Skip to main content
SpringerLink
Log in

Segmentation of Hematoxylin-Eosin stained breast cancer histopathological images based on pixel-wise SVM classifier

基于像素级支持向量机分类算法的苏木素-伊红染色乳腺癌病理图像分割

  • Research Paper
  • Published:
Science China Information Sciences Aims and scope Submit manuscript

Abstract

Hematoxylin-Eosin (HE) staining is the routine diagnostic method for breast cancer (BC), and large amounts of HE stained histopathological images are available for analysis. It is emergent to develop computational methods to efficiently and objectively analyze these images, with the aim of providing potentially better diagnostic and prognostic information for BC. This work focus on analyzing our in-house HE stained histopathological images of breast cancer tissues. Since tumor nests (TNs) and stroma morphological characteristics can reflect the biological behaviors of breast invasive ductal carcinoma (IDC), accurate segmentation of TNs and the stroma is the first step towards the subsequent quantitative analysis. We first propose a method based on the pixel-wise support vector machine (SVM) classifier for segmenting TNs and the stroma, then extract four morphological characters related to the TNs from the images and investigate their relationships with the patients’ 8-year disease free survival (8-DFS). The evaluation result shows that the classification based segmentation method is able to distinguish between TNs and stroma with 87.1% accuracy and 80.2% precision, suggesting that the proposed method is promising in segmenting HE stained IDC histopathological images. The Kaplan-Meier survival curves show that three morphological characters (number of TNs, total perimeter, and average area of TNs) in the images have statistical correlations with 8-DFS of the patients, illustrating that the segmented images can help to identify new morphological factors in IDC TNs for the prediction of BC prognosis.

抽象

创新点

苏木素-伊红 (Hematoxylin-Eosin, HE) 染色组织病理图像分析是乳腺癌的常规诊断方法. 随着数字病理的发展, 病理实验室采集了大量数字化HE组织病理图像, 迫切需要开发基于计算机的高效客观的病理图像分析方法. 医学领域认为病理图像中癌巢和间质的形态学特征可以反映乳腺浸润性导管癌的生物学行为趋势, 因此精确分割癌巢和间质是计算机辅助分析的基础. 本文将图像分割问题看作是像素点的分类问题, 提出了一种基于像素级特征的支持向量机分类算法来识别癌巢/间质像素点, 从而实现癌巢-间质的分割. 基于此算法, 我们对本实验采集的HE 染色病理图像进行分割, 结果显示该算法在分割癌巢-间质时有87.1%的准确率和80.2%的精度. 我们提取出癌巢的4个形态学特征, Kaplan-Meier生存分析揭示其中三个癌巢形态学特征(癌巢数量、 癌巢总周长以及癌巢平均面积)与患者8年无病生存期 (8-DFS) 具有显著的统计相关性, 该结果表明该分割算法有助于鉴别乳腺浸润性导管癌新的病理学形态预后因子.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Siegel R, Naishadham D, Jemal A. Cancer statistics. CA Cancer J Clin, 2013, 63: 11–30

    Article  Google Scholar 

  2. Berzina D, Miklasevica M N, Zestkova J, et al. BRCA1/2 mutation screening in high-risk breast/ovarian cancer families and sporadic cancer patient surveilling for hidden high-risk families. BMC Med Genet, 2013, 14: 61

    Article  Google Scholar 

  3. Fox H. Is H&E morphology coming to an end? J Clin Pathol, 2000, 53: 38–40

    Article  Google Scholar 

  4. Elston C W, Ellis I O. Pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer: experience from a large study with long-term follow-up. Histopathology, 1991, 19: 403–410

    Article  Google Scholar 

  5. Schnitt S J, Connolly J L, Tavassoli F A, et al. Inter observer reproducibility in the diagnosis of ductal proliferative breast lesions using standardized criteria. Am J Surg Pathol, 1992, 16: 1133–1143

    Article  Google Scholar 

  6. Tawfik O, Kimler B F, Davis M. Grading invasive ductal carcinoma of the breast: advantages of using automated proliferation index instead of mitotic count. Virchows Arch, 2007, 450: 627–636

    Article  Google Scholar 

  7. Isse K, Lesniak A, Grama K, et al. Digital transplantation pathology: combining whole slide imaging, multiplex staining and automated image analysis. Am J Trans Plant, 2012, 12: 27–37

