SavedAdd your journal

Journals / Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi / 2026 / Cilt: 19 Sayı: 1

Segmentation and Measurement of Carotid Artery Stenosis in Ultrasound Images Using Computer Vision Methods

Bilgisayar Görüntüleme Yöntemleri Kullanılarak Ultrason Görüntülerinde Karotis Arter Stenozunun Segmentasyonu ve Ölçümü

Elçin Bilici(ATATURK UNIVERSITY)0000-0002-7957-6373
Mete Yağanoğlu(ATATURK UNIVERSITY)0000-0003-3045-169X
Pages
379–394
Publication Date
2026-03-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Computer vision deep learning segmentation successfully detected carotid arteries with a rate of 98% and stenosis in the carotid artery with a rate of 90%, which is considered high.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:With the change of living conditions and dietary habits, there has been an increase in vascular diseases in recent years.
📊
Key Findings & Data:In the management of vascular diseases, which can lead to serious consequences such as stroke and even death, it is very valuable to use appropriate imaging techniques for early and accurate diagnosis.
💡
Conclusion & Impact:Computer vision deep learning segmentation successfully detected carotid arteries with a rate of 98% and stenosis in the carotid artery with a rate of 90%, which is considered high.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:Karotis Arter tespiti · Derin öğrenme · Görüntü segmentasyonu

Abstract

With the change of living conditions and dietary habits, there has been an increase in vascular diseases in recent years. These diseases often lead to peripheral narrowing and occlusion of the arteries. In the management of vascular diseases, which can lead to serious consequences such as stroke and even death, it is very valuable to use appropriate imaging techniques for early and accurate diagnosis. However, the large and complex vascular network makes it difficult to analyze accurate data during diagnostic procedures. In our study, we aimed to easily, quickly and effectively recognize carotid arteries and stenoses ultrasonographically using computer vision deep learning techniques. A dataset containing 3 different levels of the carotid artery was created by obtaining 3401 US images from 120 cases whose age and gender were randomly selected. The width of the carotid artery and the vessels where stenosis was detected were measured using the computer vision deep learning method. Computer vision deep learning segmentation successfully detected carotid arteries with a rate of 98% and stenosis in the carotid artery with a rate of 90%, which is considered high.

Özet

Yaşam koşullarının ve beslenme alışkanlıklarının değişmesiyle birlikte son yıllarda damar hastalıklarında artış görülmektedir. Bu hastalıklar sıklıkla atardamarların periferik daralmasına ve tıkanmasına yol açmaktadır. İnme ve hatta ölüm gibi ciddi sonuçlara yol açabilen damar hastalıklarının yönetiminde erken ve doğru tanı için uygun görüntüleme tekniklerinin kullanılması oldukça değerlidir. Ancak damar ağının geniş ve karmaşık olması tanısal işlemler sırasında doğru verilerin analizini zorlaştırmaktadır. Çalışmamızda bilgisayarlı görüntü derin öğrenme tekniklerini kullanarak karotis arterlerini ve darlıklarını ultrasonografik olarak kolay, hızlı ve etkili bir şekilde tanımayı amaçladık. Yaş ve cinsiyeti rastgele seçilen 120 olgudan 3401 US görüntüsü elde edilerek karotis arterinin 3 farklı seviyesini içeren bir veri seti oluşturuldu. Karotis arterinin genişliği ve darlık tespit edilen damarlar bilgisayarlı görüntü derin öğrenme yöntemi kullanılarak ölçüldü. Bilgisayarlı görüntü derin öğrenme segmentasyonu karotis arterlerini %98 oranında, karotis arterindeki darlığı ise %90 oranında başarılı bir şekilde tespit etti ki bu yüksek bir orandır.

