Skip to main content

Advertisement

Log in

Classification of Carotid Artery Intima Media Thickness Ultrasound Images with Deep Learning

  • Image & Signal Processing
  • Published:
Journal of Medical Systems Aims and scope Submit manuscript

A Correction to this article was published on 26 July 2019

This article has been updated

Abstract

Cerebrovascular accident due to carotid artery disease is the most common cause of death in developed countries following heart disease and cancer. For a reliable early detection of atherosclerosis, Intima Media Thickness (IMT) measurement and classification are important. A new method for decision support purpose for the classification of IMT was proposed in this study. Ultrasound images are used for IMT measurements. Images are classified and evaluated by experts. This is a manual procedure, so it causes subjectivity and variability in the IMT classification. Instead, this article proposes a methodology based on artificial intelligence methods for IMT classification. For this purpose, a deep learning strategy with multiple hidden layers has been developed. In order to create the proposed model, convolutional neural network algorithm, which is frequently used in image classification problems, is used. 501 ultrasound images from 153 patients were used to test the model. The images are classified by two specialists, then the model is trained and tested on the images, and the results are explained. The deep learning model in the study achieved an accuracy of 89.1% in the IMT classification with 89% sensitivity and 88% specificity. Thus, the assessments in this paper have shown that this methodology performs reasonable results for IMT classification.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Change history

  • 26 July 2019

    The original article unfortunately contained a mistake. Figure 2b was removed in the article.

References

  1. Seçil, M., Carotid and Vertebral Doppler. Basic Ultrasonography and Doppler (pp. 479–498). Akademisyen Bookstore, 2013.

  2. Centers for Disease Control and Prevention, Prevalence of disabilities and associated health conditions among adults. United States, 1999.MMWR. Morbidity and mortality weekly report, 50(7), 120.

  3. Barnett, H., Taylor, D., Haynes, R., Sacket, D., Peerless, S., Ferguson, G., and Eliasziw, M., Beneficial effect of carotid endarterectomy in symptomatic patients with high-grade carotid stenosis. N. Engl. J. Med. 325(7):445–453, 1991.

    Article  CAS  Google Scholar 

  4. Henry, J., Barnett, M., Taylor, D., Eliasziwq, M., Fox, A., Gary, G., and Meldrum, H., Benefit of Carotid Endarterectomy in Patients with Symptomatic Moderate or Severe Stenosis. N. Engl. J. Med. 339(20):1415–1425, 1998.

    Article  Google Scholar 

  5. Benjamin, M., and Dean, R., Current Diagnosis & Treatment in Vascular Surgery. R. H. Dean, J. S. Yao, & D. C. Brewster içinde, Current Diagnosis & Treatment in Vascular Surgery (1st Edition b., pp. 1–5). Appleton & Lange, 1995.

  6. Koçak, A., Comparison of Color Doppler Ultrasonography, Magnetic Resonance Angiography, Multislice Computed Tomography Angiography and Digital Subtraction Angiography Findings in Carotid Artery and Peripheral Artery Lesions. İstanbul: T. C. Ministry of Health Dr. Siyami Ersek Thoracic and Cardiovascular Surgery Training and Research Hospital, 2009.

    Google Scholar 

  7. Burns, P., Gough, S., and Bradbury, A. W., Management of peripheral arterial disease in primary care. BMJ 326:584–588, 2003.

    Article  Google Scholar 

  8. Phatouros, C. C., Higashida, R. T., Malek, A. M., Meyers, P. M., Lempert, T. E., Dowd, C. F., and Halbach, V. V., Carotid Artery Stent Placement for Atherosclerotic Disease: Rationale, Technique, and Current Status. Radiology:26–41, 2000.

  9. Demirci Şahin, A., Üstü, Y., and Işık, D., Management of Preventable Risk Factors of Cerebrovascular Disease. Ankara Medical Journal 15(2):106–113, 2015.

    Article  Google Scholar 

  10. Kocamaz, Ö., Jugular Veil Congestion "Carotid Artery Disease", 2016. Accessed: 05 01, 2018 Kalp ve Damar Cerrahisi Uzmanı Dr. Kocamaz: http://www.drkocamaz.com/karotis-arter-hastaligi

  11. HSFC, What is stroke?, 2018. Accessed: 14 04, 2019 https://www.heartandstroke.ca/stroke/what-is-stroke

  12. Civelek, A., Carotid Artery Disease, 2014. Accessed: 04 24, 2018, Prof. Dr. Ali Civelek: http://www.alicivelek.com/karotis-arter-hastaligi/

  13. Bousser, M.-G., Stroke prevention: an update. Frontiers of Medicine 6(1):22–34, 2012.

    Article  Google Scholar 

  14. Ünüvar, N., Mollahaliloğlu, S., Yardım, N., Bora Başara, B., Dirimeşe, V., Özkan, E., and Varol, Ö., Turkey Burden of Disease Study. T.C. Ministry of Health. Refik Saydam Hıfzıssıhha Center, 2004.

  15. Caplan, L. R., Basic pathology, anatomy, and pathophysiology of stroke. In: Caplan's Stroke: A Clinical (4th ed. b.). Philadelphia: Saunders Elsevier, 2009.