    Article  Google Scholar 

  8. Brachtel E, Yagi Y. Digital imaging in pathology-current applications and challenges. J Biophoton, 2012, 5: 327–335

    Article  Google Scholar 

  9. Gurcan M N, Boucheron L E, Can A, et al. Histopathologic image analysis: a review. IEEE Rev Biomed Eng, 2009, 2: 147–171

    Article  Google Scholar 

  10. Tambasco M, Eliasziw M, Magliocco A M. Morphologic complexity of epithelial architecture for predicting invasive breast cancer survival. J Transl Med, 2010, 8: 140

    Article  Google Scholar 

  11. Mitko V, Josien P W P, Paul J D, et al. Breast cancer histopathology image analysis: a review. IEEE Trans Bio-Med Eng, 2014, 61: 1400–1411

    Article  Google Scholar 

  12. Wang C W, Yu C P. Automated morphological classification of lung cancer subtypes using H&E tissue images. Mach Vis Appl, 2013, 24: 1383–1391

    Article  Google Scholar 

  13. Sonal K, John H P, Todd H S, et al. Pathology imaging informatics for quantitative analysis of whole-slide images. J Am Med Inf Assoc, 2013, 20: 1099–1108

    Article  Google Scholar 

  14. Dimaras H, Dimba E A, Waweru W, et al. Digital cancer pathology in Africa. Lancet Oncol, 2013, 14: 289–290

    Article  Google Scholar 

  15. Beck A H, Sangoi A R, Leung S, et al. Systematic analysis of breast cancer morphology uncovers stromal features associated with survival. Sci Transl Med, 2011, 3: 108–113

    Article  Google Scholar 

  16. Bourzac K. Software: the computer will see you now. Nature, 2013, 502: 92–94

    Article  MATH  Google Scholar 

  17. McCann M, Mixon D, Fickus M, et al. Images as occlusions of textures: a framework for segmentation. IEEE Trans Image Process, 2014, 23: 2033–2046

    Article  MathSciNet  Google Scholar 

  18. Ilea D E, Whelan P F. Image segmentation based on the integration of colour-texture descriptors-a review. Patt Recogn, 2011, 44: 2479–2501

    Article  MATH  Google Scholar 

  19. Vantaram S R, Saber E. Survey of contemporary trends in color image segmentation. J Electron Imag, 2012, 21: 040901

    Article  Google Scholar 

  20. Wang X Y, Wang T, Bu J. Color image segmentation using pixel vise support vector machine classification. Patt Recogn, 2011, 44: 777–787

    Article  MATH  Google Scholar 

  21. Huang P W, Lai Y H. Effective segmentation and classification for HCC biopsy images. Patt Recogn, 2010, 43: 1550–1563

    Article  Google Scholar 

  22. Filipczuk P, Fevens T, Krzyzak A, et al. Computer-aided breast cancer diagnosis based on the analysis of cytological images of fine needle biopsies. IEEE Trans Med Imag, 2013, 32: 2169–2178

    Article  Google Scholar 

  23. Meijering E. Cell segmentation: 50 years down the road. IEEE Signal Proc Mag, 2012, 29: 140–145

    Article  Google Scholar 

  24. Rexhepaj E, Agnarsdóttir M, Bergman J, et al. A texture based pattern recognition approach to distinguish melanoma from non-melanoma cells in histopathological tissue microarray sections. PloS One, 2013, 8: e62070

    Article  Google Scholar 

  25. Wang C W. Robust automated tumour segmentation on histological and immunohistochemical tissue images. PloS One, 2011, 6: e15818

    Article  Google Scholar 

  26. Akbar S, McKenna S J, Amaral T, et al. Spin-context segmentation of breast tissue microarray images. Ann BMVA, 2013, 2013: 1–11

    Google Scholar 

  27. Allred D C, Wu Y, Mao S, et al. Ductal carcinoma in situ and the emergence of diversity during breast cancer evolution. Clin Cancer Res, 2008, 14: 370–378

    Article  Google Scholar 

  28. Khan A M, El-Daly H, Simmons E, et al. HyMaP: a hybrid magnitude-phase approach to unsupervised segmentation of tumor areas in breast cancer histology images. J Pathol Inform, 2013, 4: 1–7

    Google Scholar 

  29. Wang L W, Qu A P, Yuan J P, et al. Computer-based image studies on tumor nests mathematical features of breast cancer and their clinical prognostic value. PloS One, 2013, 8: e82314