🔖

Cite This Article

Bilici, E., Yağanoğlu, M. (2026). Segmentation and Measurement of Carotid Artery Stenosis in Ultrasound Images Using Computer Vision Methods. Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt: 19 Sayı: 1, 379–394. https://doi.org/10.18185/erzifbed.1738617

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (34)

  1. Bhagawati, M., Paul, S., Agarwal, S., Protogeron, A., Sfikakis, P. P., Kitas, G. D.,. & Suri, J. S. (2023). Cardiovascular disease/stroke risk stratification in deep learning framework: a review. Cardiovascular Diagnosis and Therapy, 13(3), 557.
  2. Zhou, Z., Ni, D., & Li, W. (2020). Deep learning-based methods for carotid artery stenosis evaluation in ultrasound imaging: A review. Ultrasonics, 104, 106128. https://doi.org/10.1016/j.ultras.2019.106128
  3. Zhao, J., Wu, Y., & Zhang, H. (2023). Explainable AI models for carotid artery disease diagnosis using multimodal imaging. Medical Image Analysis, 79, 102480. https://doi.org/10.1016/j.media.2022.102480
  4. Jain, P. K., Sharma, N., Giannopoulos, A. A., Saba, L., Nicolaides, A., & Suri, J. S. (2021). Hybrid deep learning segmentation models for atherosclerotic plaque in internal carotid artery B-mode ultrasound. Computers in biology and medicine, 136, 104721.
  5. Gupta, A., Shah, P., & Patel, R. (2020). A machine learning approach for automatic detection of carotid artery stenosis using ultrasound images. Biomedical Signal Processing and Control, 58, 101855. https://doi.org/10.1016/j.bspc.2020.101855
  6. Latha, S., Muthu, P., Lai, K. W., Khalil, A., & Dhanalakshmi, S. (2022). Performance analysis of machine learning and deep learning architectures on early stroke detection using carotid artery ultrasound images. Frontiers in Aging Neuroscience, 13, 828214.
  7. Huang, T., Zhang, Y., & Li, M. (2022). Multi-task learning for carotid artery stenosis detection and classification using deep learning. Computerized Medical Imaging and Graphics, 97, 102074. https://doi.org/10.1016/j.compmedimag.2021.102074
  8. Jiang, M., Spence, J. D., & Chiu, B. (2020). Segmentation of carotid vessel wall using U-Net and segmentation average network. arXiv preprint arXiv:2002.11467.
  9. Lainé, N., Liebgott, H., Zahnd, G., & Orkisz, M. (2022, September). Carotid artery wall segmentation in ultrasound image sequences using a deep convolutional neural network. In International Conference on Computer Vision and Graphics (pp. 73-84). Cham: Springer Nature Switzerland.
  10. Jain, P. K., Sharma, N., Giannopoulos, A. A., Saba, L., Nicolaides, A., & Suri, J. S. (2021). Hybrid deep learning segmentation models for atherosclerotic plaque in internal carotid artery B-mode ultrasound. Computers in biology and medicine, 136, 104721.
  11. Huang, T., Zhang, Y., & Li, M. (2022). Multi-task learning for carotid artery stenosis detection and classification using deep learning. Computerized Medical Imaging and Graphics, 97, 102074. https://doi.org/10.1016/j.compmedimag.2021.102074
  12. Yuan, X., Chen, Y., & Lu, Y. (2021). Automated carotid artery segmentation using U-Net in ultrasound images. IEEE Transactions on Medical Imaging, 40(1), 73-83. https://doi.org/10.1109/TMI.2020.3012790
  13. Liu, M., Gao, W., Song, D., Dong, Y., Hong, S., Cui, C.,. & Dong, F. (2024). A deep learning-based calculation system for plaque stenosis severity on common carotid artery of ultrasound images. Vascular, 17085381241246312.
  14. Zhou, T., Wu, Y., & Zhang, Z. (2022). Comparative study of deep learning and traditional techniques for vascular imaging. Artificial Intelligence in Medicine, 126, 102015.
  15. Li, H., Jiang, Z., & Wang, S. (2019). Carotid artery segmentation in medical images using traditional and deep learning methods. Journal of Medical Imaging, 6(4), 042406. https://doi.org/10.1117/1.JMI.6.4.042406
  16. Chai, Y., Zhang, J., & Li, H. (2020). Adaptive thresholding for blood vessel detection in fundus images. Computerized Medical Imaging and Graphics, 79, 101-110.
