ABSTRACT
Acute coronary syndrome (ACS) caused by vulnerable plaques can lead to sudden death. The resolution of intravascular optical coherence tomography (IVOCT) is up to 10 μm, and it has become the first choice for vulnerable plaque recognition. However, it is time-consuming and burdensome for doctors to label vulnerable plaques manually. As a result, it is important to develop an automatic method for vulnerable plaque recognition in IVOCT images. This paper proposes a lightweight and real-time method to identify the main vulnerable plaque areas in IVOCT images. The accuracy rate, recall rate and overlap rate of this method on the test set are 84.8%, 90.1%, and 87.0% respectively, and the recognition quality is 87.2%. The results suggest that our method may assist doctors to recognize vulnerable plaque areas fast and accurately.
- Subban Vijayakumar, Owen Christopher Raffel. Optical coherence tomography: fundamentals and clinical utility[J]. Cardiovascular diagnosis and therapy, 2020, 10(5): 1389-1414.Google Scholar
- Y Taishi, Ik-Kyung J. Advances in Intravascular Imaging: New Insights into the Vulnerable Plaque from Imaging Studies[J]. Korean Circ J, 2018, 48(1): 1-15.Google ScholarCross Ref
- Usui Eisuke, Gary S Mintz, Tetsumin Lee, Prognostic impact of healed coronary plaque in non-culprit lesions assessed by optical coherence tomography[J]. Atherosclerosis, 2020, 309: 1-7.Google ScholarCross Ref
- Shenghua He, Zheng Jie, Maehara Akiko, Convolutional neural network based automatic plaque characterization for intracoronary optical coherence tomography images[M]. 2018: 107..Google Scholar
- Dario-A-B Oliveira, MacEdo Maysa-M-G, Nicz Pedro, Coronary calcification identification in optical coherence tomography using convolutional neural networks. Progress in Biomedical Optics and Imaging - Proceedings of SPIE[C]. Houston, TX, United states: SPIE, 2018.Google Scholar
- Nils, Gessert, Matthias, Automatic Plaque Detection in IVOCT Pullbacks Using Convolutional Neural Networks[J]. IEEE Transactions on Medical Imaging, 2019, 38(2): 426-434.Google ScholarCross Ref
- G-A Cheimariotis, Riga M, Toutouzas K, Automatic Characterization of Plaques and Tissue in IVOCT Images Using a Multi-step Convolutional Neural Network Framework[C]. Lhotska L, Sukupova L, Lacković I, Singapore: Springer Singapore, 2019: 261-265.Google Scholar
- R Liu, Zhang Y, Zheng Y, Automated Detection of Vulnerable Plaque for Intravascular Optical Coherence Tomography Images[J]. Cardiovascular Engineering and Technology, 2019, 10(4): 590-603.Google ScholarCross Ref
- Y Lecun, Bottou L. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.Google ScholarCross Ref
- Alex Krizhevsky, Sutskever Ilya, Hinton Geoffrey. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.Google ScholarDigital Library
- Karen Simonyan, Zisserman Andrew. Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. arXiv e-prints, 2014, 1409-1556.Google Scholar
- Christian Szegedy, Liu Wei, Jia Yangqing, Going Deeper with Convolutions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C]. Boston, MA, United states: IEEE Computer Society, 2015: 1-9.Google Scholar
- Kaiming He, Zhang Xiangyu, Ren Shaoqing, Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C]. Las Vegas, NV, United states: IEEE Computer Society, 2016: 770-778.Google ScholarCross Ref
- Dilbag Singh, Kumar Vijay, Kaur Manjit. Densely connected convolutional networks-based COVID-19 screening model[J]. Applied Intelligence, 2021, 51(5): 3044-3051.Google ScholarCross Ref
- Jie Hu, Shen Li, Albanie Samuel, Squeeze-and-Excitation Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.Google ScholarDigital Library
Index Terms
- SE-ResNet based vulnerable plaque recognition in IVOCT images
Recommendations
Analysis methods of coronary artery intravascular images: A review
AbstractCoronary artery disease is among one of the diseases human suffer most. Intravascular coronary arterial image analysis consists of denoising, segmentation, detection, and three-dimensional reconstruction, having a significant meaning ...
Investigation of fibrous cap stresses on vulnerable plaques leading to heart attacks
Recent Innovations on Biomedical EngineeringRupture-prone plaques in the coronary arteries, called ``vulnerable plaques'', are recognized as the key factor in acute myocardial infarction. Vulnerable plaques have a thin fibrous cap over a large fatty core and are highly susceptible to rupture. In ...
Characterization of Atherosclerotic Plaques and Mural Thrombi With Intravascular Ultrasound Elastography: A Potential Method Evaluated in an Aortic Rabbit Model and a Human Coronary Artery
Plaque rupture is correlated with the plaque morphology, composition, mechanical properties, and with the blood pressure. Whereas the geometry can accurately be assessed with intravascular ultrasound (IVUS) imaging, intravascular elastography (IVE) is ...
Comments