Ultrasound Intima-Media Complex (IMC) Segmentation Using Deep Learning Models
Source abstract
Abstract
Common carotid intima-media thickness (CIMT) is a common measure of atherosclerosis, often assessed through carotid ultrasound images. However, the use of deep learning methods for medical image analysis, segmentation and CIMT measurement in these images has not been extensively explored. This study aims to evaluate the performance of four recent deep learning models, including a convolutional neural network (CNN), a self-organizing operational neural network (self-ONN), a transformer-based network and a pixel difference convolution-based network, in segmenting the intima-media complex (IMC) using the CUBS dataset, which includes ultrasound images acquired from both sides of the neck of 1088 participants. The results show that the self-ONN model outperforms the conventional CNN-based model, while the pixel difference- and transformer-based models achieve the best segmentation performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Cardiovascular Health and Disease Prevention · Cerebrovascular and Carotid Artery Diseases · Reliability and Agreement in Measurement
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Engineering, Qatar University, Doha P.O. Box 2713, Qatar
Department of Electrical Engineering, Qatar University, Doha P.O. Box 2713, Qatar
Cybersecurity and Data Analytics Research Center, University of Sharjah, Sharjah 27272, United Arab Emirates
Department of Basic Medical Sciences, College of Medicine, Qatar University, Doha P.O. Box 2713, Qatar
Funding
Qatar University Internal
References (47)
Show source-provided references
1. Carotid artery ultrasound image analysis: A review of the literature10.1177/0954411919900720 ↗
2. Vila, M.D.M., Remeseiro, B., Grau, M., Elosua, R., and Igual, L. (2022). Handbook of Artificial Intelligence in Healthcare, Springer.
3. BEMD-3DCNN-based method for COVID-19 detection10.1016/j.compbiomed.2021.105188 ↗
4. Integrated system for the complete segmentation of the common carotid artery bifurcation in ultrasound images10.1007/978-3-642-41142-7_30 ↗
5. Christodoulou, L., Loizou, C.P., Spyrou, C., Kasparis, T., and Pantziaris, M. (2012, January 2–4). Full-automated system for the segmentation of the common carotid artery in ultrasound images. Proceedings of the 2012 IEEE 5th International Symposium on Communications, Control and Signal Processing, Rome, Italy.10.1109/ISCCSP.2012.6217824 ↗
6. Automated segmental-IMT measurement in thin/thick plaque with bulb presence in carotid ultrasound from multiple scanners: Stroke risk assessment10.1016/j.cmpb.2017.01.009 ↗
7. Madipalli, P., Kotta, S., Dadi, H., Nagaraj, Y., Asha, C.S., and Narasimhadhan, A.V. (2018, January 25–28). Automatic Segmentation of Intima Media Complex in Common Carotid Artery using Adaptive Wind Driven Optimization. Proceedings of the 2018 Twenty Fourth National Conference on Communications (NCC), Hyderbad, India.10.1109/NCC.2018.8600240 ↗
8. Automatic Segmentation of Intima Media Complex in Carotid Ultrasound Images Using Support Vector Machine10.1007/s13369-018-3549-8 ↗
9. Two-stage artificial intelligence model for jointly measurement of atherosclerotic wall thickness and plaque burden in carotid ultrasound: A screening tool for cardiovascular/stroke risk assessment10.1016/j.compbiomed.2020.103847 ↗
10. Su, Z., Liu, W., Yu, Z., Hu, D., Liao, Q., Tian, Q., Pietikainen, M., and Liu, L. (2021, January 11–17). Pixel difference networks for efficient edge detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.00507 ↗
11. Self-organized operational neural networks with generative neurons10.1016/j.neunet.2021.02.028 ↗
12. Gabbouj, M., Kiranyaz, S., Malik, J., Zahid, M.U., Ince, T., Chowdhury, M.E., Khandakar, A., and Tahir, A. (2022). Robust peak detection for holter ECGs by self-organized operational neural networks. IEEE Trans. Neural Netw. Learn. Syst., Early Access.10.1109/TNNLS.2022.3158867 ↗
13. Malik, J., Kiranyaz, S., and Gabbouj, M. (2020). Operational vs. convolutional neural networks for image denoising. arXiv.10.1007/s00521-020-04780-3 ↗
14. Real-time patient-specific ECG classification by 1D self-operational neural networks10.1109/TBME.2021.3135622 ↗
15. Robust biometric system using session invariant multimodal EEG and keystroke dynamics by the ensemble of self-ONNs10.1016/j.compbiomed.2022.105238 ↗
16. Soltanian, M., Malik, J., Raitoharju, J., Iosifidis, A., Kiranyaz, S., and Gabbouj, M. (2021, January 18–22). Speech command recognition in computationally constrained environments with a quadratic self-organized operational layer. Proceedings of the 2021 IEEE International Joint Conference on Neural Networks (IJCNN), Shenzhen, China.10.1109/IJCNN52387.2021.9534232 ↗
17. Operational neural networks10.1007/s00521-020-04780-3 ↗
18. Transformers in vision: A survey10.1145/3505244 ↗
19. DeepCrack: A deep hierarchical feature learning architecture for crack segmentation10.1016/j.neucom.2019.01.036 ↗
20. Refined edge detection with cascaded and high-resolution convolutional network10.1016/j.patcog.2023.109361 ↗
21. Segmentation of the common carotid intima-media complex in ultrasound images using active contours10.1109/TBME.2012.2214387 ↗
22. Constrained snake vs. conventional snake for carotid ultrasound automated IMT measurements on multi-center data sets10.1016/j.ultras.2012.03.005 ↗
23. Ceccarelli, M., Luca, N.D., and Morganella, A. (2006, January 14–19). An active contour approach to automatic detection of the intima-media thickness. Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, Toulouse, France.