    Article  Google Scholar 

  30. Wang L W, Yang G F, Chen J M, et al. A clinical database of breast cancer patients reveals distinctive clinico pathological characteristics: a study from central China. Asian Pac J Cancer Prev, 2014, 15: 1621

    Article  Google Scholar 

  31. Chen C, Xia H S, Gong Y P, et al. The quantitative detection of total HER2 load by quantum dots and the identification of a new subtype of breast cancer with different 5-year prognosis. Biomaterials, 2010, 31: 8818–8825

    Article  Google Scholar 

  32. Peng C W, Liu X L, Liu X, et al. Co-evolution of cancer microenvironment reveals distinctive patterns of gastric cancer invasion: laboratory evidence and clinical significance. J Transl Med, 2010, 8: 1479–5876

    Article  MathSciNet  Google Scholar 

  33. Sobin L H, Mary K G, Christian W. TNM classification of malignant tumours. New Jersey: John Wiley & Sons, 2011. 260–280

    MATH  Google Scholar 

  34. Miyamoto E, Merryman T. Fast Calculation of Haralick Texture Features. Technical Report. Pittsburgh: Carnegie Mellon University, 2005

    Google Scholar 

  35. Gavrilovic M, Azar J C, Lindblad J, et al. Blind color decomposition of histological images. IEEE Trans Med Imag, 2013, 32: 983–994

    Article  Google Scholar 

  36. Unnikrishnan R, Pantofaru C, Hebert M. Toward objective evaluation of image segmentation algorithms. IEEE Trans Patt Anal, 2007, 29: 929–944

    Article  MATH  Google Scholar 

  37. Estrada F J, Jepson A D. Benchmarking image segmentation algorithms. Int J Comput Vis, 2009, 85: 167–181

    Article  Google Scholar 

  38. Haralick R M, Shanmugam K, Dinstein I H. Textural features for image classification. IEEE Trans Syst Man Cybern B-Syst Man Cybern, 1973, 6: 610–621

    Article  Google Scholar 

  39. Ojala T, Pietikäinen M, Mäenpää T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Patt Anal, 2002, 24: 971–987

    Article  Google Scholar 

  40. Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, 2005. 886–893

    Google Scholar 

  41. Lowe D G. Distinctive image features from scale invariant keypoints. Int J Comput Vis, 2004, 60: 91–110

    Article  Google Scholar 

  42. Zhao G, Ahonen T, Matas J, et al. Rotation-invariant image and video description with local binary pattern features. IEEE Trans Image Process, 2012, 21: 1465–1467

    Article  MathSciNet  Google Scholar 

  43. Cortes C, Vapnik V. Support-vector networks. Mach Learn, 1995, 20: 273–297

    MATH  Google Scholar 

  44. Ruifrok A C, Johnston D A. Quantification of histochemical staining by color deconvolution. Anal Quant Cytol Histol, 2001, 23: 291–299

    Google Scholar 

  45. Camp R, Dolled-Filhart M, Rimm D. X-tile a new bioinformatics tool for biomarker assessment and outcome-based cut-point optimization. Clin Cancer Res, 2004, 10: 7252–7259

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Key State Laboratory of Software Engineering, School of Computer, Wuhan University, Wuhan, 430072, China

    AiPing Qu & Juan Liu

  2. Department of Oncology, Zhongnan Hospital of Wuhan University, Hubei Key Laboratory of Tumor Biological Behaviors & Hubei Cancer Clinical Study Center, Wuhan, 430071, China

    JiaMei Chen, LinWei Wang, JingPing Yuan, Fang Yang, QingMing Xiang & Yan Li

  3. Department of Pathology, Zhongnan Hospital of Wuhan University, Wuhan, 430071, China

    Ninu Maskey & GuiFang Yang

  4. Center of High Performance Computing, Huaihua University, Huaihua, 418000, China

    AiPing Qu

Authors
  1. AiPing Qu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. JiaMei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. LinWei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. JingPing Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Fang Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. QingMing Xiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ninu Maskey
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. GuiFang Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Juan Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Yan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Juan Liu or Yan Li.

Additional information

The first 2 authors contributed equally to this article.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Qu, A., Chen, J., Wang, L. et al. Segmentation of Hematoxylin-Eosin stained breast cancer histopathological images based on pixel-wise SVM classifier. Sci. China Inf. Sci. 58, 1–13 (2015). https://doi.org/10.1007/s11432-014-5277-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11432-014-5277-3

Keywords

关键词

Search

Navigation