Presented at the International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA2019), Ürgüp, Turkey, Jul 05, 2019

SETSCI Conference Proceedings, 2019, 8, Page (s): 125-131 , https://doi.org/10.36287/setsci.4.5.025

Published Date: 12 October 2019    | 12614     121

Deep learning is a machine learning sub-field that uses deep neural networks. Instead of customized algorithms for each study in this field, it is aimed to cover the wider data set of solutions based on learning the data. Deep learning is a promising approach to solving artificial intelligence problems in machine learning. Nowadays, deep learning algorithms have begun to show themselves in many applications also being studied in biomedical fields. In this medical image processing study, Carotid Artery Intima Media Thickness Ultrasound images were used. Carotid Artery is a type of cardiovascular disease that can result in stroke. If stroke is not diagnosed early, it is in the first place among the disabling diseases. On the other hand, it is the third most common cause of death after cancer and heart disease. For an early diagnose, biomedical image classification performances of VGGNet architecture, which had successful results in the Imagenet competition and an original convolutional neural network model were compared in this study. 501 ultrasound images from 153 patients were used to test the models’ classification performances. It is seen that VGG16, VGG19 and CNNcc models achieved rates of 93%, 90% and 89.1% respectively. These results showed that deep architectures can provide proper classification on biomedical images and this can help clinics to diagnose the disease.

Keywords - Deep learning, carotid artery, intima media thickness, vggnet, convolutional neural network, machine learning, artificial intelligence

[1] K. Phil, MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence. Seoul, Soul-t'ukpyolsi, Korea: Apress. 2017.

[2] Y. Bengio, Learning Deep Architectures for AI. Foundations and Trends in Machine Learning, vol. 2, pp. 1-127. 2009. doi:http://dx.doi.org/10.1561/2200000006.

[3] I. Goodfellow, Y. Bengio, A. Courville, Deep Learning. MIT Press. 2016. [Online]. Available http://www.deeplearningbook.org

[4] L. Deng, & D. Yu, Deep Learning Methods and Applications. Foundations and Trends in Signal Processing, vol. 7, pp. 197-387. 2013. doi: http://dx.doi.org/10.1561/2000000039

[5] O. Z. Kraus, J. L. Ba, & J. Brendan, Classifying and segmenting microscopy images with deep multiple instance learning. Bioinformatics, vol. 32, pp. 52–59. 2016.

[6] O. Ronneberger, P. Fischer, & T. Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation. 2015. arXiv: https://arxiv.org/pdf/1505.04597.pdf

[7] P. Hu, F. Wu, J. Peng, Y. Bao, F. Chen, & D. Kong, Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets. International Journal of Computer Assisted Radiology and Surgery, vol. 12, pp. 399–411, 2017.

[8] D. Wang, A. Khosla, R. Gargeya, H. Irshad, & A. H. Beck, Deep Learning for Identifying Metastatic Breast Cancer. 2018. arXiv: https://arxiv.org/pdf/1606.05718.pdf

[9] D. C. Cireşan, A. Giusti, L. M. Gambardella, & J. Schmidhuber, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013. Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks, pp. 411-418. Berlin: Springer, 2013.

[10] V. Gulshan, L. Peng, M. Coram, M. C. Stumpe, D. Wu, A. Narayanaswamy, R. D. Webster, Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA, vol. 316(22), pp. 2402-2410, 2016.

[11] Q. Dou, H. Chen, L. Yu, J. Qin, & P. A. Heng, Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection. IEEE Transactions on Biomedical Engineering, vol. 64(7), pp. 1558-1567, 2017.

[12] U. R. Acharya, S. L. Oh, Y. Hagiwara, J. H. Tan, & H. Adeli, Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Computers in Biology and Medicine, vol. 100, pp. 270–278, 2018.

[13] A. Civelek, (2014). Karotis Arter Hastalığı. [Online]. Available: http://www.alicivelek.com/karotis-arter-hastaligi/

[14] Ö. Kocamaz, (2016). Şah Damar Tıkanıklığı "Karotis Arter Hastalığı". [Online]. Available: http://www.drkocamaz.com/karotis-arterhastaligi/

[15] M. G. Bousser, Stroke prevention: an update. Frontiers of Medicine, vol. 6(1), pp. 22-34, 2012.

[16] K. Strong, C. Mathers, & R. Bonita, Preventing stroke: saving lives around the world. Lancet Neurol, vol. 6, pp. 182-187, 2007.

[17] A. Demirci Şahin, Y. Üstü, & D. Işık, Serebrovasküler Hastalıklarda Önlenebilen Risk Faktörlerinin Yönetimi. Ankara Medical Journal, vol. 15(2), pp. 106-113, 2015.

