Abstract
The work aims to develop a fast detection method for instances of mitosis in breast cell sections, which needs time-consuming and labor-intensive searches. The system consists of two sequential processes. The first involves data pre-processing to avoid confusing images transferring to the successive detection procedure from wasteful computations. The input data is filtered using the blue ratio threshold to remove unnecessary background information and increase the color difference between the target and the non-target. Cropped images of suspicious candidates are classified as mitotic or non-mitotic employing a hard attention model, which only grapes the fine trained features locally and detailly instead of the entire picture. There is less computational complexity in terms of efficiency and performance because there are fewer parameters and smaller image sizes, so the proposed classification system outperforms traditional models, such as LEnet-5 and VGG-19, for the benchmarked data set provided in the TPAC2016 competition data sets. The proposed method is also compared to other methods listed on a ranking table for the ICPR2012 competition using its official test data set.
Similar content being viewed by others
References
Huh S, Bise R, Chen M, Kanade T (2010) Automated mitosis detection of stem cell populations in phase-contrast microscopy images. IEEE Trans Med Imaging 30(3):586–596
Yancey RE (2020) Multi-stream faster rcnn for mitosis counting in breast cancer images. arXiv preprint arXiv:2002.03781
Cireşan DC, Giusti A, Gambardella LM, Schmidhuber J (2013, September) Mitosis detection in breast cancer histology images with deep neural networks. In: International conference on medical image computing and computer-assisted intervention. Springer, Berlin, Heidelberg, pp 411–418
Shkolyar A, Gefen A, Benayahu D, Greenspan H (2015, August) Automatic detection of cell divisions (mitosis) in live-imaging microscopy images using convolutional neural networks. In: 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE, pp 743–746
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440
Liu AA, Li K, Kanade T (2010, April) Mitosis sequence detection using hidden conditional random fields. In: 2010 IEEE international symposium on biomedical imaging: from nano to macro. IEEE, pp 580–583
Saha M, Chakraborty C, Racoceanu D (2018) Efficient deep learning model for mitosis detection using breast histopathology images. Comput Med Imaging Graph 64:29–40
Janowczyk A, Madabhushi A (2016) Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases. J Pathol Inform, 7
Zhou DX (2020) Theory of deep convolutional neural networks: Downsampling. Neural Netw 124:319–327
Aptoula E, Courty N, Lefevre S (2013, April) Mitosis detection in breast cancer histological images with mathematical morphology. In: 2013 21st Signal Processing and Communications Applications Conference (SIU). IEEE, pp 1–4
Irshad H (2013) Automated mitosis detection in histopathology using morphological and multi-channel statistics features. J Pathol Inform 4
Alom MZ, Aspiras T, Taha TM, Bowen TJ, Asari VK (2020) MitosisNet: end-to-end mitotic cell detection by multi-task learning. IEEE Access 8:68695–68710
Ding S, Qu S, Xi Y, Wan S (2020) Stimulus-driven and concept-driven analysis for image caption generation. Neurocomputing 398:520–530
Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473
Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European Conference on Computer Vision. Springer, Cham, pp 213–229
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Huang X, Sun W, Tseng TLB, Li C, Qian W (2019) Fast and fully-automated detection and segmentation of pulmonary nodules in thoracic CT scans using deep convolutional neural networks. Comput Med Imaging Graph 74:25–36
Veta M, Heng YJ, Stathonikos N, Bejnordi BE, Beca F, Wollmann T, Pluim JP (2019) Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge. Med Image Anal 54:111–121
Roux L, Racoceanu D, Loménie N, Kulikova M, Irshad H, Klossa J, Gurcan MN (2013) Mitosis detection in breast cancer histological images An ICPR 2012 contest. J Pathol Inform 4
Sommer C, Fiaschi L, Hamprecht FA, Gerlich DW (2012) Learning-based mitotic cell detection in histopathological images. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012). IEEE, pp 2306-2309
Sebai M, Wang X, Wang T (2020) MaskMitosis: a deep learning framework for fully supervised, weakly supervised, and unsupervised mitosis detection in histopathology images. Med Biol Eng Comput 58:1603–1623
Tek FB (2013) Mitosis detection using generic features and an ensemble of cascade adaboosts. J Pathol Inform 4
Mathew T, Kini JR, Rajan J (2020) Computational methods for automated mitosis detection in histopathology images: a review. Biocybern Biomed Eng
Hwang M, Wang D, Wu C, Jiang WC, Kong XX, Hwang KS, Ding K (2020) A fuzzy segmentation method to learn classification of mitosis. Int J Fuzzy Syst 22:1653–1664
Irshad H, Jalali S, Roux L, Racoceanu D, Hwee LJ, Le Naour G, Capron F (2013) Automated mitosis detection using texture, SIFT features and HMAX biologically inspired approach. J Pathol Inform 4(Suppl)
Pan X, Lu Y, Lan R, Liu Z, Qin Z, Wang H, Liu Z (2021) Mitosis detection techniques in H&E stained breast cancer pathological images: a comprehensive review. Comput Electr Eng 91:107038
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66
Mnih V, Heess N, Graves A (2014) Recurrent models of visual attention. In: Advances in neural information processing systems, pp 2204–2212
Sutton RS, Barto AG (2018) Reinforcement learning: An introduction. MIT press
Barto AG, Sutton RS, Anderson CW (2020) Looking back on the actor-critic architecture. IEEE Trans Syst Man Cybern Syst 51(1):40–50
Raybaut P (2017) Spyder: Scientific python development environment, 2009–. URL“ https://github.com/spyder-ide/spyder”
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, ..., Zheng X (2015) TensorFlow: Large-scale machine learning on heterogeneous systems, software available from tensorflow. org (2015). URL https://www.tensorflow.org
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481–2495
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Author contributions
The new contributor, Wei-Chen Hung, gave some useful suggestions to revise the new submission.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix
The loss function consists of three sub-losses from a classifier for accuracy. The critic-network in the Locator predicts the returns for each round. The actor-network in the Locator accounts for the policy gradient. For TensorFlow, these three loss functions are used to update the weights in a gradient descent manner.
Hybird loss function
Classification loss–using cross-entropy
where \(cross\_entropy = -[ylog{\hat{y}}+(1-y)log(1-{\hat{y}})]\); \(y = LOGIT[0]\) and \({\hat{y}} = LABEL[0]\). LOGIT is the output of a Classifier with softmax and LABEL is a single encoder from the initial label, where b denotes data from the batch and c denotes the class is it.
Critic loss–using mean square error
where \(R_{b,t}\) is a reward from a Classifier, \(BL_{b,t}\) is the prediction of the critic, B is the batch size, T is the number of glimpses.
Actor loss–using Policy gradient
Rights and permissions
About this article
Cite this article
Hwang, M., Wu, C., Jiang, WC. et al. A sequential attention interface with a dense reward function for mitosis detection. Int. J. Mach. Learn. & Cyber. 13, 2663–2675 (2022). https://doi.org/10.1007/s13042-022-01549-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-022-01549-z