IVUS Image Segmentation Using Superpixel-Wise Fuzzy Clustering and Level Set Evolution
Source abstract
Abstract
Reliable detection of the media-adventitia border (MAB) and the lumen-intima border (LIB) in intravascular ultrasound (IVUS) images remains a challenging task that is of high clinical interest. In this paper, we propose a superpixel-wise fuzzy clustering technique modified by edges, followed by level set evolution (SFCME-LSE), for automatic border extraction in 40 MHz IVUS images. The contributions are three-fold. First, the usage of superpixels suppresses the influence of speckle noise in ultrasound images on the clustering results. Second, we propose a region of interest (ROI) assignment scheme to prevent the segmentation from being distracted by pathological structures and artifacts. Finally, the contour is converged towards the target boundary through LSE with an appropriately improved edge indicator. Quantitative evaluations on two IVUS datasets by the Jaccard measure (JM), the percentage of area difference (PAD), and the Hausdorff distance (HD) demonstrate the effectiveness of the proposed SFCME-LSE method. SFCME-LSE achieves the minimal HD of 1.20 ± 0.66 mm and 1.18 ± 0.70 mm for the MAB and LIB, respectively, among several state-of-the-art methods on a publicly available dataset.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Cerebrovascular and Carotid Artery Diseases · Photoacoustic and Ultrasonic Imaging · Medical Image Segmentation Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electronic Engineering, Fudan University, Shanghai 200433, China
Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai, Fudan University, Shanghai 200433, China
Funding
National Key Research and Development Program of China
References (39)
Show source-provided references
1. SLE, atherosclerosis and cardiovascular disease10.1111/j.1365-2796.2005.01502.x ↗
2. A state-of-the-art review on segmentation algorithms in intravascular ultrasound (IVUS) images10.1109/TITB.2012.2189408 ↗
3. Fractional-order Darwinian PSO-based feature selection for media-adventitia border detection in intravascular ultrasound images10.1016/j.ultras.2018.06.012 ↗
4. Automatic media-adventitia IVUS image segmentation based on sparse representation framework and dynamic directional active contour model10.1016/j.compbiomed.2017.03.022 ↗
5. Lumen and media-adventitia border detection in IVUS images using texture enhanced deformable model10.1016/j.compmedimag.2018.02.003 ↗
6. Lumen-intima and media-adventitia segmentation in IVUS images using supervised classifications of arterial layers and morphological structures10.1016/j.cmpb.2019.05.021 ↗
7. Assessment of image features for vessel wall segmentation in intravascular ultrasound images10.1007/s11548-015-1345-4 ↗
8. An artificial neural network method for lumen and media-adventitia border detection in IVUS10.1016/j.compmedimag.2016.11.003 ↗
9. Shape-driven segmentation of the arterial wall in intravascular ultrasound images10.1109/TITB.2008.920620 ↗
10. An automated method for lumen and media-adventitia border detection in a sequence of IVUS frames10.1109/TITB.2004.828889 ↗
11. Hammouche, A., Cloutier, G., Tardif, J.C., and Meunier, J. (2018, January 28–30). Space curve approach for IVUS image segmentation. Proceedings of the IEEE Life Sciences Conference, Montreal, QC, Canada.10.1109/LSC.2018.8572073 ↗
12. Automatic IVUS lumen segmentation using a 3D adaptive helix model10.1016/j.compbiomed.2019.01.023 ↗
13. Intravascular ultrasound image segmentation: A three-dimensional fast-marching method based on gray level distributions10.1109/TMI.2006.872142 ↗
14. Fast-marching segmentation of three-dimensional intravascular ultrasound images: A pre- and post-intervention study10.1118/1.3438476 ↗
15. Segmentation method of intravascular ultrasound images of human coronary arteries10.1016/j.compmedimag.2013.09.004 ↗
16. A novel segmentation approach for intravascular ultrasound images10.1007/s40846-017-0233-5 ↗
17. Graph-based IVUS segmentation with efficient computer-aided refinement10.1109/TMI.2013.2260763 ↗
18. Automatic segmentation of cross-sectional coronary arterial images10.1016/j.cviu.2017.11.004 ↗
19. Balocco, S., Gatta, C., Ciompi, F., Pujol, O., Carrillo, X., Mauri, J., and Radeva, P. (2011). Combining growcut and temporal correlation for IVUS lumen segmentation. Lect. Notes Comput. Sci., 556–563.10.1007/978-3-642-21257-4_69 ↗
20. A new nonparametric statistical approach to detect lumen and media-adventitia borders in intravascular ultrasound frames10.1016/j.compbiomed.2018.10.024 ↗
21. Yang, J., Tong, L., Faraji, M., and Basu, A. (2018). IVUS-Net: An intravascular ultrasound segmentation network. Int. Conf. Smart Multimed., 367–377.10.1007/978-3-030-04375-9_31 ↗
22. Robust segmentation of arterial walls in intravascular ultrasound images using dual path U-Net10.1016/j.ultras.2019.03.014 ↗
23. Bezdek, J.C. (1981). Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum.10.1007/978-1-4757-0450-1 ↗
24. A modified fuzzy c-means algorithm for MRI bias field estimation and adaptive segmentation10.1109/42.996338 ↗
25. Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure10.1109/TSMCB.2004.831165 ↗
26. Fuzzy c-means clustering with spatial information for image segmentation10.1016/j.compmedimag.2005.10.001 ↗
27. A robust fuzzy local information c-means clustering algorithm10.1109/TIP.2010.2040763 ↗
28. Incorporating adaptive local information into fuzzy clustering for image segmentation10.1109/TIP.2015.2456505 ↗
29. Superpixel-based fast fuzzy c-means clustering for color image segmentation10.1109/TFUZZ.2018.2889018 ↗
30. SLIC superpixels compared to state-of-the-art superpixel methods10.1109/TPAMI.2012.120 ↗
31. Geodesic active contours10.1023/A:1007979827043 ↗
32. Distance regularized level set evolution and its application to image segmentation10.1109/TIP.2010.2069690 ↗
33. Active contours without edges10.1109/83.902291 ↗
34. Minimization of region-scalable fitting energy for image segmentation10.1109/TIP.2008.2002304 ↗
35. Image segmentation for intensity inhomogeneity in presence of high noise10.1109/TIP.2018.2825101 ↗
36. Zuiderveld, K. (1994). Contrast limited adaptive histograph equalization. Graphic Gems IV, Academic Press Professional.10.1016/B978-0-12-336156-1.50061-6 ↗
37. Kumar, K., Li, J.P., Khan, S.A., Mustafa, N., Shaikh, R.A., and Khan, A. (2014, January 19–21). Image edge detection scheme using wavelet transform. Proceedings of the International Computer Conference on Wavelet Actiev Media Technology and Information Processing, Chengdu, China.10.1109/ICCWAMTIP.2014.7073404 ↗
38. Automatic segmentation of calcifications in intravascular ultrasound images using snakes and the contourlet transform10.1016/j.ultrasmedbio.2009.06.1097 ↗
39. Standardized evaluation methodology and reference database for evaluating IVUS image segmentation10.1016/j.compmedimag.2013.07.001 ↗