24. Snakes based segmentation of the common carotid artery intima media10.1007/s11517-006-0140-3 ↗
25. Gutierrez, M.A., Pilon, P.E., Lage, S.G., Kopel, L., Carvalho, R.T., and Furuie, S.S. (2002, January 22–25). Automatic measurement of carotid diameter and wall thickness in ultrasound images. Proceedings of the Computers in Cardiology, Memphis, TN, USA.
26. Chan, R.C., Kaufhold, J., Hemphill, L.C., Lees, R.S., and Karl, W.C. (2000, January 24–27). Anisotropic edge-preserving smoothing in carotid B-mode ultrasound for improved segmentation and intima-media thickness (IMT) measurement. Proceedings of the Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163), Cambridge, MA, USA.
27. Characterization of a completely user-independent algorithm for carotid artery segmentation in 2-D ultrasound images10.1109/TIM.2007.900433 ↗
28. Automated Segmentation of Common Carotid Artery in Ultrasound Images10.1109/ACCESS.2022.3179402 ↗
29. A multiscale dynamic programming procedure for boundary detection in ultrasonic artery images10.1109/42.836372 ↗
30. A new automated computerized analyzing system simplifies readings and reduces the variability in ultrasound measurement of intima-media thickness10.1161/01.STR.28.11.2195 ↗
31. Detections of arterial wall in sonographic artery images using dual dynamic programming10.1109/TITB.2008.926413 ↗
32. Gustavsson, T., Wendelhag, Q.L.I., and Wikstrand, J. (1994, January 25–28). A dynamic programming procedure for automated ultrasonic measurement of the carotid artery. Proceedings of the Computers in Cardiology, Bethesda, MD, USA.
33. Non-invasive evaluation of carotid artery wall thickness using improved dynamic programming technique10.1007/s11760-007-0048-x ↗
34. Boundary detection in carotid ultrasound images using dynamic programming and a directional Haar-like filter10.1016/j.compbiomed.2010.03.010 ↗
35. An automatic measurement system for the evaluation of carotid intima-media thickness10.1109/19.982968 ↗
36. Improved common carotid elasticity and intima-media thickness measurements from computer analysis of sequential ultrasound frames10.1016/S0021-9150(00)00461-5 ↗
37. Pramulen, A.S., Yuniarno, E.M., Nugroho, J., Sunarya, I.M.G., and Purnama, I.K.E. (2020, January 17–18). Carotid Artery Segmentation on Ultrasound Image using Deep Learning based on Non-Local Means-based Speckle Filtering. Proceedings of the 2020 International Conference on Computer Engineering, Network and Intelligent Multimedia (CENIM), Surabaya, Indonesia.10.1109/CENIM51130.2020.9298009 ↗
38. Automated deep learning-based paradigm for high-risk plaque detection in B-mode common carotid ultrasound scans: An asymptomatic Japanese cohort study
39. Lainé, N., Liebgott, H., Zahnd, G., and Orkisz, M. (2022). Carotid artery wall segmentation in ultrasound image sequences using a deep convolutional neural network. arXiv.10.1109/IUS54386.2022.9957590 ↗
40. Radovanovic, N., Dašić, L., Blagojevic, A., Sustersic, T., and Filipovic, N. (2023, January 01). Carotid Artery Segmentation Using Convolutional Neural Network in Ultrasound Images. Available online: https://scidar.kg.ac.rs/bitstream/123456789/16643/4/p8.pdf.
41. Ultrasound deep learning for monitoring of flow–vessel dynamics in murine carotid artery10.1016/j.ultras.2021.106636 ↗
42. Far wall plaque segmentation and area measurement in common and internal carotid artery ultrasound using U-series architectures: An unseen Artificial Intelligence paradigm for stroke risk assessment10.1016/j.compbiomed.2022.106017 ↗
43. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation10.1109/TMI.2018.2791488 ↗
44. CSM-Net: Automatic joint segmentation of intima-media complex and lumen in carotid artery ultrasound images10.1016/j.compbiomed.2022.106119 ↗
45. Twins: Revisiting the design of spatial attention in vision transformers
46. Elharrouss, O., Akbari, Y., Almaadeed, N., and Al-Maadeed, S. (2022). Backbones-review: Feature extraction networks for deep learning and deep reinforcement learning approaches. arXiv.
47. Carotid ultrasound boundary study (CUBS): An open multicenter analysis of computerized intima-media thickness measurement systems and their clinical impact10.1016/j.ultrasmedbio.2021.03.022 ↗