Abstract
Artificial Intelligence (AI) and Machine Learning (ML) are becoming some of the most dominant tools in scientific research. Despite this, little is often understood about the complex decisions taken by the models in predicting their results. This disproportionately affects biomedical and healthcare research where explainability of AI is one of the requirements for its wide adoption. To help answer the question of what the network is looking at when the labels do not correspond to the presence of objects in the image but the context in which they are found, we propose a novel framework for Explainable AI that combines and simultaneously analyses Class Activation and Segmentation Maps for thousands of images. We apply our approach to two distinct, complex examples of real-world biomedical research, and demonstrate how it can be used to provide a global and concise numerical measurement of how distinct classes of objects affect the final classification. We also show how this can be used to inform model selection, architecture design and aid traditional domain researchers in interpreting the model results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Provided by the Department of Information Technology at Universitá degli Studi di Milano, https://homes.di.unimi.it/scotti/all/.
References
McKinney, S.M., Sieniek, M., Godbole, V., et al.: International evaluation of an AI system for breast cancer screening. Nature 577, 89–94 (2020). https://doi.org/10.1038/s41586-019-1799-6
Artificial intelligence-created medicine to be used on humans for the first time. Exscientia. https://www.exscientia.ai/news-insights/artificial-intelligence-created-medicine-to-be-used. Accessed 21 Jan 2021
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016, pp. 2921–2929 (2016). https://doi.org/10.1109/CVPR.2016.319
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you?: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016). https://doi.org/10.1145/2939672.2939778
Ghassemi, M., Oakden-Rayner, L., Andrew, B.L.: The false hope of current approaches to explainable artificial intelligence in health care. Lancet Digit. Health 3, 745–750 (2021). https://doi.org/10.1016/S2589-7500(21)00208-9
Jia, S., Lansdall-Welfare, T., Cristianini, N.: Right for the right reason: training agnostic networks. In: Duivesteijn, W., Siebes, A., Ukkonen, A. (eds.) IDA 2018. LNCS, vol. 11191, pp. 164–174. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01768-2_14
Overton, T., Tucker, A.: DO-U-Net for segmentation and counting. In: Berthold, M.R., Feelders, A., Krempl, G. (eds.) IDA 2020. LNCS, vol. 12080, pp. 391–403. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-44584-3_31
Overview: acute lymphoblastic leukaemia. NHS. https://www.nhs.uk/conditions/acute-lymphoblastic-leukaemia/. Accessed 01 Nov 2021
Acute Lymphoblastic Leukemia Image Database for Image Processing. Department of Computer Science - Universitá degli Studi di Milano. https://homes.di.unimi.it/scotti/all/#. Accessed 01 Nov 2021
Paul, S.M., et al.: How to improve R&D productivity: the pharmaceutical industry’s grand challenge. Nat. Rev. Drug Discov. 9(3), 203–214 (2010). https://doi.org/10.1038/nrd3078
Chan, S.H.C., Shan, H., Dahoun, T., Vogel, H., Yuan, S.: Advancing drug discovery via artificial intelligence. Trends Pharmacol. Sci. 40, 592–604 (2019). https://doi.org/10.1016/j.tips.2019.06.004
Zhu, H.: Big data and artificial intelligence modeling for drug discovery. Ann. Rev. Pharmacol. Toxicol. 60, 573–589 (2020). https://doi.org/10.1146/annurev-pharmtox-010919-023324. First published as a Review in Advance in September 2019
Hofmarcher, M., Rumetshofer, E., Clevert, D.-A., Hochreiter, S., Klambauer, G.: Accurate prediction of biological assays with high-throughput microscopy images and convolutional networks. J. Chem. Inf. Model. 59(3), 1163–1171 (2019). https://doi.org/10.1021/acs.jcim.8b00670
Bray, M.-A., et al.: A dataset of images and morphological profiles of 30000 small-molecule treatments using the Cell Painting assay. GigaScience 6(12), giw014 (2017). https://doi.org/10.1093/gigascience/giw014
The ChEMBL Database. https://www.ebi.ac.uk/chembl/. Accessed 01 Nov 2021
ECACC General Cell Collection: U-2 OS, Public Health England. https://www.phe-culturecollections.org.uk/products/celllines/generalcell/detail.jsp?refId=92022711&collection=ecacc_gc. Accessed 20 Jan 2021
Ghadezadeh, M., Asadi, F., Hosseini, A., Bashash, D., Abolghasemi, H., