Image Based Diameter Measurement and Aneurysm Detection of the Ascending Aorta

  • Şerife KabaEmail author
  • Boran Şekeroğlu
  • Hüseyin Haci
  • Enver Kneebone
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 858)


Thoracic aortic aneurysm (TAA) is the enlargement of the aorta that needs surgical treatment. Radiologists measure the diameter of the aorta manually using a software ruler. Manual measurements may cause human errors which reduce accuracy of the results. Image processing techniques have been successful in analysing medical images and have been used on biomedical imaging applications. We proposed a novel system that measures the diameter of the ascending aorta using CT thorax (chest) images without considering other aorta-like shape. In this study, image processing techniques were used on these images to detect the aorta from series of slices and to calculate the diameter of the aorta. The axial plane has been used in these CT thorax scans. In this analysis, 20 patients were studied. In this research, the objective was on the measurement of the ascending aorta, this is because the majority of the thoracic aortic aneurysm’s which tend to be in the ascending aorta. On the analysed data, for the diameter of the ascending aorta measurements average of 2.3% (0.9 mm) difference was obtained between the manual measurements and the values measured by the system. This system can also provide online support to developing countries where there are not enough radiologists to analyse CT scans.


Aorta Aneurysm Thoracic aortic aneurysm Ascending aorta Descending aorta Image processing CT 


  1. 1.
    Tortora, G.J., Derrickson, B.H.: Principles of Anatomy and Physiology, 12th ed, pp. 760–831. Wiley, New Jersey (2009)Google Scholar
  2. 2.
    Saliba, E., Sia, Y.: The ascending aortic aneurysm: when to intervene? IJC Heart Vasculature 6, 91–100 (2015)CrossRefGoogle Scholar
  3. 3.
    Boxt, L., Abbara, S.: Cardiac Imaging: The Requisites, 4th edn, pp. 302–359. Elsevier, Philadelphia (2015)Google Scholar
  4. 4.
    Avila-Montes, O.C., Kurkure, U., Nakazato, R., Berman, D.S., Dey, D., Kakadiaris, I.A.: Segmentation of the thoracic aorta in noncontrast cardiac CT images. IEEE J. Biomed. Health Inform. 17, 936–949 (2013)CrossRefGoogle Scholar
  5. 5.
    Quint, L.E., Liu, P.S., Booher, A.M., Watcharotone, K., Myles, J.D.: Proximal thoracic aortic diameter measurements at CT: repeatability and reproducibility according to measurement method. Int. J. Cardiovasc. Imaging 29, 479–488 (2013)CrossRefGoogle Scholar
  6. 6.
    Sobotnicka, E., Wróbel, J., Sobotnicki, A.: Detection of aorta anatomical structures characterized by various levels of pixel intensity. In: MIXDES-23rd International Conference, Zabre, Poland, pp. 498–503, June 2016Google Scholar
  7. 7.
    Erbel, R., et al.: 2014 ESC Guidelines on the diagnosis and treatment of aortic diseases. Eur. Heart J. 35, 2873–2926 (2014)CrossRefGoogle Scholar
  8. 8.
    Pal, R., Gopal, A., Budoff, M.J.: Ascending aortic aneurysm by cardiac CT angiography. Clin. Cardiol. 32, E58–E59 (2009)CrossRefGoogle Scholar
  9. 9.
    Umbaugh, S.E.: Computer imaging: digital image analysis and processing. Boca Raton, Florida, pp. 143–145 (2005)Google Scholar
  10. 10.
    Zhu, X., Rangayyan, R.M.: Detection of the optic disc in images of the retina using the hough transform. In: 30th Annual International Conference of the Engineering in Medicine and Biology Society, pp. 3546–3549. IEEE, Canada, October 2018Google Scholar
  11. 11.
    Aquino, A., Gegúndez-Arias, M.E., Marín, D.: Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques. IEEE Trans. Med. Imaging 29, 1860–1869 (2010)CrossRefGoogle Scholar
  12. 12.
    Herman, E., Bleicken, S., Subburaj, Y., García-Sáez, A.J.: Automated analysis of giant unilamellar vesicles using circular hough transformation. Bioinformatics 30, 1747–1754 (2014)CrossRefGoogle Scholar
  13. 13.
    Satyasavithri, T., Devi, S.C.: Nodule detection from posterior and anterior chest radio graph using circular hough transform. In: CCIS 2nd International Conference of the IEE, Mathura, India, pp. 54–59, November 2016Google Scholar
  14. 14.
    Pavaloiu, I.B., Vasilateanu, A., Goga, N., Marin, I., Ungar, A., Pătrascu, I.: Teeth labelling from CBCT data using the circular hough transform. In: ISFEE 2016 International Symposium, Bucharest, Romania, pp. 1–4, June 2016Google Scholar
  15. 15.
    Goswami, B., Misra, S.K.: Analysis of various edge detection methods for X-ray images. In: ICEEOT International Conference of the Electrical, Electronics, and Optimization Techniques, pp. 2694–2699. IEEE, Chennai, March 2016Google Scholar
  16. 16.
    Li, Y., Chen, L., Huang, H., Li, X., Xu, W., Zheng, L., Huang, J.: Night-time lane markings recognition based on canny detection and hough transform. In: Proceedings of IEEE Device, (IUS) Real-time Computing and Robotics (RCAR), pp. 1–4 (2015)Google Scholar
  17. 17.
    Ma, T., Ma, J.: A sea-sky line detection method based on line segment detector and hough transform. In: 2nd International Conference of ICCC, pp. 700–703. IEEE, Wuhan, October 2016Google Scholar
  18. 18.
    Khan, N.H., Tegnander, E., Dreier, J.M., Eik-Nes, S., Torp, H., Kiss, G.: Automatic detection and measurement of fetal femur length using a portable ultrasound. ULTSYM, Trondheim, Norway, October 2015Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Şerife Kaba
    • 1
    Email author
  • Boran Şekeroğlu
    • 2
  • Hüseyin Haci
    • 3
  • Enver Kneebone
    • 4
  1. 1.Biomedical EngineeringNear East UniversityNicosiaTurkey
  2. 2.Information Systems EngineeringNear East UniversityNicosiaTurkey
  3. 3.Electrical and Electronic EngineeringNear East UniversityNicosiaTurkey
  4. 4.Radiology ConsultantLETAM EMAR Radiology ClinicNicosiaCyprus

Personalised recommendations