Segmentation of Structural Components of Atherosclerotic Plaques on OCT Images Using Deep Machine Learning

Aim        To develop an optimal method for automated segmentation of atherosclerotic plaque structural components in optical coherence tomography (OCT) images using an ensemble of deep learning neural network models based on a comparison of nine artificial neural network architectures.

Material and methods          This study utilized a multidisciplinary OCT dataset obtained from examinations of 103 patients. Each OCT session was annotated as a set of two-dimensional binary masks corresponding to the pixel boundaries of four key morphological features of plaques: vascular lumen, fibrous cap, lipid core, and microvessels. Nine deep learning models, including U-Net, DeepLabV3, and others, were used to segment the anatomical structures. Model hyperparameters were tuned using Bayesian optimization, and the performance was assessed using the Dice Similarity Coefficient (DSC) metric.

Results    The models demonstrated high segmentation accuracy for the vascular lumen (DSC: 0.987) and moderate accuracy for the fibrous cap (DSC: 0.736) and lipid core (DSC: 0.751). Microvessel segmentation proved more challenging, with a final DSC accuracy of 61%. A weighted ensemble of models, accounting for the uneven representation of different morphological structures and model confidence, achieved an average DSC of 88.2%, which significantly improved the overall accuracy compared to individual models. This accuracy value exceeds those of all individual models, including the highest DSC values of 0.784 (for microvessels) and 0.751 (for lipid core), indicating a consistent improvement in the segmentation accuracy by integrating the models.

Conclusion            The study confirms the effectiveness of the proposed strategy for segmentation of atherosclerotic plaques in OCT images. This strategy is based on using specialized models for various morphological features and a weighted ensemble adapted to the uneven representation of different morphological structures and morphological complexity. This approach provided a high segmentation accuracy despite the pronounced inequality in the representation of classes. The study results can contribute to the development of decision support methods in cardiology aimed at improving diagnostic accuracy and treatment of cardiovascular diseases.

1. Zibaeenejad F, Mohammadi SS, Sayadi M, Safari F, Zibaeenezhad MJ. Ten-year atherosclerosis cardiovascular disease (ASCVD) risk score and its components among an Iranian population: a cohort-based cross-sectional study. BMC Cardiovascular Disorders. 2022;22(1):162. DOI: 10.1186/s12872-022-02601-0

2. Kochergin N.A., Kochergina A.M., Ganjukov V.I., Barbarash O.L. Vulnerable atherosclerotic plaques of coronary arteries in patients with stable coronary artery disease. Complex Issues of Cardiovascular Diseases. 2018;7(3):65–71. DOI: 10.17802/2306-1278-2018-7-3-65-71

3. Vaduganathan M, Mensah GA, Turco JV, Fuster V, Roth GA. The Global Burden of Cardiovascular Diseases and Risk. Journal of the American College of Cardiology. 2022;80(25):2361–71. DOI: 10.1016/j.jacc.2022.11.005

4. Araki M, Yonetsu T, Kurihara O, Nakajima A, Lee H, Soeda T et al. Predictors of Rapid Plaque Progression. JACC: Cardiovascular Imaging. 2021;14(8):1628–38. DOI: 10.1016/j.jcmg.2020.08.014

5. Kochergin N.A., Kochergina A.M., Khorlampenko A.A., Ganyukov V.I., Shilov A.A., Barbarash O.L. Vulnerable atherosclerotic plaques of coronary arteries in patients with stable coronary artery disease: 12-months followup. Kardiologiia. 2020;60(2):69–74. DOI: 10.18087/cardio.2020.2.n467

6. Kowara M, Cudnoch-Jedrzejewska A. Different Approaches in Therapy Aiming to Stabilize an Unstable Atherosclerotic Plaque. International Journal of Molecular Sciences. 2021;22(9):4354. DOI: 10.3390/ijms22094354

7. Bentzon JF, Otsuka F, Virmani R, Falk E. Mechanisms of Plaque Formation and Rupture. Circulation Research. 2014;114(12):1852–66. DOI: 10.1161/CIRCRESAHA.114.302721

8. Baruś P, Modrzewski J, Gumiężna K, Dunaj P, Głód M, Bednarek A et al. Comparative Appraisal of Intravascular Ultrasound and Optical Coherence Tomography in Invasive Coronary Imaging: 2022 Update. Journal of Clinical Medicine. 2022;11(14):4055. DOI: 10.3390/jcm11144055

9. Kochergin N.A., Kochergina A.M. Potential of optical coherence tomography and intravascular ultrasound in the detection of vulnerable plaques in coronary arteries. Cardiovascular Therapy and Prevention. 2022;21(1):101–6. DOI: 10.15829/1728-8800-2022-2909

