Abstract
We propose a fast and accurate method for counting the mitotic figures from histopathological slides using regenerative random forest. Our method performs automatic feature selection in an integrated manner with classification. The proposed random forest assigns a weight to each feature (dimension) of the feature vector in a novel manner based on the importance of the feature (dimension). The forest also assigns a misclassification-based penalty term to each tree in the forest. The trees are then regenerated to make a new population of trees (new forest) and only the more important features survive in the new forest. The feature vector is constructed from domain knowledge using the intensity features of nucleus, features of nuclear membrane and features of the possible stroma region surrounding the cell. The use of domain knowledge improves the classification performance. Experiments show at least 4% improvement in F-measure with an improvement in time complexity on the MITOS dataset from ICPR 2012 grand challenge.
Chapter PDF
Similar content being viewed by others
Keywords
References
(2012). http://ipal.cnrs.fr/ICPR2012/?q=node/5 Available as on (February 18, 2015)
Barlow, P.W.: Changes in chromatin structure during the mitotic cycle. Protoplasma 91(2), 207–211 (1977)
Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)
Cireşan, D.C., Giusti, A., Gambardella, L.M., Schmidhuber, J.: Mitosis detection in breast cancer histology images with deep neural networks. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part II. LNCS, vol. 8150, pp. 411–418. Springer, Heidelberg (2013)
Haralick, R.M., Shanmugam, K., Dinstein, I.H.: Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics (6), 610–621 (1973)
Huang, C.H., et al.: Automated mitosis detection based on exclusive independent component analysis. In: 21st ICPR, pp. 1856–1859. IEEE (2012)
Khan, A.M., et al.: A gamma-gaussian mixture model for detection of mitotic cells in breast cancer histopathology images. Journal of Pathology Informatics 4 (2013)
Kuru, K.: Optimization and enhancement of h&e stained microscopical images by applying bilinear interpolation method on lab color mode. Theoretical Biology and Medical Modelling 11(1), 9 (2014)
Malon, C.D., Cosatto, E.: Classification of mitotic figures with convolutional neural networks and seeded blob features. Journal of Pathology Informatics 4 (2013)
Paul, A., Mukherjee, D.P.: Enhanced random forest for mitosis detection. In: Proceedings of the 2014 Indian Conference on Computer Vision Graphics and Image Processing, p. 85. ACM (2014)
Veta, M., et al.: Breast cancer histopathology image analysis: a review. IEEE Trans. Biomed. Engineering 61(5), 1400–1411 (2014)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Paul, A., Dey, A., Mukherjee, D.P., Sivaswamy, J., Tourani, V. (2015). Regenerative Random Forest with Automatic Feature Selection to Detect Mitosis in Histopathological Breast Cancer Images. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds) Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science(), vol 9350. Springer, Cham. https://doi.org/10.1007/978-3-319-24571-3_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-24571-3_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24570-6
Online ISBN: 978-3-319-24571-3
eBook Packages: Computer ScienceComputer Science (R0)