(49-5) 10 * << * >> * Russian * English * Content * All Issues

Uncovering unstable plaques: deep learning segmentation in optical coherence tomography
V.V. Laptev 1, V.V. Danilov 2,3, E.A. Ovcharenko 1, K.Yu. Klyshnikov 1, A.Yu. Kolesnikov 1, A.A. Arnt 1, I.S. Bessonov 4, N.V. Litvinyuk 5, N.A. Kochergin 1

1 Research Institute for Complex Issues of Cardiovascular Diseases,
Academician L.S. Barbarash Boulevard 6,Kemerovo, 650002, Russia;
2 Pompeu Fabra University,
Calle de la Mercè 12, Barcelona, 08002, Spain;
3 Quantori,
1 Broadway, Cambridge, MA 02142, United States;
4 Tyumen Cardiology Research Center, Russian Academy of Science,
Melnikayte Street 111, Tyumen, 625026, Russia;
5 Krasnoyarsk Regional Clinical Hospital,
Partizan Zheleznyak Street 3K, Krasnoyarsk, 660022, Russia

 PDF, 3394 kB

DOI: 10.18287/2412-6179-CO-1571

Pages: 775-793.

Full text of article: English language.

Abstract:
One of the primary objectives in modern cardiology is to analyze the risk of acute coronary syndrome (ACS) in patients with ischemic heart disease to develop preventive measures and determine the optimal treatment strategy. This study aims to develop an automated approach for the timely detection of significant, rupture-prone coronary lesions (unstable plaques) to prevent ACS. We collected optical coherence tomography (OCT) volumes from 34 patients, with each OCT volume representing an RGB video of 704×704 pixels per frame, acquired over a certain depth. After filtering and manual annotation, 11,771 images were obtained to identify four types of objects: Lumen, Fibrous cap, Lipid core, and Vasa vasorum. To segment and quantitatively assess these features, we configured and evaluated the performance of nine deep learning models (U-Net, LinkNet, FPN, PSPNet, DeepLabV3, PAN, MA-Net, U-Net++, DeepLabV3++). The study presents two approaches for training the aforementioned models: 1) detecting all analyzed objects and 2) applying a cascade of neural network models to separately detect subsets of objects. The results demonstrate the superiority of the cascade approach for analyzing OCT images. The combined use of PAN and MA-Net models achieved the highest average Dice similarity coefficient (DSC) of 0.721.

Keywords:
semantic segmentation, deep learning, vascular segmentation, unstable plaques, optical coherence tomography.

Citation:
Laptev VV, Danilov VV, Ovcharenko EA, Klyshnikov KY, Kolesnikov AY, Arnt AA, Bessonov IS, Litvinyuk NV, Kochergin NA. Uncovering unstable plaques: deep learning segmentation in optical coherence tomography. Computer Optics 2025; 49(5): 775-793. DOI: 10.18287/2412-6179-CO-1571.

Acknowledgements:
The study was supported by the Russian Science Foundation through grant № 23-75-10009, titled “Development of an automated system for detecting unstable plaques utilizing optical coherence tomography and deep learning methods”. Further details about the grant can be found at https://rscf.ru/project/23-75-10009.

