Mitosis detection in breast cancer histological images based on texture features using AdaBoost
محورهای موضوعی : Image Processing
Sooshiant Zakariapour
1
(Babol Noshivani University of Technology)
حمید جزایری
2
()
Mehdi Ezoji
3
(Babol Noshivani University of Technology)
کلید واژه: Mitosis detection , Breast cancer grading , Texture Features , Ensemble learning , Pathology,
چکیده مقاله :
Counting mitotic figures present in tissue samples from a patient with cancer, plays a crucial role in assessing the patient’s survival chances. In clinical practice, mitotic cells are counted manually by pathologists in order to grade the proliferative activity of breast tumors. However, detecting mitoses under a microscope is a labourious, time-consuming task which can benefit from computer aided diagnosis. In this research we aim to detect mitotic cells present in breast cancer tissue, using only texture and pattern features. To classify cells into mitotic and non-mitotic classes, we use an AdaBoost classifier, an ensemble learning method which uses other (weak) classifiers to construct a strong classifier. 11 different classifiers were used separately as base learners, and their classification performance was recorded. The proposed ensemble classifier is tested on the standard MITOS-ATYPIA-14 dataset, where a pixel window around each cells center was extracted to be used as training data. It was observed that an AdaBoost that used Logistic Regression as its base learner achieved a F1 Score of 0.85 using only texture features as input which shows a significant performance improvement over status quo. It also observed that "Decision Trees" provides the best recall among base classifiers and "Random Forest" has the best Precision.
Counting mitotic figures present in tissue samples from a patient with cancer, plays a crucial role in assessing the patient’s survival chances. In clinical practice, mitotic cells are counted manually by pathologists in order to grade the proliferative activity of breast tumors. However, detecting mitoses under a microscope is a labourious, time-consuming task which can benefit from computer aided diagnosis. In this research we aim to detect mitotic cells present in breast cancer tissue, using only texture and pattern features. To classify cells into mitotic and non-mitotic classes, we use an AdaBoost classifier, an ensemble learning method which uses other (weak) classifiers to construct a strong classifier. 11 different classifiers were used separately as base learners, and their classification performance was recorded. The proposed ensemble classifier is tested on the standard MITOS-ATYPIA-14 dataset, where a pixel window around each cells center was extracted to be used as training data. It was observed that an AdaBoost that used Logistic Regression as its base learner achieved a F1 Score of 0.85 using only texture features as input which shows a significant performance improvement over status quo. It also observed that "Decision Trees" provides the best recall among base classifiers and "Random Forest" has the best Precision.
[1] L. Roux, D. Racoceanu, N. Loménie, M. Kulikova, H. Irshad, J. Klossa, F. Capron, C. Genestie, G. Le Naour, and M. N. Gurcan, “Mitosis detection in breast cancer histological images an icpr 2012 contest,” Journal of pathology informatics, vol. 4, 2013.
[2] J. A. A. Jothi and V. M. A. Rajam, “A survey on automated cancer diagnosis from histopathology images,” Artificial Intelligence Review, pp. 1–51, 2016.
[3] A. Paul and D. P. Mukherjee, “Mitosis detection for invasive breast cancer grading in histopathological images,” Image Processing, IEEE Transactions on, vol. 24, no. 11, pp. 4041–4054, 2015.
[4] Y. Freund and R. E. Schapire, “A desicion-theoretic generalization of on-line learning and an application to boosting,” in European conference on computational learning theory. Springer, 1995, pp. 23–37.
[5] H. Wang, A. Cruz-Roa, A. Basavanhally, H. Gilmore, N. Shih, M. Feldman, J. Tomaszewski, F. Gonzalez, and A. Madabhushi, “Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection,” in SPIE Medical Imaging. International Society for Optics and Photonics, 2014, pp. 90 410B–90 410B.
[6] D. C. Cireşan, A. Giusti, L. M. Gambardella, and J. Schmidhuber, “Mitosis detection in breast cancer histology images with deep neural networks,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2013. Springer, 2013, pp. 411–418.
[7] C. D. Malon, E. Cosatto et al., “Classification of mitotic figures with convolutional neural networks and seeded blob features,” Journal of pathology informatics, vol. 4, no. 1, p. 9, 2013.
[8] F. B. Tek et al., “Mitosis detection using generic features and an ensemble of cascade adaboosts,” Journal of pathology informatics, vol. 4, no. 1, p. 12, 2013.