[18] N. Ünüvar, S. Mollahaliloğlu, N. Yardım, B. Bora Başara, V. Dirimeşe, E. Özkan, & Ö. Varol, Türkiye Hastalık Yükü Çalışması. T.C. Sağlık Bakanlığı. Refik Saydam Hıfzıssıhha Merkezi Başkanlığı Hıfzıssıhha Mektebi Müdürlüğü, 2004.

[19] K. Simonyan, & A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition. (2014). [Online]. Available: arXiv:1409.1556

[20] F. Doğan, & İ. Türkoğlu, Derin Öğrenme Algoritmalarının Yaprak Sınıflandırma Başarımlarının Karşılaştırılması. Sakarya Universıty Journal Of Computer And Informatıon Scıences, vol. 1, pp. 10-21, 2018.

[21] R. M. Menchón-Lara, J. L. Sancho-Gómez, & A. Bueno-Crespo, Earlystage atherosclerosis detection using deep learning over carotidultrasound images. Applied Soft Computing, pp. 616-628, 2016.

[22] R. Rocha, A. Campilho, J. Silva, E. Azevedo, & R. Santos, Segmentation of the carotid intima-media region in B-mode ultrasound images. Image and Vision Computing, vol. 28, pp. 614-625, 2010.

[23] F. Molinari, G. Zeng, & J. S. Suri, Inter-Greedy Technique for Fusion of Different Segmentation Strategies Leading to High-Performance Carotid IMT Measurement in Ultrasound Images. Journal of Medical Systems, vol. 35, pp. 905-919, 2011.

[24] M. C. Bastida-Jumilla, R. M. Menchón-Lara, J. Morales-Sánchez, R. Verdú-Monedero, J. Larrey-Ruiz, & J. Sancho-Gómez, Frequencydomain active contours solution to evaluate intima–mediathickness of the common carotid artery. Biomedical Signal Processing and Control, pp. 68-79, 2015.

[25] R. M. Menchón-Lara, & J. L. Sancho-Gómez, Fully automatic segmentation of ultrasound common carotid artery images based on machine learning. Neurocomputing, pp. 161–167, 2015.

[26] U. Kutbay, F. Hardalaç, M. Akbulut, & Ü. Akaslan, A Computer Aided Diagnosis System for Measuring Carotid Artery Intima-Media Thickness (IMT) Using Quaternion Vectors. Journal of Medical Systems, vol. 40(149), 2016.

[27] F. Milletari, S. A. Ahmadi, C. Kroll, A. Plate, V. Rozanski, J. Maiostre, N. Navab, Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound. Computer Vision and Image Understanding, pp. 1–11, 2017.

[28] N. Ikeda, N. Dey, A. Sharma, A. Gupta, S. Bose, S. Acharjee, J. S. Suri, Automated segmental-IMT measurement in thin/thick plaque with bulb presence in carotid ultrasound from multiple scanners: Stroke risk assessment. Computer Methods and Programs in Biomedicine, vol. 141, pp. 73-81, 2017.

[29] E. C. Kyriacou, M. S. Pattichis, C. I. Christodoulou, C. S. Pattichis, S. K. Kakkos, M. Griffin, & A. Nicolaides, Ultrasound imaging in the analysis of carotid plaque morphology for the assessment of stroke. Studies in health technology and informatics, pp. 241-275, 2005.

[30] C. I. Christodoulou, C. S. Pattichis, M. Pantzaris, & A. Nicolaides, Texture-based classification of atherosclerotic carotid plaques. IEEE Trans Med Imaging, pp. 902-912, 2003.

[31] S. Mougiakakou, S. Golemati, I. Gousias, A. Nicolaides, & K. Nikita, Computer-aided diagnosis of carotid atherosclerosis based on ultrasound image statistics, laws' texture and neural networks. Ultrasound in Medicine & Biology, pp. 26-36, 2007.

[32] E. C. Kyriacou, M. S. Pattichis, C. S. Pattichis, A. Mavrommatis, C. I. Christodoulou, S. K. Kakkos, & A. Nicolaides, Classification of atherosclerotic carotid plaques using morphological analysis on ultrasound images. Applied Intelligence, pp. 3-23, 2009.

[33] U. R. Acharya, O. Faust, A. Alvin, V. S. Sree, F. Molinari, L. Saba, J. S. Suri, Symptomatic vs. Asymptomatic Plaque Classification in Carotid Ultrasound. Journal of Medical Systems, vol. 36, pp. 1861– 1871, 2012.

[34] Z. Hao, (2017). Loss Functions in Neural Networks. [Online]. Available: https://isaacchanghau.github.io/post/loss_functions/ [35] D. Ballabio, F. Grisoni, & R. Todeschini, Multivariate comparison of classification performance measures. Chemometrics and Intelligent Laboratory Systems, vol. 174, pp. 33-44, 2018. doi:https://doi.org/10.1016/j.chemolab.2017.12.004