Abstract
Histopathological image analysis is a critical area of research with the potential to aid pathologists in faster and more accurate diagnoses. However, Whole-Slide Images (WSIs) present challenges for deep learning frameworks due to their large size and lack of pixel-level annotations. Multi-Instance Learning (MIL) is a popular approach that can be employed for handling WSIs, treating each slide as a bag composed of multiple patches or instances. In this work we propose Buffer-MIL, which aims at tackling the covariate shift and class imbalance characterizing most of the existing histopathological datasets. With this goal, a buffer containing the most representative instances of each disease-positive slide of the training set is incorporated into our model. An attention mechanism is then used to compare all the instances against the buffer, to find the most critical ones in a given slide. We evaluate Buffer-MIL on two publicly available WSI datasets, Camelyon16 and TCGA lung cancer, outperforming current state-of-the-art models by 2.2% of accuracy on Camelyon16.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Allegretti, S., Bolelli, F., Cancilla, M., Pollastri, F., Canalini, L., Grana, C.: How does connected components labeling with decision trees perform on GPUs? In: Vento, M., Percannella, G. (eds.) CAIP 2019. LNCS, vol. 11678, pp. 39–51. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29888-3_4
Bejnordi, B.E., et al.: Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318(22), 2199–2210 (2017)
Bontempo, G., Porrello, A., Bolelli, F., Calderara, S., Ficarra, E.: DAS-MIL: distilling across scales for MIL classification of histological WSIs. In: Medical Image Computing and Computer Assisted Intervention - MICCAI 2023 (2023)
Bruno, P., Amoroso, R., Cornia, M., Cascianelli, S., Baraldi, L., Cucchiara, R.: Investigating bidimensional downsampling in vision transformer models. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds.) Image Analysis and Processing - ICIAP 2022, pp. 287–299. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-06430-2_24
Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9650–9660 (2021)
Chen, R.J., et al.: Scaling vision transformers to gigapixel images via hierarchical self-supervised learning. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16144–16155 (2022)
Chen, R.J., et al.: Pathomic fusion: an integrated framework for fusing histopathology and genomic features for cancer diagnosis and prognosis. IEEE Trans. Med. Imaging 41(4), 757–770 (2020)
Cornia, M., Baraldi, L., Cucchiara, R.: Explaining transformer-based image captioning models: an empirical analysis. AI Commun. 35(2), 111–129 (2022)
Dietterich, T.G., Lathrop, R.H., Lozano-Pérez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89(1), 31–71 (1997)
Huang, J., Gretton, A., Borgwardt, K., Schölkopf, B., Smola, A.: Correcting sample selection bias by unlabeled data. In: Advances in Neural Information Processing Systems, vol. 19 (NIPS) (2006)
Ilse, M., Tomczak, J., Welling, M.: Attention-based deep multiple instance learning. In: International Conference on Machine Learning, vol. 80, pp. 2127–2136. PMLR, July 2018
Kumar, N., Gupta, R., Gupta, S.: Whole Slide Imaging (WSI) in pathology: current perspectives and future directions. J. Digit. Imaging 33(4), 1034–1040 (2020)
Li, B., Li, Y., Eliceiri, K.W.: Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14318–14328 (2021)
Lovino, M., Bontempo, G., Cirrincione, G., Ficarra, E.: Multi-omics classification on kidney samples exploiting uncertainty-aware models. In: Huang, D.-S., Jo, K.-H. (eds.) ICIC 2020. LNCS, vol. 12464, pp. 32–42. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60802-6_4
Lu, M.Y., Williamson, D.F., Chen, T.Y., Chen, R.J., Barbieri, M., Mahmood, F.: Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5(6), 555–570 (2021)
Maksoud, S., Zhao, K., Hobson, P., Jennings, A., Lovell, B.C.: SOS: selective objective switch for rapid immunofluorescence whole slide image classification. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3862–3871 (2020)
Panariello, A., Porrello, A., Calderara, S., Cucchiara, R.: Consistency-based self-supervised learning for temporal anomaly localization. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision - ECCV 2022 Workshops, vol. 13805, pp. 338–349. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-25072-9_22
Ponzio, F., Urgese, G., Ficarra, E., Di Cataldo, S.: Dealing with lack of training data for convolutional neural networks: the case of digital pathology. Electronics 8(3) (2019)
Roberti, I., Lovino, M., Di Cataldo, S., Ficarra, E., Urgese, G.: Exploiting gene expression profiles for the automated prediction of connectivity between brain regions. Int. J. Mol. Sci. 20(8), 2035 (2019)
Shao, Z., et al.: TransMIL: transformer based correlated multiple instance learning for whole slide image classification. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 34, pp. 2136–2147 (2021)
Shimodaira, H.: Improving predictive inference under covariate shift by weighting the log-likelihood function. J. Stat. Plann. Inference 90(2), 227–244 (2000)
Sugiyama, M., Nakajima, S., Kashima, H., Buenau, P., Kawanabe, M.: Direct importance estimation with model selection and its application to covariate shift adaptation. In: Advances in Neural Information Processing Systems (NIPS), vol. 20 (2007)
Tu, M., Huang, J., He, X., Zhou, B.: Multiple instance learning with graph neural networks. In: ICML Workshop on Learning and Reasoning with Graph-Structured Representations (2019)
Vitter, J.S.: Random sampling with a reservoir. ACM Trans. Math. Softw. 11(1), 37–57 (1985)
Zhang, J., Hu, J.: Image segmentation based on 2D Otsu method with histogram analysis. In: International Conference on Computer Science and Software Engineering, vol. 6, pp. 105–108. IEEE (2008)
Zhang, W., Li, J., Liu, L.: Robust multi-instance learning with stable instances. In: ECAI 2020: 24th European Conference on Artificial Intelligence (2019)
Acknowledgements
This project has received funding from DECIDER, the European Union’s Horizon 2020 research and innovation programme under GA No. 965193, and from the Department of Engineering “Enzo Ferrari” of the University of Modena through the FARD-2022 (Fondo di Ateneo per la Ricerca 2022).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bontempo, G., Lumetti, L., Porrello, A., Bolelli, F., Calderara, S., Ficarra, E. (2023). Buffer-MIL: Robust Multi-instance Learning with a Buffer-Based Approach. In: Foresti, G.L., Fusiello, A., Hancock, E. (eds) Image Analysis and Processing – ICIAP 2023. ICIAP 2023. Lecture Notes in Computer Science, vol 14234. Springer, Cham. https://doi.org/10.1007/978-3-031-43153-1_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-43153-1_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43152-4
Online ISBN: 978-3-031-43153-1
eBook Packages: Computer ScienceComputer Science (R0)