Abstract
We utilized deep fused fully convolutional neural network (FF-CNN) based on the knowledge transferred from pre-trained AlexNet model to detect mitoses in hematoxylin and eosin stained histology image of breast cancer. Currently, existing mitosis counting methods are based on either the handcrafted features including morphology, color and texture or the abstract features learning from deep neural network. The handcrafted features are pertinent, corresponding to what learned from lower layers of deep convolutional neural network (CNN), on the other hand, features extracted from higher layers are comprehensive. Both handcrafted and extracted features are significant to mitosis detection. More importantly, this detection suffers from class-imbalance and the inconsistent staining color of H&E images. This paper proposed a modified fully convolutional neural network (FCN) structure combining the rich features from different level layers together and a multi-step fine-tuning strategy to reduce over-fitting. In order to treat class-imbalance, we utilized a cascaded approach to select the most confusing non-mitosis samples which made the training efficiently, and weighted the loss function by the corresponding class frequency. For the inconsistent staining appearance issue, we applied the method of stain-normalization to the augment training samples to improve generalization ability of model and to pre-process testing images to obtain more accurate results. As preliminarily validated on the public 2014 ICPR MITOSIS data, our method achieves a better performance in term of detection accuracy than ever recorded for this dataset with an acceptable detection speed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Roux, L., Racoceanu, D., Lomenie, N., et al.: Mitosis detection in breast cancer histological images an ICPR 2012 contest. J. Pathol. Inform. 4(1), 8 (2013)
Basavanhally, A., Ganesan, S., Feldman, M., et al.: Multi-field-of-view framework for distinguishing tumor grade in ER+ Breast cancer from entire histopathology slides. IEEE Trans. Biomed. Eng. 60(8), 2089–2099 (2013)
Irshad, H.: Automated mitosis detection in histopathology using morphological and multi-channel statistics features. J. Pathol. Inform. 4(1), 10 (2013)
Irshad, H., Jalali, S., Roux, L., et al.: Automated mitosis detection using texture, SIFT features and HMAX biologically inspired approach. J. Pathol. Inform. 4(2) (2013)
Huang, C., Lee, H.C.: Automated mitosis detection based on eXclusive independent component analysis. In: International Conference on Pattern Recognition, pp. 1856–1859 (2012)
Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E., et al.: ImageNet classification with deep convolutional neural networks. In: Neural Information Processing Systems, pp. 1097–1105 (2012)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: Computer Vision Pattern Recognition, pp. 1–9 (2015)
Sainath, T.N., Mohamed, A., Kingsbury, B., et al.: Deep convolutional neural networks for LVCSR. In: International Conference on Acoustics, Speech, Signal Processing, pp. 8614–8618 (2013)
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. LNCS, vol. 8150, pp. 411–418. Springer, Heidelberg (2013). doi:10.1007/978-3-642-40763-5_51
Chen, H., Dou, Q., Wang, X., et al.: Mitosis detection in breast cancer histology images via deep cascaded networks. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)
Wang, H.: Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features. J. Med. Imaging 1(3), 1–8 (2014)
Kampffmeyer, M., Salberg, A.B., Jenssen, R.: Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 680–688. IEEE (2016)
Veta, M., van Diest, P.J., Willems, S.M., et al.: Assessment of algorithms for mitosis detection in breast cancer histopathology images. Med. Image Anal. 20(1), 237–248 (2014)
Chang, H., Loss, L.A., Parvin, B.: Nuclear segmentation in H&E sections via multi-reference graph cut (MRGC). In: Proceedings of the Sixth IEEE International Conference on Symposium on Biomedical Imaging, ISBI 2012 (2012)
Veta, M., Van Diest, P.J., Pluim, J.P., et al.: Detecting mitotic figures in breast cancer histopathology images. In: Proceedings of SPIE (2013)
Macenko, M., Niethammer, M., Marron, J.S., et al.: A method for normalizing histology slides for quantitative analysis. In: IEEE International Symposium on Biomedical Imaging: From Nano To Macro, pp. 1107–1110. IEEE (2009)
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems, pp. 3320–3328 (2014)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, pp. 770–778 (2015)
Zhao, L., Jia, K.: Multiscale CNNs for brain tumor segmentation and diagnosis. Comput. Math. Methods Med. 2016(7), 1–7 (2016)
Acknowledgements
This research was financially supported by Basic layout of Shenzhen City (no. JCYJ 20150827165024088), Supporting platform project in Guangdong Province (no. 2014B0909B001), the CAS ‘Light of West China’ Program (XB BS-2014-16), the “Thousand Talents” plan (Y474161) and the Shenzhen Basic Research Project (JCYJ20150630114942260). The author was grateful to Dr. Ludovic Roux for the data providing and results evaluation.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Wu, B. et al. (2017). FF-CNN: An Efficient Deep Neural Network for Mitosis Detection in Breast Cancer Histological Images. In: Valdés Hernández, M., González-Castro, V. (eds) Medical Image Understanding and Analysis. MIUA 2017. Communications in Computer and Information Science, vol 723. Springer, Cham. https://doi.org/10.1007/978-3-319-60964-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-60964-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60963-8
Online ISBN: 978-3-319-60964-5
eBook Packages: Computer ScienceComputer Science (R0)