Brain Stroke Classification Based on Deep Learning Approach in Microwave Brain Imaging System

Subject Areas : Renewable energy

Majid Roohi ¹ , Jalil Mazloum ² , Mohammad Ali Pourmina ³ , Behbod Ghalamkari ⁴

1 - Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 - Department of Electrical Engineering, Shahid Sattari Aeronautical University of Science and Technology, Tehran, Iran
3 - Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
4 - Department of Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

Received: 2021-11-23 Accepted : 2022-06-11 Published : 2022-06-11

Keywords: convolutional neural network, Microwave head imaging system, Confocal image reconstruction algorithm, Intracranial hemorrhage stroke detection, support vector machine classifier,

Abstract :

One of the main reasons of death in the world, mostly affecting seniors, is brain stroke. Almost 85% of all brain strokes are ischemic due to internal bleeding in a part of the brain. Due the high mortality rate, quick diagnosic and treatment of ischemic and hemorrhagic strokes are of utmost importance. In this paper, to realize microwave brain imaging system, a circular array-based of modified bowtie antennas located around the multilayer head phantom with a spherical target with radius of 1 cm as intracranial hemorrhage target aresimulated in CST simulator. To obtain satisfied radiation characteristics in the desired band (from 0.5-5 GHz) an appropriate matching medium is designed. First, in the processing section, a confocal image-reconstructing method based using delay and sum (DAS) and delay, multiply and sum (DMAS) beam-forming algorithms is used. The reconstructed images generated shows the usefulness of the proposed confocal method in detecting the spherical target in the range of 1 cm. The main purpose of this paper is stroke classification using deep learning approaches. For this, an image classification algorithm is developed to estimate the stroke type from reconstructed images. By using the proposed deep learning method, the reconstructed images are classified into different categories of cerebrovascular diseases using a multiclass linear support vector machine (SVM) trained with convol­uti­onal neural networks (CNN) features extracted from the images. The simulated results show the suitability of the proposed image reconstruction method for precisely localizing bleeding targets, with 89% accuracy in 9 seconds. In addition, the proposed deep-learning approach shows good performance in terms of classification, since the system does not confuse between different classes.

References:

[1]   R. Scapaticci, J. Tobon, G. Bellizzi, F. Vipiana, L. Crocco, "Design and numerical characterization of a low-complexity microwave device for brain stroke monitoring", IEEE Trans. on Antennas and Propagation, vol. 66, pp. 7328-7338, Dec. 2018 (doi: 10.1109/TAP.2018.2871266).

[2]   B. Sohani, G. Tiberi, N. Ghavami, M. Ghavami, S. Dudley, A. Rahimi, "Microwave imaging for stroke detection:validation on head-mimicking phantom", Proceeding of the IEEE/PIERS,  pp. 940-948, Rome, Italy, June 2019 (doi: 10.1109/PIERS-Spring46901.2019.9017851).

[3]   J. Wang, X. Jiang, L. Peng, X. Li, H. An, B. Wen, "Detection of neural activity of brain functional site based on microwave scattering principle", IEEE Access, vol. 7, pp. 13468-13475, Jan. 2019 (doi: 10.110­9/ACC­ESS­.2019.2894128).

[4]   M. Ilja, A. Massa, D. Vrba, O. Fiser, M. Salucci, J. Vrba, "Microwave tomography system for methodical testing of human brain stroke detection approaches", International Journal of Antennas and Propagation,vol. 2019, pp. 1-9, Mar. 2019 (doi: 10.1155/2019/4074862).

[5]   A. Santorelli, E. Porter, E. Kirshin,Y.J. Liu, M. Popovic "Investigation of classifiers for tumor detection with an experimental time domain breast screening system", Progress in Electromagnetics Research, vol. 144, pp. 45-57, 2014 (doi: 10.2528/PIER13110709).

[6]   T. Pokorny, J. Tesarik, "Microwave stroke detection and classification using different methods from matlab’s classification learner toolbox", Proceeding of the IEEE/EuMCR, pp. 500-503, Prague, Czech Republic, May. 2019.

[7]   R.C. Conceicao, M. O'Halloran, M. Glavin, E. Jones, "Support vector machines for the classification of early-stage breast cancer based on radar target signatures", Progress in Electromagnetics Research B, vol. 23, pp. 311-327, 2010 (doi: 10.2528/PIERB10062407).

[8]   Y.A. Rahama, O.A. Aryani, U.A. Din, M.A. Awar, A. Zakaria, N. Qaddoumi, "Novel microwave tomography system using a phased-array antenna", IEEE Trans. on Microwave Theory and Techniques, vol. 66, pp. 5119–5128, Aug. 2018 (doi: 10.1109/TMTT.2018.2859929).

[9]   I.T. Rekanos, "Neural-network-based inverse-scattering technique for online microwave medical imaging", IEEE Trans. on Magnetics, vol. 38, no. 2, pp. 1061–1064, Mar. 2002 (doi: 10.1109/20.996272).

[10] L. Li, L.G. Wang, F.L. Teixeira, C. Liu, A. Nehorai, T.J. Cui, "DeepNIS: Deep neural network for nonlinear electromagnetic inverse scattering", IEEE Trans. on Antennas and Propagation, vol. 67, no. 3, pp. 1819–1825, Mar. 2019 (doi: 10.1109/TAP.2018.2885437).