[9] J. A. A. Jothi and V. M. A. Rajam, “Segmentation of nuclei from breast histopathology images using pso-based otsus multilevel thresholding,” in Artificial Intelligence and Evolutionary Algorithms in Engineering Systems. Springer, 2015, pp. 835–843.
[10] A. Paul, A. Dey, D. P. Mukherjee, J. Sivaswamy, and V. Tourani, “Regenerative random forest with automatic feature selection to detect mitosis in histopathological breast cancer images,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015. Springer, 2015, pp. 94–102.
[11] H. Irshad et al., “Automated mitosis detection in histopathology using morphological and multi-channel statistics features,” Journal of pathology informatics, vol. 4, no. 1, p. 10, 2013.
[12] A. Tashk, M. S. Helfroush, H. Danyali, and M. Akbarzadeh, “An automatic mitosis detection method for breast cancer histopathology slide images based on objective and pixel wise textural features classification,” in Information and Knowledge Technology (IKT), 2013 5th Conference on. IEEE, 2013, pp. 406–410.
[13] J. Monaco, J. Hipp, D. Lucas, S. Smith, U. Balis, and A. Madabhushi, “Image segmentation with implicit color standardization using spatially constrained expectation maximization: Detection of nuclei,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2012. Springer, 2012, pp. 365–372.
[14] K. Nandy, P. R. Gudla, R. Amundsen, K. J. Meaburn, T. Misteli, and S. J. Lockett, “Automatic segmentation and supervised learning-based selection of nuclei in cancer tissue images,” Cytometry Part A, vol. 81, no. 9, pp. 743–754, 2012.
[15] S. Waheed, R. A. Moffitt, Q. Chaudry, A. N. Young, and M. D. Wang, “Computer aided histopathological classification of cancer subtypes,” in 2007 IEEE 7th International Symposium on BioInformatics and BioEngineering. IEEE, 2007, pp. 503–508.
[16] M. N. Gurcan, L. E. Boucheron, A. Can, A. Madabhushi, N. M. Rajpoot, and B. Yener, “Histopathological image analysis: A review,” IEEE reviews in biomedical engineering, vol. 2, pp. 147–171, 2009.
[17] O. Sertel, U. V. Catalyurek, H. Shimada, and M. Guican, “Computer-aided prognosis of neuroblastoma: Detection of mitosis and karyorrhexis cells in digitized histological images,” in Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE. IEEE, 2009, pp. 1433–1436.
[18] A. Brook, R. El-Yaniv, E. Isler, R. Kimmel, R. Meir, and D. Peleg, “Breast cancer diagnosis from biopsy images using generic features and svms,” IEEE Transactions on Information Technology in Biomedicine, 2006.
[19] S. M. Pizer, E. P. Amburn, J. D. Austin, R. Cromartie, A. Geselowitz, T. Greer, B. ter Haar Romeny, J. B. Zimmerman, and K. Zuiderveld, “Adaptive histogram equalization and its variations,” Computer vision, graphics, and image processing, vol. 39, no. 3, pp. 355–368, 1987.
[20] F. Chan, F. Lam, and H. Zhu, “Adaptive thresholding by variational method,” IEEE Transactions on Image Processing, vol. 7, no. 3, pp. 468–473, 1998.
[21] T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Transactions on pattern analysis and machine intelligence, vol. 24, no. 7, pp. 971–987, 2002.
[22] R. M. Haralick, K. Shanmugam et al., “Textural features for image classification,” IEEE Transactions on systems, man, and cybernetics, no. 6, pp. 610–621, 1973. [23] R. Rojas, “Adaboost and the super bowl of classifiers a tutorial introduction to adaptive boosting,” Freie University, Berlin, Tech. Rep, 2009.
[24] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R.Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
[25] J. Wickramaratna, S. Holden, and B. Buxton, “Performance degradation in boosting,” in International Workshop on Multiple Classifier Systems. Springer, 2001, pp. 11–21.
[26] X. Li, L. Wang, and E. Sung, “Adaboost with svm-based component classifiers,” Engineering Applications of Artificial Intelligence, vol. 21, no. 5, pp. 785–795, 2008.
[27] H. Irshad et al., “Automated mitosis detection in histopathology using morphological and multi-channel statistics features,” Journal of pathology informatics, vol. 4, no. 1, p. 10, 2013.
