计算机科学 ›› 2018, Vol. 45 ›› Issue (3): 247-252.doi: 10.11896/j.issn.1002-137X.2018.03.039
所属专题: 医学图像
王帅,刘娟,毕姚姚,陈哲,郑群花,段慧芳
WANG Shuai, LIU Juan, BI Yao-yao, CHEN Zhe, ZHENG Qun-hua and DUAN Hui-fang
摘要: 腺管的自动识别在乳腺癌的组织病理学诊断中十分关键,因为腺管密度 是乳腺癌分级中的一个重要因子。腺管由一个周围充满细胞质的中心管腔以及管腔周围均匀环绕的细胞核组成。若管腔、细胞质、细胞核 在空间位置上接近,则意味着这可能是一个腺管,但是这种识别方法会因为乳腺组织切片中存在脂肪、气泡以及其他类似管腔的对象而出现假阳性错误。为了解决上述问题,提出基于二次聚类与随机森林的腺管自动识别方法。首先通过一次聚类和二次聚类构建出待分割图片;然后通过形态学操作对图片进行处理,并在此基础上进行分割,进而构建候选腺管,利用中心管腔与其周围细胞核的空间位置关系以及一些统计特征来描述腺管;最后通过随机森林分类算法进行分类。实验结果表明,所提算法可以达到86%以上的准确率,为乳腺癌的自动分级奠定了基础。
[1] LATSON L,SEBEK B,POWELL K A.Automated cell nuclear segmentation in color images of hematoxylin and eosin-stained breast biopsy[J].Analytical and Quantitative Cytology and Histology/the International Academy of Cytology and American Society of Cytology,2003,25(6):321-331. [2] PETUSHI S,GARCIA F U,HABER M M,et al.Large-scale computations on histology images reveal grade-differentiating parameters for breast cancer[J].BMC Medical Imaging,2006,6(1):1-11. [3] BAMFORD P,LOVELL B.Unsupervised cell nucleus segmentation with active contours[J].Signal Processing,1998,71(2):203-213. [4] XU J,JANOWCZYK A,CHANDRAN S,et al.A weightedmean shift,normalized cuts initialized color gradient based geodesic active contour model:Applications to histopathology image segmentation[C]∥Medical Imaging:Image Processing.2010. [5] SHI J,MALIK J.Normalized cuts and image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):888-905. [6] CHAN T F,VESE L A.Active contours without edges[J].IEEE Transactions on image processing,2001,10(2):266-277. [7] BASAVANHALLY A,YU E,XU J,et al.Incorporating domain knowledge for tubule detection in breast histopathology using O’Callaghan neighborhoods[C]∥Proceedings of SPIE-The International Society for Optics and Photonics.2011. [8] MAQLIN P,THAMBURAJ R,MAMMEN J J,et al.Automatic detection of tubules in breast histopathological images[M]∥Proceedings of Seventh International Conference on Bio-Inspired Computing:Theories and Applications (BIC-TA 2012).India:Springer,2013:311-321. [9] NGUYEN K,BARNES M,SRINIVAS C,et al.Automatic glandular and tubule region segmentation in histological grading of breast cancer[C]∥SPIE Medical Imaging.International Society for Optics and Photonics.2015. [10] SIRINUKUNWATTANA K,PLUIM J P W,CHEN H,et al.Gland segmentation in colon histology images:The glas challenge contest[J].Medical Image Analysis,2016,35:489-502. [11] JANOWCZYK A,MADABHUSHI A.Deep learning for digital pathology image analysis:A comprehensive tutorial with selec-ted use cases[J].Journal of Pathology Informatics,2016,7(1):29. [12] PENG Y,JIANG Y,EISENGART L,et al.Segmentation ofprostatic glands in histology images[C]∥2011 IEEE International Symposium on Biomedical Imaging:From Nano to Macro.IEEE,2011:2091-2094. [13] NGUYEN K,SARKAR A,JAIN A K.Structure and context in prostatic gland segmentation and classification[M]∥Medical Image Computing and Computer-Assisted Intervention.Springer Berlin Heidelberg,2012:115-123. |
No related articles found! |
|