[11] S. Chaplot, L.M. Patnaik, N.R. Jagannathan, "Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network", Biomedical Signal Processing and Control, vol. 1, no. 1, pp. 86-92, Jan. 2006 (doi: 10.1016/j.bspc.2006.05.002).

[12] S.P. Rana, M. Dey, G. Tiberi, L. Sani, A. Vispa, G. Raspa, M. Duranti, M. Ghavami, S. Dudley, "Machine learning approaches for automated lesion detection in microwave breast imaging clinical data", Scientific Reports, vol. 9, Article Number: 10510, July. 2019 (doi: 10.1038/s41598-019-46974-3).

[13] X. Wan, M. Qi, T. Chen, T.J. Cui, "Field-programmable beam reconfiguring based on digitally-controlled coding metasurface", Scientific Reports, vol. 6, pp. 1-8, Feb. 2016 (doi: 10.1038/srep20663).

[14] A. Klautau, P. Batista, N. González-Prelcic, Y. Wang, R. W. Heath, "5G MIMO data for machine learning: application to beam-selection using deep learning", Proceeding of the IEEE/ITA, pp. 1-9, San Diego, CA, USA, Feb. 2018 (doi: 10.1109/ITA.2018.8503086).

[15] L. Nanni, S. Ghidoni, S. Brahnam, "Handcrafted vs. non-handcrafted features for computer vision classification", Pattern Recognition, vol. 71, pp. 158-172, Nov. 2017 (doi: 10.1016/j.patcog.2017.05.025).

[16] F. Hirtenfelder, "Effective antenna simulations using CST MICROWAVE STUDIO (R)", Proceeding of the IEEE/INICA, pp. 239-239, Munich, Germany, April. 2007 (doi: 10.1109/INICA.2007.4353972).

[17] M. Ojaroudi, S. Bila, M. Salimi, "A novel approach of brain tumor detection using miniaturized high-fidelity UWB slot antenna array", Proceeding of the IEEE/EuCAP, pp. 1-5, Krakow, Poland, Mar./April 2019.

[18] B.R. Lavoie, M. Okoniewski, E.C. Fear, "Estimating the effective permittivity for reconstructing accurate microwave-radar images", Plos One, vol. 11, no. 9, pp. 1-25, Sept. 2016 (doi: 10.1371/journal.pone.0160849).

[19] R. Benny, T.A. Anjit, P. Mythili, "An overview of microwave imaging for breast tumor detection", Progress in Electromagnetics Research, vol. 87, pp. 61-91, May. 2020 (doi: 10.2528/PIERB20012402).

[20] M.T. Islam, M.T. Islam, M. Samsuzzaman, S. Kibria, M.E.H Chowdhury, "Microwave breast imaging using compressed sensing approach of iteratively corrected delay multiply and sum beamforming", Diagnostics, vol. 11, no. 470, pp. 1-12, Mar. 2021 (doi: 10.3390/diagnostics11030470).

[21] M.S. Islam, M.T. Islam, A. Hoque, M.T. Islam, N. Amin, M.E. Chowdhury, "A portable electromagnetic head imaging system using metamaterial loaded compact directional 3D antenna", IEEE Access, vol. 9, pp. 50893-50906, Mar. 2021 (doi: 10.1109/ACCESS.2021.3069712).

[22] D.U.N. Qomariah, H. Tjandrasa, C. Fatichah, "Classification of diabetic retinopathy and normal retinal images using CNN and SVM", Proceeding of the IEEE/ICTS, pp. 152-157, Surabaya, Indonesia, July. 2019 (doi: 10.1109/ICTS.2019.8850940).

[23] W. Shao, Y. Du, "Microwave imaging by deep learning network: Feasibility and training method", IEEE Trans. on Antennas and Propagation, vol. 68, pp. 5626-5635, July. 2020 (doi: 10.1109/TAP.2020.2978952).

[24] M. Ghaffari, A. Sowmya, R. Oliver, "Automated brain tumor segmentation using multimodal brain scans: A survey based on models submitted to the BraTS 2012-2018 challenges", IEEE Reviews in Biomedical Engineering, vol. 68, pp. 5626-5635, Oct. 2019 (doi: 10.1109/RBME.2019.2946868).

[25] A. Kerhet, M. Raffetto, A. Boni, A. Massa, "A SVM-based approach to microwave breast cancer detec­tion", Engineering Applications of Artificial Intelligence, vol. 19, pp. 807-818, Oct. 2006 (doi: 10.101­6/j.en­gappai.2006.05.010).

[26] Y. Wu, M. Zhu, D. Li, Y. Zhang, Y. Wang, "Brain stroke localization by using microwave-based signal classification", Proceeding of the IEEE/ICEAA, pp. 828-831, Cairns, QLD, Australia, Sept. 2016 (doi: 10.1109/ICEAA.2016.7731527).

[27] L. Guo, A. Abbosh, "Stroke localization and classification using microwave tomography with k-means clustering and support vector machine", Bioelectromagnetics, vol. 39, pp. 312-324, May. 2018 (doi: 10.100­2/bem.22118).

[28] M. Roohi, J. Mazloum, M.A. Pourmina, B. Ghalamkari, "Machine learning approaches for automated stroke detection, segmentation, and classification in microwave brain imaging systems", Progress in Electromagn­etics Research C, vol. 116, pp. 193-205, Nov. 2021 (doi: 10.2528/PIERC21080404).