  17. Wang, Y., Jiang, Z., & Hu, J. (2019). Gaussian mixture model for retinal blood vessel segmentation. Medical Image Computing and Computer-Assisted Intervention, 11767, 1-7.
  18. Li, Z., Zhang, W., & He, X. (2021). Carotid artery segmentation using a level set method. Biomedical Signal Processing and Control, 68, 102637.
  19. Sivaswamy, J., C. R., & P. A. (2019). Region growing algorithm for blood vessel segmentation in angiographic images. International Journal of Biomedical Imaging, 2019, 1-9.
  20. Tzeng, P., Huang, H., & Cheng, C. (2020). Mathematical morphology for vessel enhancement and segmentation in retinal images. IEEE Transactions on Image Processing, 29, 5902-5914.
  21. Peng, H., Li, Y., & Wang, Z. (2021). Vessel attribute-based segmentation framework for complex vascular networks. IEEE Transactions on Medical Imaging, 40(2), 456-467.
  22. Naik V N, Gamad R S, Bansod P. (2022). Effect of despeckling filters on the segmentation of ultrasound common carotid artery images. Biomed J. 2022 Aug;45(4):686-695
  23. Wang K, Li Z, Zhang Y. (2022). Speckle Reduction in Ultrasound Images of the Common Carotid Artery Based on Integer and Fractional-Order Total Variation. Ultrason Imaging,44(4):123-141.
  24. Wang K, Pu Y, Zhang Y, Wang P. Fully Automatic Measurement of Intima-Media Thickness in Ultrasound Images of the Common Carotid Artery Based on Improved Otsu's Method and Adaptive Wind Driven Optimization. (2020) Ultrason Imaging, Nov;42(6):245-260.
  25. Adrian JY, et al. "Walled carotid bifurcation phantoms for imaging investigations of vessel wall motion and blood flow dynamics." IEEE transactions on ultrasonics, ferroelectrics, and frequency control 63.11 (2016): 1852-1864.
  26. F. Turk, M. Luy and N. Barışçı, " Comparison of Unet and Unet-ResNet Models for Kidney Tumor Segmentation," 2019 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), 2019, pp. 1-5, doi: 10.1109/ISMSIT.2019.8932725.
  27. Shodiq, Moh Nur, et al. "Ultrasound image segmentation for deep vein thrombosis using UNet-CNN based on denoising filter." 2022 IEEE international conference on imaging systems and techniques (IST). IEEE, 2022.
  28. Alblas, D., Brune, C., & Wolterink, J. M. (2022, April). Deep-learning-based carotid artery vessel wall segmentation in black-blood MRI using anatomical priors. In Medical Imaging 2022: Image Processing (Vol. 12032, pp. 237-244). SPIE.
  29. Groves, L. A., VanBerlo, B., Veinberg, N., Alboog, A., Peters, T. M., & Chen, E. C. (2020). Automatic segmentation of the carotid artery and internal jugular vein from 2D ultrasound images for 3D vascular reconstruction. International journal of computer assisted radiology and surgery, 15, 1835-1846.
  30. Saba, L., Biswas, M., Suri, H. S., Viskovic, K., Laird, J. R., Cuadrado-Godia, E.,. & Suri, J. S. (2019). Ultrasound-based carotid stenosis measurement and risk stratification in diabetic cohort: a deep learning paradigm. Cardiovascular diagnosis and therapy, 9(5), 439.
  31. Ronneberger, O., Fischer, P., & Brox, T. (2015, October). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention (pp. 234-241). Cham: Springer international publishing.
  32. Bhagawati, M., Paul, S., Agarwal, S., Protogeron, A., Sfikakis, P. P., Kitas, G. D.,. & Suri, J. S. (2023). Cardiovascular disease/stroke risk stratification in deep learning framework: a review. Cardiovascular Diagnosis and Therapy, 13(3), 557.
  33. Liu, M., Gao, W., Song, D., Dong, Y., Hong, S., Cui, C.,. & Dong, F. (2024). A deep learning-based calculation system for plaque stenosis severity on common carotid artery of ultrasound images. Vascular, 17085381241246312.
  34. Saba, L., Biswas, M., Suri, H. S., Viskovic, K., Laird, J. R., Cuadrado-Godia, E.,. & Suri, J. S. (2019). Ultrasound-based carotid stenosis measurement and risk stratification in diabetic cohort: a deep learning paradigm. Cardiovascular diagnosis and therapy, 9(5), 439.