冠脉光学相干断层成像（OCT）图像斑块区域分割是冠脉斑块识别的前提和基础，对后续斑块特征分析及易损斑块识别，进而实现冠脉疾病的辅助诊断分析具有十分重要的意义。本文提出了一种新的算法，使用K-means 算法与图割算法结合，实现了冠脉 OCT 图像斑块准确的多区域分割——纤维化斑块、钙化斑块和脂质池，并较好地保留了斑块的边界特征信息。本文实验中对 20 组具有典型斑块特征的冠脉 OCT 图像进行了分割，通过与医生手动分割结果比较，证明本文方法能准确地分割出斑块区域，且算法具有较好的稳定性。研究结果证明了本文工作能够极大减少医生分割斑块所消耗的时间，避免不同医生之间的主观差异性，或可辅助临床医生对冠心病的诊断与治疗
3. Athanasiou L S, Bourantas C V, Rigas G A, et al. Fully automated Calcium detection using optical coherence tomography//35th Annual International Coference of the IEEE EMBS. Osaka,Japan, 2013: 1430-1433.
[4]
4. WANG Z, Hiroyuki K, Hiram G B, et al. Automatic segmentation of intravascular optical coherence tomography images for facilitating quantitative diagnosis of athrosclerosis. SPIE-The International Society for Optical Engineering, 2011, 7889(1): 78890N-78890N-7.
[5]
5. Prakash A, Hewko M D, Sowa M, et al. Texture based segmentation method to detect atherosclerotic plaque from optical tomography images.// European Conference on Biomedical Optics VI. Munich, Germany, 2013.
[6]
6. Prakash A, Hewko M D, Sowa M, et al. Detection of atherosclerotic plaque from optical coherence tomography images using texture-based segmentation. Medical Technologies in Medicine/ Sovremennye,Tehnologii v Medicine, 2015, 7(1): 21-28.
8. Ben Salah M, Mitiche A, Ben Ayed I. Multiregion image segmentation by parametric kernel graph cuts. IEEE Trans Image Process, 2011, 20(2): 545-557.
[9]
9. Kubo T, XU Chenyang, WANG Zhao, et al. Plaque and thrombus evaluation by optical coherence tomography. Int J Cardiovasc Imaging, 2011, 27(2): 289-298.
[10]
10. Athanasiou L, Bourantas C, Rigas G, et al. Methodology for fully automated segmentation and plaque characterization in intracoronary optical coherence tomography images. J Biomed Opt, 2014, 19(2): 026009.
