Attention Multiple Instance Learning for Cancer Tissue Classification in Digital Histopathology Images

Authors: Afaf Alharbi, Qianni Zhang

Abstract:

The identification of malignant tissue in histopathological slides holds significant importance in both clinical settings and pathology research. This paper presents a methodology aimed at automatically categorizing cancerous tissue through the utilization of a multiple instance learning framework. This framework is specifically developed to acquire knowledge of the Bernoulli distribution of the bag label probability by employing neural networks. Furthermore, we put forward a neural network-based permutation-invariant aggregation operator, equivalent to attention mechanisms, which is applied to the multi-instance learning network. Through empirical evaluation on an openly available colon cancer histopathology dataset, we provide evidence that our approach surpasses various conventional deep learning methods.

Keywords: Attention Multiple Instance Learning, Multiple Instance Learning, transfer learning, histopathological slides, cancer tissue classification.

References:

[1] Thomas G. Dietterich a, Richard H. Lathrop band Lozano-P´erez, Tom´as, ”Solving the multiple instance problem with axis-parallel rectangles”,Artificial intelligence,Elsevier. vol.89,pp. 31–71,1997.
[2] Maron, Oded and Lozano-P´erez, Tom´as,”A framework for multiple-instance learning”, Advances in neural information processing systems, Citeseer,pp.570–576,1998.
[3] Cosatto, Eric and Laquerre, Pierre-Francois and Malon, Christopher and Graf, Hans-Peter and Saito, Akira and Kiyuna, Tomoharu and Marugame, Atsushi and Kamijo, Ken’ichi,” Automated gastric cancer diagnosis on h&e-stained sections; ltraining a classifier on a large scale with multiple instance machine learning”, Medical Imaging 2013: Digital Pathology, International Society for Optics and Photonics, vol. 8676, pp.867–605, 2013.
[4] liu2012key,Liu, Guoqing and Wu, Jianxin and Zhou, Zhi-Hua,”Key instance detection in multi-instance learning” ,Asian Conference on Machine Learning,PMLR, pp.253–268,2012.
[5] Cheplygina, Veronika and Sørensen, Lauge and Tax, David MJ and de Bruijne, Marleen and Loog, Marco, ”Label stability in multiple instance learning”,International Conference on Medical Image Computing and Computer-Assisted Intervention, pp.539–546,Springer, 2015.
[6] Andrews, Stuart and Tsochantaridis, Ioannis and Hofmann, Thomas, ”Support vector machines for multiple-instance learning”,Advances in neural information processing systems,vol. 15, MIT; 1998,2003.
[7] Chen, Yixin and Bi, Jinbo and Wang, James Ze,”Multiple-instance learning via embedded instance selection”,IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28,pp. 1931–1947, IEEE,2006.
[8] Ramon, Jan and De Raedt, Luc,”Multi instance neural networks”,Proceedings of the ICML-2000 workshop on attribute-value and relational learning, pp. 53–60,2000.
[9] Raykar, Vikas C and Krishnapuram, Balaji and Bi, Jinbo and Dundar, Murat and Rao, R Bharat, ”Bayesian multiple instance learning: automatic feature selection and inductive transfer”,Proceedings of the 25th international conference on Machine learning, pp. 808–815,2008.
[10] Zhang, Cha and Platt, John and Viola, Paul,”Multiple instance boosting for object detection”, Advances in neural information processing systems, vol. 18, pp. 1417–1424, Citeseer, 2005.
[11] Kandemir, Melih and Hamprecht, Fred A,”Computer-aided diagnosis from weak supervision: A benchmarking study”, Computerized medical imaging and graphics, vol. 42, Elsevier, 2015.
[12] Sirinukunwattana, Korsuk and Raza, Shan E Ahmed and Tsang, Yee-Wah and Snead, David RJ and Cree, Ian A and Rajpoot, Nasir M,”Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images”,IEEE transactions on medical imaging,vol. 35, pp. 1196–1206, IEEE, 2016.
[13] Glorot, Xavier and Bengio, Yoshua,”Understanding the difficulty of training deep feedforward neural networks”,Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp. 249–256, JMLR Workshop and Conference Proceedings, 2010.
[14] Wang, Xinggang and Yan, Yongluan and Tang, Peng and Bai, Xiang and Liu, Wenyu,”Revisiting Multiple Instance Neural Networks”, arXiv preprint arXiv:1610.02501, 2016.
[15] LeCun, Yann and Bottou, L´eon and Bengio, Yoshua and Haffner, Patrick,”Gradient-based learning applied to document recognition”,Proceedings of the IEEE,vol. 86, pp. 2278–2324, IEEE, 1998.