Display options
Cite
Iyer K, Najarian CP, Fattah AA, et al. AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography. Sci Rep. 2021;11(1):18066doi: 10.1038/s41598-021-97355-8.
Iyer, K., Najarian, C. P., Fattah, A. A., Arthurs, C. J., Soroushmehr, S. M. R., Subban, V., Sankardas, M. A., Nadakuditi, R. R., Nallamothu, B. K., & Figueroa, C. A. (2021). AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography. Scientific reports, 11(1), 18066. https://doi.org/10.1038/s41598-021-97355-8
Iyer, Kritika, et al. "AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography." Scientific reports vol. 11,1 (2021): 18066. doi: https://doi.org/10.1038/s41598-021-97355-8
Iyer K, Najarian CP, Fattah AA, Arthurs CJ, Soroushmehr SMR, Subban V, Sankardas MA, Nadakuditi RR, Nallamothu BK, Figueroa CA. AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography. Sci Rep. 2021 Sep 10;11(1):18066. doi: 10.1038/s41598-021-97355-8. PMID: 34508124; PMCID: PMC8433338.
Copy Download .nbib Format: NLM
Share it on

Sci Rep. 2021 Sep 10;11(1):18066. doi: 10.1038/s41598-021-97355-8.

AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography.

Scientific reports

Kritika Iyer, Cyrus P Najarian, Aya A Fattah, Christopher J Arthurs, S M Reza Soroushmehr, Vijayakumar Subban, Mullasari A Sankardas, Raj R Nadakuditi, Brahmajee K Nallamothu, C Alberto Figueroa

Affiliations

  1. University of Michigan, 500 S State St, Ann Arbor, MI, 48109, USA.
  2. King's College London, Strand, London, UK.
  3. Madras Medical Mission, Chennai, Tamil Nadu, India.
  4. University of Michigan, 500 S State St, Ann Arbor, MI, 48109, USA. [email protected].

PMID: 34508124 PMCID: PMC8433338 DOI: 10.1038/s41598-021-97355-8

Abstract

Coronary Artery Disease (CAD) is commonly diagnosed using X-ray angiography, in which images are taken as radio-opaque dye is flushed through the coronary vessels to visualize the severity of vessel narrowing, or stenosis. Cardiologists typically use visual estimation to approximate the percent diameter reduction of the stenosis, and this directs therapies like stent placement. A fully automatic method to segment the vessels would eliminate potential subjectivity and provide a quantitative and systematic measurement of diameter reduction. Here, we have designed a convolutional neural network, AngioNet, for vessel segmentation in X-ray angiography images. The main innovation in this network is the introduction of an Angiographic Processing Network (APN) which significantly improves segmentation performance on multiple network backbones, with the best performance using Deeplabv3+ (Dice score 0.864, pixel accuracy 0.983, sensitivity 0.918, specificity 0.987). The purpose of the APN is to create an end-to-end pipeline for image pre-processing and segmentation, learning the best possible pre-processing filters to improve segmentation. We have also demonstrated the interchangeability of our network in measuring vessel diameter with Quantitative Coronary Angiography. Our results indicate that AngioNet is a powerful tool for automatic angiographic vessel segmentation that could facilitate systematic anatomical assessment of coronary stenosis in the clinical workflow.

© 2021. The Author(s).

References

  1. Lancet. 1986 Feb 8;1(8476):307-10 - PubMed
  2. Neural Comput. 2017 Sep;29(9):2352-2449 - PubMed
  3. Am J Cardiol. 1998 May 1;81(9):1110-5 - PubMed
  4. N Engl J Med. 2002 Jun 6;346(23):1773-80 - PubMed
  5. Circulation. 2013 Jan 1;127(1):e6-e245 - PubMed
  6. Sci Rep. 2019 Nov 15;9(1):16897 - PubMed
  7. Comput Methods Programs Biomed. 2021 Mar;200:105897 - PubMed
  8. IEEE Trans Med Imaging. 1997 Oct;16(5):468-82 - PubMed
  9. Med Image Anal. 2019 Dec;58:101556 - PubMed
  10. IEEE Trans Biomed Eng. 2020 May;67(5):1338-1348 - PubMed
  11. Am J Cardiol. 2002 Apr 15;89(8):913-8 - PubMed
  12. IEEE Trans Inf Technol Biomed. 2012 Nov;16(6):1332-40 - PubMed
  13. Eur Heart J. 2016 Nov 7;37(42):3232-3245 - PubMed
  14. Stat Med. 2009 Nov 10;28(25):3083-107 - PubMed
  15. Circulation. 1987 Feb;75(2):452-60 - PubMed
  16. Physiol Rev. 1983 Jan;63(1):1-205 - PubMed
  17. J Am Coll Cardiol. 1993 Oct;22(4):1068-74 - PubMed
  18. IEEE Trans Biomed Eng. 2011 Apr;58(4):1023-32 - PubMed
  19. Front Cardiovasc Med. 2019 Jan 22;6:1 - PubMed
  20. Circulation. 1990 Dec;82(6):2231-4 - PubMed
  21. Ann Transl Med. 2016 Jul;4(13):256 - PubMed
  22. IEEE Trans Pattern Anal Mach Intell. 2017 Dec;39(12):2481-2495 - PubMed
  23. IEEE Trans Med Imaging. 2000 Apr;19(4):318-36 - PubMed

Publication Types

Grant support