    Chapter  Google Scholar 

  16. Tahmasebpour, H. R., Buckley, A. R., Cooperberg, P. L., and Fix, C. H., Sonographic Examination of the Carotid Arteries. RadioGraphics 25:1561–1575, 2005.

    Article  Google Scholar 

  17. Yurdakul, S., and Aytekin, S., Doppler ultrasonography of the carotid and vertebral arteries. Turkish Society of Cardiology Archive:508–517, 2011.

  18. Öztürk, A., Arslan, A., and Hardalaç, F., Comparison of neuro-fuzzy systems for classification of transcranial Doppler signals with their chaotic invariant measures. Expert Syst. Appl. 34:1044–1055, 2008.

    Article  Google Scholar 

  19. Menchón-Lara, R.-M., Sancho-Gómez, J.-L., and Bueno-Crespo, A., Early-stage atherosclerosis detection using deep learning over carotid ultrasound images. Appl. Soft Comput.:616–628, 2016.

    Article  Google Scholar 

  20. Santos, A. M., Santos, R. M., Castro, P. M., Azevedo, E., Sousa, L., and Tavares, J. M., A novel automatic algorithm for the segmentation of the lümen of the carotid artery in ultrasound B-mode images. Expert Syst. Appl. 40:6570–6579, 2013.

    Article  Google Scholar 

  21. Rocha, R., Campilho, A., Silva, J., Azevedo, E., and Santos, R., Segmentation of the carotid intima-media region in B-mode ultrasound images. Image Vis. Comput. 28:614–625, 2010.

    Article  Google Scholar 

  22. Molinari, F., Zeng, G., and Suri, J. S., Inter-Greedy Technique for Fusion of Different Segmentation Strategies Leading to High-Performance Carotid IMT Measurement in Ultrasound Images. J. Med. Syst. 35:905–919, 2011.

    Article  Google Scholar 

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

    Article  Google Scholar 

  24. Menchón-Lara, R.-M., and Sancho-Gómez, J.-L., Fully automatic segmentation of ultrasound common carotid artery images based on machine learning. Neurocomputing:161–167, 2015.

    Article  Google Scholar 

  25. Kutbay, U., Hardalaç, F., Akbulut, M., and Akaslan, Ü., A Computer Aided Diagnosis System for Measuring Carotid Artery Intima-Media Thickness (IMT) Using Quaternion Vectors. J. Med. Syst. 40(149), 2016.

  26. Milletari, F., Ahmadi, S.-A., Kroll, C., Plate, A., Rozanski, V., Maiostre, J., and Navab, N., Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound. Comput. Vis. Image Underst.:1–11, 2017.

  27. Ikeda, N., Dey, N., Sharma, A., Gupta, A., Bose, S., Acharjee, S., and Suri, J. S., Automated segmental-IMT measurement in thin/thick plaque with bulb presence in carotid ultrasound from multiple scanners: Stroke risk assessment. Comput. Methods Prog. Biomed. 141:73–81, 2017.

    Article  Google Scholar 

  28. Kızılkaya, A., Image Segmentation. Denizli: Pamukkale University, 2008. Accessed: 20.08.2018 http://akizilkaya.pamukkale.edu.tr/B%C3%B6l%C3%BCm4_goruntu_isleme.pdf

  29. Rossi, A. C., Brands, P. J., and Hoeks, A. P., Automatic recognition of the common carotid artery in longitudinal ultrasound B-mode scans. Med. Image Anal. 12:653–665, 2008.

    Article  Google Scholar 

  30. Cheng, D.-C., Schmidt-Trucksäss, A., Liu, C.-H., and Liu, S.-H., Automated Detection of the Arterial Inner Walls of the Common Carotid Artery Based on Dynamic B-Mode Signals. Sensors 10:10601–10619, 2010.

    Article  Google Scholar 

  31. Loizou, C. P., Kasparis, T., Lazarou, T., Pattichis, C. S., and Pantziaris, M., Manual and automated intima-media thickness and diameter measurements of the common carotid artery in patients with renal failure disease. Comput. Biol. Med. 53:220–229, 2014.

    Article  Google Scholar 

  32. Melillo, P., Orrico, A., Scala, P., Crispino, F., and Pecchia, L., Cloud-Based Smart Health Monitoring System for Automatic Cardiovascular and Fall Risk Assessment in Hypertensive Patients. J. Med. Syst. 39(109), 2015.

  33. Christodoulou, C. I., Pattichis, C. S., Pantzaris, M., and Nicolaides, A., Texture-based classification of atherosclerotic carotid plaques. IEEE Trans. Med. Imaging:902–912, 2003.

    Article  CAS  Google Scholar 

  34. Kyriacou, E. C., Pattichis, M. S., Christodoulou, C. I., Pattichis, C. S., Kakkos, S. K., Griffin, M., and Nicolaides, A., Ultrasound imaging in the analysis of carotid plaque morphology for the assessment of stroke. Studies in Health Technology and Informatics:241–275, 2005.