References:
  1. Muller JE, Tofler GH, Stone PH. Circadian variation and triggers of onset of acute cardiovascular disease. Circulation 1989;79(4):733-743. DOI: 10.1161/01.CIR.79.4.733.
  2. Ambrose JA, Winters SL, Arora RR, Eng A, Riccio A, Gorlin R, Fuster V. Angiographic evolution of coronary artery morphology in unstable angina. J AmCollCardiol 1986;7(3):472-478. DOI: 10.1016/S0735-1097(86)80455-7.
  3. Giroud D, Li JM, Urban P, Meier B, Rutishauser W. Relation of the site of acute myocardial infarction to the most severe coronary arterial stenosis at prior angiography. Am J Cardiol 1992;69(8):729-732. DOI: 10.1016/0002-9149(92)90495-K.
  4. Okura H, Kobayashi Y, Sumitsuji S, et al. Effect of culprit-lesion remodeling versus plaque rupture on three-year outcome in patients with acute coronary syndrome. Am J Cardiol 2009;103(6):791-795. DOI: 10.1016/j.amjcard.2008.11.030.
  5. Motoyama S, Sarai M, Harigaya H, et al. Computed tomographic angiography characteristics of atherosclerotic plaques subsequently resulting in acute coronary syndrome. J Am Coll Cardiol 2009; 54(1): 49-57. DOI: 10.1016/j.jacc.2009.02.068.
  6. Alsheikh-Ali AA. The vulnerable atherosclerotic plaque: scope of the literature. AnnInternMed 2010;153(6):387-395. DOI: 10.7326/0003-4819-153-6-201009210-00272.
  7. Danilov VV, KlyshnikovKYu, Gerget OM, Skirnevsky IP, Kutikhin AG, Shilov AA, Ganyukov VI, Ovcharenko EA. Aortography keypoint tracking for transcatheter aortic valve implantation based on multi-task learning. Front Cardiovasc Med 2021;8:697737. DOI: 10.3389/fcvm.2021.697737.
  8. Shi F, Wang J, Shi J, Wu Z, Wang Q, Tang Z. Review of artificial intelligence techniques in imaging data acquisition, segmentation, and diagnosis for covid-19. IEEE RevBiomedEng 2021;14:4-15. DOI: 10.1109/RBME.2020.2987975.
  9. Qaiser T, Tsang Y-W, Taniyama D, Sakamoto N, Nakane K, Epstein D, Rajpoot N. Fast and accurate tumor segmentation of histology images using persistent homology and deep convolutional features. Med Image Anal 2019; 55: 1-14. DOI: 10.1016/j.media.2019.03.014.
  10. Laptev VV, Kochergin NA. Application of modern object tracking technologies to the task of aortography key point detection in transcatheter aortic valve implantation. Sci Vis 2024;16(2):106-115. DOI: 10.26583/sv.16.2.09.
  11. Abdelsamea MM, Pitiot A, Grineviciute RB, Besusparis J, Laurinavicius A, Ilyas M. A cascade-learning approach for automated segmentation of tumour epithelium in colorectal cancer. Expert SystAppl 2019;118:539-552. DOI: 10.1016/j.eswa.2018.10.030.
  12. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In Book: Navab N, Hornegger J, Wells WM, Frangi AF, eds. Medical image computing and computer-assisted intervention – MICCAI 2015. 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III. Cham: Springer International Publishing Switzerland; 2015: 234-241. DOI: 10.1007/978-3-319-24574-4_28.
  13. Chaurasia A, Culurciello E. LinkNet: Exploiting encoder representations for efficient semantic segmentation. 2017 IEEE Visual Communications and Image Processing (VCIP) 2017: 1-4. DOI: 10.1109/VCIP.2017.8305148.
  14. Kirillov A, He K, Girshick R, Dollár P. A unified architecture for instance and semantic segmentation. 2017. Source: <http://presentations.cocodataset.org/COCO17-Stuff-FAIR.pdf>.
  15. Zhao H, Shi J, Qi X, Wang X, Jia J. Pyramid scene parsing network. arXiv Preprint. 2016. Source: <https://arxiv.org/abs/1612.01105>. DOI: 10.48550/arXiv.1612.01105.
  16. Chen L-C, Papandreou G, Schroff F, Adam H. Rethinking atrous convolution for semantic image segmentation. arXiv Preprint. 2017. Source: <https://arxiv.org/abs/1706.05587>. DOI: 10.48550/arXiv.1706.05587.
  17. Li H, Xiong P, An J, Wang L. Pyramid attention network for semantic segmentation. arXiv Preprint. 2018. Source: <https://arxiv.org/abs/1805.10180>. DOI: 10.48550/arXiv.1805.10180.
  18. Fan T, Wang G, Li Y, Wang H. MA-Net: A multi-scale attention network for liver and tumor segmentation. IEEE Access 2020; 8: 179656-179665. DOI: 10.1109/ACCESS.2020.3025372.
  19. Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J. UNet++: A nested U-Net architecture for medical image segmentation. In Book: Stoyanov D, Taylor Z, Carneiro G, et al, eds. Deep learning in medical image analysis and multimodal learning for clinical decision support. 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings. Cham, Switzerland: Springer Nature Switzerland AG; 2018: 3-11. DOI: 10.1007/978-3-030-00889-5_1.
  20. Chen L-C, Zhu Y, Papandreou G, Schroff F, Adam H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Book: Ferrari V, Hebert M, Sminchisescu C, Weiss Y, eds. Computer vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part VII. Cham, Switzerland: Springer Nature Switzerland AG; 2018: 833-851. DOI: 10.1007/978-3-030-01234-2_49.
  21. Weiss K, Khoshgoftaar TM, Wang D. A survey of transfer learning. J Big Data 2016; 3: 9. DOI: 10.1186/s40537-016-0043-6.
  22. Buslaev A, Iglovikov VI, Khvedchenya E, Parinov A, Druzhinin M, Kalinin AA. Albumentations: Fast andflexibleimageaugmentations. Information 2020;11(2):125. DOI: 10.3390/info11020125.
  23. Yonetsu T, Jang I-K. Cardiac optical coherence tomography: History, current status, and perspective. JACC Asia 2024; 4(2): 89-107. DOI: 10.1016/j.jacasi.2023.10.001.
  24. Tagieva NR, Shakhnovich RM, Mironov VM, Ruda MYa. Invasive methods of detection of unstable atherosclerotic plaques in coronary arteries. Kardiologiia 2014; 54(11): 46-56. DOI: 10.18565/cardio.2014.11.46-56.
  25. Kochergin NA, Kochergina AM, Ganyukov VI, Barbarash OL. Predictors of coronary plaque vulnerability in patients with stable coronary artery disease. Kardiologiia 2020; 60(10): 20-26. DOI: 10.18087/cardio.2020.10.n1188.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20