A Classification Scheme for Lymphocyte Segmentation in H&E Stained Histology Images
A technique for automating the detection of lymphocytes in histopathological images is presented. The proposed system takes Hematoxylin and Eosin (H&E) stained digital color images as input to identify lymphocytes. The process involves segmentation of cells from extracellular matrix, feature extraction, classification and overlap resolution. Extracellular matrix segmentation is a two step process carried out on the HSV-equivalent of the image, using mean shift based clustering for color approximation followed by thresholding in the HSV space. Texture features extracted from the cells are used to train a SVM classifier that is used to classify lymphocytes and non-lymphocytes. A contour based overlap resolution technique is used to resolve overlapping lymphocytes.
KeywordsLymphocytes Classification Contour Overlap Resolution
Unable to display preview. Download preview PDF.
- 1.Bikhet, S.F., Darwish, A.M., Tolba, H.A., Shaheen, S.I.: Segmentation and classification of white blood cells. In: IEEE International Conference on Acostics, Speech and Signal Processing, ICASSP, pp. 550–553 (1992)Google Scholar
- 4.Comaniciu, D.: Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 58, 71–96 (2002)Google Scholar
- 6.Doughri, R., M’hiri, S., Romdhane, K.B., Ghorbel, F., Essafi, S.: Segmentation and classification of breast cancer cells in hostological images. Information and Communication Technology (2006)Google Scholar
- 7.Fatakdawala, H., Basavanhally, A., Xu, J., Bhanot, G., Ganesan, S., Feldman, M., Tomaszewski, J., Madabhushi, A.: Expectation maximization driven geodesic active contour with overlap resolution: Application to lymphocyte segmentation on breast cancer histopathology. In: International Conference on Bioinformatics and Bioengineering (2009)Google Scholar
- 9.PR in HIMA, http://bmi.osu.edu/cialab/ICPR_contest
- 11.Joachims, T.: Making large-scale svm learning practical. advances in kernel methods - support vector learning. MIT-Press, Cambridge (1999)Google Scholar
- 12.Latson, L., Sebek, B., Powell, K.A.: Automated cell nuclear segmentation in colour images of he stained breast biopsy. Anal. Quant. Cytol. Histol. 25(321-331) (2003)Google Scholar
- 13.Losi, L., Ponti, G., Di Gregorio, C., Marino, M., Rossi, G., Pedroni, M., Benatti, P., Roncucci, L., de Leon, M.P.: Prognostic significance of histological features and biological parameters in stage i (pt1 and pt2) colorectal adenocarcinoma. Pathology - Research and Practice 202(9), 663–670 (2006)CrossRefGoogle Scholar
- 14.Ongun, G., Halici, U., Leblebiciogl, K., Atalay, V.: Feature extraction and classification of blood cells for an automated differential blood count system. IEEE IJCNN, 2461–2466 (2001)Google Scholar
- 15.Rasband, W.S.: Imagej. U.S. National Laboratory of Health, Bethesda (1997-2005)Google Scholar
- 16.Schnorrenberg, F., Pattichis, C., Kyriacou, K., Schizas, C.: Computer-aided detection of breast cancer nuclei. IEEE Transaction on Information Technology in Bio-medicine, 128–140 (1997)Google Scholar
- 19.Scarff, R.W., Torloni, H.: Histological typing of breast tumors. international classification of tumors. World Health Organization, 13–20 (1968)Google Scholar