Abstract
One of the major causes of the coronary heart disease is vascular stenosis and thrombosis that is generally caused by development of fibrous plaques. Therefore, detection of a fibrous plaque in coronary arteries for the diagnosis and treatment of coronary heart disease is of clinical significance. Technical challenges are in reading the optical coherence tomography (OCT) images which is tedious and inaccurate. In response, we propose an automated coronary artery fibrous plaque detection method based on deep learning with Convolutional Neural Networks (CNN). We present our novel techniques of identifying a contracting path to capture the context and a symmetric expanding path that enables the precise localization. The algorithm utilizes the features of the contracting path and the expanding path, so that the merged features can present the context and accurate localization, and uses the multi-scale feature maps for detection. Experimental results show that the proposed method achieved a coincidence of 91.04%, accuracy of 94.12%, and recall of 94.12%. Compared with the previously published work the proposed method is advantageous in both accuracy and robustness.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ali, Y.M.B. (2009). Edge-based segmentation using robust evolutionary algorithm applied to medical images. Journal of Signal Processing Systems, 54(1-3), 231–238.
Athanasiou, L.S., Exarchos, T.P., Naka, K., Michalis, L.K., Prati, F., Fotiadis, D.I. (2011). Atherosclerotic plaque characterization in optical coherence tomography images. In: 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 4485–4488). IEEE.
Ballard, D.H. (1981). Generalizing the hough transform to detect arbitrary shapes. Pattern Recognition, 13 (2), 111–122.
Cheong, L.S., Lin, F., Seah, H.S., Qian, K., Zhao, F., Thong, P.S., Soo, K.C., Olivo, M., Kung, S.Y. (2009). Embedded computing for fluorescence confocal endomicroscopy imaging. Journal of Signal Processing Systems, 55(1-3), 217–228.
Chiew, W.M., Lin, F., Seah, H.S. (2016). A novel embedded interpolation algorithm with negative squared distance for real-time endomicroscopy. ACM Transactions on Embedded Computing Systems (TECS), 15(4), 75.
Chiew, W.M., Lin, F., Seah, H.S. (2017). Demons registration for in vivo and deformable laser scanning confocal endomicroscopy. Journal of Biomedical Optics, 22(9), 096,009.
De, J., Zhang, X., Lin, F., Cheng, L. (2017). Transduction on directed graphs via absorbing random walks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(7), 1770– 1784.
Fan, Y., Wu, G., Wei, W., Yuan, Y., Lin, F., Wu, X. (2012). Fiber-optic bend sensor using lp 21 mode operation. Optics Express, 20(24), 26,127–26,134.
Feng, L., Wasser, M., et al. (2017). Spatial pattern analysis of nuclear migration in remodelled muscles during drosophila metamorphosis. BMC Bioinformatics, 18(1), 329.
Gessert, N., Lutz, M., Heyder, M., Latus, S., Leistner, D.M., Abdelwahed, Y.S., Schlaefer, A. (2019). Automatic plaque detection in ivoct pullbacks using convolutional neural networks. IEEE Transactions on Medical Imaging, 38(2), 426–434.
Hasegawa, A., Lo, S.C.B., Lin, J.S., Freedman, M.T., Mun, S.K. (1998). A shift-invariant neural network for the lung field segmentation in chest radiography. Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 18(3), 241–250.
Huang, D., Swanson, E.A., Lin, C.P., Schuman, J.S., Stinson, W.G., Chang, W., Hee, M.R., Flotte, T., Gregory, K., Puliafito, C.A., et al. (1991). Optical coherence tomography. Science, 254(5035), 1178–1181.
Huang, Y., He, C., Wang, J., Miao, Y., Zhu, T., Zhou, P., Li, Z. (2018). Intravascular optical coherence tomography image segmentation based on support vector machine algorithm. Molecular & Cellular Biomechanics, 15(2), 117–125.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C. (2016). Ssd: Single shot multibox detector. In: European Conference on Computer Vision (pp. 21–37). Springer.
Lo, S.C.B., Lin, J.S.J., Freedman, M.T., Mun, S.K. (1998). Application of artificial neural networks to medical image pattern recognition: detection of clustered microcalcifications on mammograms and lung cancer on chest radiographs. Journal of VLSI signal processing systems for signal, image and video technology, 18(3), 263–274.
Ma, L., Wu, Y., Wang, W., Chen, W. (2018). Interpretation of the report on cardiovascular diseases in China (2017). Chinese Journal of Cardiovascular Medicine, 23, 3–6.
Neubeck, A., & Van Gool, L. (2006). Efficient non-maximum suppression. In: 18Th International Conference on Pattern Recognition (ICPR’06) (vol. 3, pp. 850–855). IEEE.
Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv:1804.02767.
Rezaei, Z., Selamat, A., Taki, A., Rahim, M.S.M., Kadir, M.R.A. (2017). Automatic plaque segmentation based on hybrid fuzzy clustering and k nearest neighborhood using virtual histology intravascular ultrasound images. Applied Soft Computing, 53, 380–395.
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556.
Stepanova, M., Lin, F., Lin, V.C.L. (2007). A hopfield neural classifier and its fpga implementation for identification of symmetrically structured dna motifs. The Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, 48(3), 239–254.
Thong, P.S., Olivo, M.C., Bhuvaneswari, R., Tandjung, S.S., Movania, M.M., Chiew, W.M., Seah, H.S., Lin, F., Qian, K., Soo, K.C. (2012). Toward real-time virtual biopsy of oral lesions using confocal laser endomicroscopy interfaced with embedded computing. Journal of Biomedical Optics, 17(5), 056,009.
Thong, P.S.P., Olivo, M., Tandjung, S.S., Movania, M.M., Lin, F., Qian, K., Seah, H.S., Soo, K.C. (2011). Review of confocal fluorescence endomicroscopy for cancer detection. IEEE Journal of Selected Topics in Quantum Electronics, 18(4), 1355–1366.
Xu, X., Wu, X., Lin, F. (2017). Cellular Image Classification. Springer.
Yu, J., Lin, F., Seah, H.S., Li, C., Lin, Z. (2012). Image classification by multimodal subspace learning. Pattern Recognition Letters, 33(9), 1196–1204.
Zhang, B., Yang, J., Wang, G., Wang, H., Liu, X., Han, Y. (2017). Plaque region segmentation of intracoronary optical cohenrence tomography images based on kernel graph cuts. Journal of Biomedical Engineering, 34(1), 15–20.
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China (61802109,61703133),Key Projects of Hebei Province (F2017201222), Natural Science Foundation of Hebei Province (F2017205066), Hebei Province 100 Excellent Innovative Talents Support Program (SLRC2017022), Scientific Research Fund of Hebei Normal University (L2017B06, L2018K02), Post-graduate’s Innovation Fund Project of Hebei University (hbu2019ss069),the personnel training project of Hebei Province (A2016002012).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
All authors declare that they have no conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, X., Du, J., Yang, J. et al. Coronary Artery Fibrous Plaque Detection Based on Multi-Scale Convolutional Neural Networks. J Sign Process Syst 92, 325–333 (2020). https://doi.org/10.1007/s11265-019-01501-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-019-01501-5