10. Kochergin N.A., Kochergina A.M. Intravascular Ultrasound Studies and the Vulnerable Atherosclerotic Plaque (Literature Review). Medical Visualization. 2017;21(4):82–7. DOI: 10.24835/1607-0763-2017-4-82-87

11. Zaghloul A, Iorgoveanu C, Balakumaran K, Balanescu DV, Donisan T. Limitations of Coronary Computed Tomography Angiography in Predicting Acute Coronary Syndrome in a Low to Intermediate-risk Patient with Chest Pain. Cureus. 2018;10(5):e2649. DOI: 10.7759/cureus.2649

12. Chamié D, Costa JR, Damiani LP, Siqueira D, Braga S, Costa R et al. Optical Coherence Tomography Versus Intravascular Ultrasound and Angiography to Guide Percutaneous Coronary Interventions: The iSIGHT Randomized Trial. Circulation: Cardiovascular Interventions. 2021;14(3):e009452. DOI: 10.1161/CIRCINTERVENTIONS.120.009452

13. Lee J, Gharaibeh Y, Zimin VN, Kim JN, Hassani NS, Dallan LAP et al. Plaque Characteristics Derived from Intravascular Optical Coherence Tomography That Predict Cardiovascular Death. Bioengineering. 2024;11(8):843. DOI: 10.3390/bioengineering11080843

14. Williams MC, Weir-McCall JR, Baldassarre LA, De Cecco CN, Choi AD, Dey D et al. Artificial Intelligence and Machine Learning for Cardiovascular Computed Tomography (CCT): A White Paper of the Society of Cardiovascular Computed Tomography (SCCT). Journal of Cardiovascular Computed Tomography. 2024;18(6):519–32. DOI: 10.1016/j.jcct.2024.08.003

15. Athanasiou LS, Bourantas CV, Rigas G, Sakellarios AI, Exarchos TP, Siogkas PK et al. Methodology for fully automated segmentation and plaque characterization in intracoronary optical coherence tomography images. Journal of Biomedical Optics. 2014;19(2):026009. DOI: 10.1117/1. JBO.19.2.026009

16. Kolluru C, Prabhu D, Gharaibeh Y, Bezerra H, Guagliumi G, Wilson D. Deep neural networks for A-line-based plaque classification in coronary intravascular optical coherence tomography images. Journal of Medical Imaging. 2018;5(4):044504. DOI: 10.1117/1.JMI.5.4.044504

17. Lee J, Gharaibeh Y, Kolluru C, Zimin VN, Dallan LAP, Kim JN et al. Segmentation of Coronary Calcified Plaque in Intravascular OCT Images Using a Two-Step Deep Learning Approach. IEEE Access. 2020;8:225581–93. DOI: 10.1109/ACCESS.2020.3045285

18. Athanasiou LS, Olender ML, De La Torre Hernandez JM, Ben-Assa E, Edelman ER. A deep learning approach to classify atherosclerosis using intracoronary optical coherence tomography. Medical Imaging 2019: Computer-Aided Diagnosis. 2019. Av. at: https://dspace.mit.edu/bitstream/ handle/1721.1/126580/109500N.pdf? DOI: 10.1117/12.2513078.

19. Shi P, Xin J, Zheng N. A-line-based thin-cap fibroatheroma detection with multi-view IVOCT images using multi-task learning and contrastive learning. Journal of the Optical Society of America A. 2022;39(12):2298. DOI: 10.1364/JOSAA.464303

20. Supervisely. Supervisely: Curate, Label and Build Production Models in One Platform. [Internet] Available at: https://supervisely.com/

21. Danilov VV, Litmanovich D, Proutski A, Kirpich A, Nefaridze D, Karpovsky A et al. Automatic scoring of COVID-19 severity in X-ray imaging based on a novel deep learning workflow. Scientific Reports. 2022;12(1):12791. DOI: 10.1038/s41598-022-15013-z

22. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. - Cham: Springer International Publishing; 2015. - P. 234-241. DOI: 10.1007/978-3-319-24574-4_28.

23. Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J. UNet++: A Nested U-Net Architecture for Medical Image Segmentation. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support - Cham: Springer International Publishing; 2018. - P. 3-11. DOI: 10.1007/978-3-030-00889-5_1.

24. Chen L-C, Papandreou G, Schroff F, Adam H. Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv. 2017. Av. at: https://arxiv.org/abs/1706.05587. DOI: 10.48550/ARXIV.1706.05587.

25. Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018;40(4):834–48. DOI: 10.1109/TPAMI.2017.2699184

26. Kirillov A, He K, Girshick R, Dollár P. A unified architecture for instance and semantic segmentation. Av. at: http://presentations.cocodataset.org/COCO17-Stuff-FAIR.pdf.

27. Chaurasia A, Culurciello E. LinkNet: Exploiting encoder representations for efficient semantic segmentation. 2017 IEEE Visual Communications and Image Processing (VCIP). 2017. Av. at: https://arxiv.org/ pdf/1707.03718. DOI: 10.1109/VCIP.2017.8305148.

28. Zhao H, Shi J, Qi X, Wang X, Jia J. Pyramid Scene Parsing Network. 2017. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). P. 6230-6239. DOI: 10.1109/CVPR.2017.660.

29. Li K, Wu Z, Peng K-C, Ernst J, Fu Y. Tell Me Where to Look: Guided Attention Inference Network. 2018. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. P. 9215-9223. DOI: 10.1109/CVPR.2018.00960.

30. Fan T, Wang G, Li Y, Wang H. MA-Net: A Multi-Scale Attention Network for Liver and Tumor Segmentation. IEEE Access. 2020;8:179656–65. DOI: 10.1109/ACCESS.2020.3025372

31. Li L, Jamieson K, DeSalvo G, Rostamizadeh A, Talwalkar A. Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization. Journal of Machine Learning Research. 2016;18(1):6765–816. DOI: 10.48550/ARXIV.1603.06560

32. Falkner S, Klein A, Hutter F. BOHB: Robust and Efficient Hyperparameter Optimization at Scale. arXiv. 2018. Av. at: https://arxiv.org/pdf/1807.01774. DOI: 10.48550/arXiv.1807.01774.

33. Buslaev A, Iglovikov VI, Khvedchenya E, Parinov A, Druzhinin M, Kalinin AA. Albumentations: Fast and Flexible Image Augmentations. Information. 2020;11(2):125. DOI: 10.3390/info11020125

34. Virani SS, Newby LK, Arnold SV, Bittner V, Brewer LC, Demeter SH et al. 2023 AHA/ACC/ACCP/ASPC/NLA/PCNA Guideline for the Management of Patients With Chronic Coronary Disease: A Report of the American Heart Association/American College of Cardiology Joint Committee on Clinical Practice Guidelines. Circulation. 2023;148(9):e9–119. DOI: 10.1161/CIR.0000000000001168

35. Byrne RA, Rossello X, Coughlan JJ, Barbato E, Berry C, Chieffo A et al. 2023 ESC Guidelines for the management of acute coronary syndromes. European Heart Journal. 2023;44(38):3720–826. DOI: 10.1093/eurheartj/ehad191

36. Kedhi E, Berta B, Roleder T, Hermanides RS, Fabris E, IJsselmuiden AJJ et al. Thin-cap fibroatheroma predicts clinical events in diabetic patients with normal fractional flow reserve: the COMBINE OCT–FFR trial. European Heart Journal. 2021;42(45):4671–9. DOI: 10.1093/eurheartj/ehab433

37. Prati F, Romagnoli E, Gatto L, La Manna A, Burzotta F, Ozaki Y et al. Relationship between coronary plaque morphology of the left anterior descending artery and 12 months clinical outcome: the CLIMA study. European Heart Journal. 2020;41(3):383–91. DOI: 10.1093/eurheartj/ehz520

38. Kochergin N.A., Kochergina A.M., Ganyukov V.I., Barbarash O.L. Vulnerable Plaques in Patients with Stable Coronary Artery Disease. Horizons in World Cardiovascular Research. 2021;21:187–203

39. Park S-J, Ahn J-M, Kang D-Y, Yun S-C, Ahn Y-K, Kim W-J et al. Preventive percutaneous coronary intervention versus optimal medical therapy alone for the treatment of vulnerable atherosclerotic coronary plaques (PREVENT): a multicentre, open-label, randomised controlled trial. The Lancet. 2024;403(10438):1753–65. DOI: 10.1016/S0140-6736(24)00413-6

40. Kini AS, Vengrenyuk Y, Yoshimura T, Matsumura M, Pena J, Baber U et al. Fibrous Cap Thickness by Optical Coherence Tomography In Vivo. Journal of the American College of Cardiology. 2017;69(6):644–57. DOI: 10.1016/j.jacc.2016.10.028

41. Lee J, Kim JN, Gomez-Perez L, Gharaibeh Y, Motairek I, Pereira GTR et al. Automated Segmentation of Microvessels in Intravascular OCT Images Using Deep Learning. Bioengineering. 2022;9(11):648. DOI: 10.3390/bioengineering9110648