical Research and Therapy, 5(6):2348– 2364, 2018.
[2] Robert Timmerman, Rebecca Paulus, James Galvin, Jeffrey Michalski, William Straube, Jeffrey Bradley, Achilles Fakiris, Andrea Bezjak, Gregory Videtic, David Johnstone, Jack Fowler, Elizabeth Gore, and Hak Choy. Stereotactic body radiation therapy for inoperable early stage lung cancer. JAMA - Journal of the American Medical Association, 303(11):1070–1076, 2010.
[3] Hosein Rafiemanesh, Mojtaba Mehtarpour, Farah Khani, Sayed Mohammadali Hesami, Reza Shamlou, Farhad Towhidi, Hamid Salehiniya, Behnam Reza Makhsosi, and Ali Moini. Epidemiology, incidence and mortality of lung cancer and their relationship with the development index in the world. Journal of Thoracic Disease, 8(6):1094–1102, 2016.
[4] Matteo Malvezzi, Cristina Bosetti, Tiziana Rosso, Paola Bertuccio, Liliane Chatenoud, Fabio Levi, Canzio Romano, Eva Negri, and Carlo La Vecchia. Lung cancer mortality in European men: Trends and predictions. Lung Cancer, 80(2):138–145, 2013.
[5] J Vansteenkiste, C Dooms, C. Mascaux, and K. Nackaerts. Screening and early-detection of lung cancer. Annals of Oncology, 23(SUPPL. 10), 2012.
[6] Alistair C. Lindsay, Arjun Nair, and Michael B. Rubens. Multidetector computed tomography of the aorta. In Surgical Management of Aortic Pathology: Current Fundamentals for the Clinical Management of Aortic Disease, pages 385–408. Springer International Publishing, jan 2019.
[7] Ayman El-Baz, Garth M. Beache, Georgy Gimel’Farb, Kenji Suzuki, Kazunori Okada, Ahmed Elnakib, Ahmed Soliman, and Behnoush Abdollahi. Computeraided diagnosis systems for lung cancer: Challenges and methodologies, 2013.
[8] Taruna Aggarwal, Asna Furqan, and Kunal Kalra. Feature extraction and LDA based classification of lung nodules in chest CT scan images. In 2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015, pages 1189–1193, 2015.
[9] Moffy Vas and Amita Dessai. Lung cancer detection system using lung CT image processing. In 2017 International Conference on Computing, Communication, Control and Automation, ICCUBEA 2017, 2018.
[10] Suren Makaju, P. W.C. Prasad, Abeer Alsadoon, A. K. Singh, and A. Elchouemi. Lung Cancer Detection using CT Scan Images. In Procedia Computer Science, volume 125, pages 107–114, 2018.
[11] Tanushree Sinha Roy, Neeraj Sirohi, and Arti Patle. Classification of lung image and nodule detection using fuzzy inference system. In International Conference on Computing, Communication and Automation, ICCCA 2015, pages 1204–1207, 2015.
[12] A Asuntha, A Brindha, S Indirani, and Andy Srinivasan. Lung cancer detection using SVM algorithm and optimization techniques. Journal of Chemical and Pharmaceutical Sciences, 9(4):3198–3203, 2016.
[13] P. B. Sangamithraa and S. Govindaraju. Lung tumour detection and classification using EK-Mean clustering. In Proceedings of the 2016 IEEE International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2016, pages 2201–2206, 2016.
[14] Frank E. Curtis and Katya Scheinberg. Optimization Methods for Supervised Machine Learning: From Linear Models to Deep Learning. In The Operations Research Revolution, pages 89–113. INFORMS, sep 2017.
[15] James Martens. Deep learning via Hessian-free optimization. In ICML 2010 - Proceedings, 27th International Conference on Machine Learning, pages 735–742, 2010.
[16] G. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504–507, jul 2006.
[17] Oriol Vinyals and Daniel Povey. Krylov subspace descent for deep learning. In Journal of Machine Learning Research, volume 22, pages 1261–1268, 2012.
[18] Xin She Yang. Engineering Optimization: An Introduction with Metaheuristic Applications. 2010.
[19] Srinath Balasubramanian, Arunapriya Panchanathan, C. Bharatiraja, Sanjeevikumar Padmanaban, and Zbigniew Leonowicz. Module based floorplanning methodology to satisfy voltage island and fixed outline constraints. Electronics, 7(11):325, nov 2018.