  35. Mougiakakou, S., Golemati, S., Gousias, I., Nicolaides, A., and Nikita, K., Computer-aided diagnosis of carotid atherosclerosis based on ultrasound image statistics, laws’ texture and neural networks. Ultrasound Med. Biol.:26–36, 2007.

    Article  Google Scholar 

  36. Kyriacou, E. C., Pattichis, M. S., Pattichis, C. S., Mavrommatis, A., Christodoulou, C. I., Kakkos, S. K., and Nicolaides, A., Classification of atherosclerotic carotid plaques using morphological analysis on ultrasound images. Appl. Intell.:3–23, 2009.

    Article  Google Scholar 

  37. Acharya, R. U., Faust, O., Alvin, A., Sree, V. S., Molinari, F., Saba, L., and Suri, J. S., Symptomatic vs. Asymptomatic Plaque Classification in Carotid Ultrasound. J. Med. Syst. 36:1861–1871, 2012.

    Article  Google Scholar 

  38. Pedro, L. M., Sanches, J. M., Seabra, J., Suri, J. S., and Fernandes, J. F., Asymptomatic Carotid Disease—A New Tool for Assessing Neurological Risk. Echocardiography:353–361, 2013.

  39. Hu, P., Wu, F., Peng, J., Bao, Y., Chen, F., and Kong, D., Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets. Int. J. Comput. Assist. Radiol. Surg. 12:399–411, 2017.

    Article  Google Scholar 

  40. Kraus, O. Z., Ba, J. L., and Brendan, J., Classifying and segmenting microscopy images with deep multiple instance learning. Bioinformatics 32:52–59, 2016.

    Article  Google Scholar 

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

  42. Thillaikkarasi, R., and Saravanan, S., An Enhancement of Deep Learning Algorithm for Brain Tumor Segmentation Using Kernel Based CNN with M-SVM. J. Med. Syst. 43:84, 2019. https://doi.org/10.1007/s10916-019-1223-7.

    Article  CAS  PubMed  Google Scholar 

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

  44. Cireşan, D. C., Giusti, A., Gambardella, L. M., and Schmidhuber, J., 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.

    Chapter  Google Scholar 

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

    Article  Google Scholar 

  46. Premaladha, J., and Ravichandran, K. S., Novel Approaches for Diagnosing Melanoma Skin Lesions Through Supervised and Deep Learning Algorithms. J. Med. Syst. 40:96, 2016. https://doi.org/10.1007/s10916-016-0460-2.

    Article  CAS  PubMed  Google Scholar 

  47. Dou, Q., Chen, H., Yu, L., Qin, J., and Heng, P.-A., Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection. IEEE Trans. Biomed. Eng. 64(7):1558–1567, 2017.

    Article  Google Scholar 

  48. Acharya, U. R., Oh, S. L., Hagiwara, Y., Tan, J. H., and Adeli, H., Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput. Biol. Med. 100:270–278, 2018.

    Article  Google Scholar 

  49. Arı, A., and Berberler, M., Yapay Sinir Ağları ile Tahmin ve Sınıflandırma Problemlerinin Çözümü İçin Arayüz Tasarımı. Acta Infologica 1(2):55–73, 2017.

    Google Scholar 

  50. Weisstein, E.W., Convolution. Accessed: 08 27, 2018. MathWorld-A Wolfram: http://mathworld.wolfram.com/Convolution.html

  51. Hao, Z., Loss Functions in Neural Networks, 2017. Isaac Changhau: https://isaacchanghau.github.io/post/loss_functions/

  52. Ferri, C., Flach, P. A., & Hernández-Orallo, J., European Conference on Machine Learning. Improving the AUC of Probabilistic Estimation Trees (s. 121–132). Berlin, Heidelberg: Springer, 2003. 10.1007/978-3-540-39857-8_13

  53. Provost, F., and Domingos, P., Tree Induction for Probability-Based Ranking. Mach. Learn. 52(3):199–215, 2003. https://doi.org/10.1023/A:1024099825458.

    Article  Google Scholar 

  54. Rosset, S., ICML '04 Proceedings of the twenty-first international conference on Machine learning. Model selection via the AUC (s. 89). Banff: ACM New York, 2004. 10.1145/1015330.1015400

Download references

Acknowledgements

The authors would like to thank the Radiology Department of Ankara Training and Research Hospital for their kindly cooperation and providing all the ultrasound images used.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Serkan Savaş.

Ethics declarations

Research Involving Human Participants and/or Animals

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee (The Ethics Approval Certificate of Gazi University Ethics Commission dated 08/05/2018 and numbered 2018–217) and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed Consent

Informed consent was obtained from all individual participants included in the study.

Conflict of Interest

There is no conflict of interest in this work.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The original version of this article was revised due missing figure 2b.

This article is part of the Topical Collection on Image & Signal Processing

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Savaş, S., Topaloğlu, N., Kazcı, Ö. et al. Classification of Carotid Artery Intima Media Thickness Ultrasound Images with Deep Learning. J Med Syst 43, 273 (2019). https://doi.org/10.1007/s10916-019-1406-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10916-019-1406-2

Keywords

Navigation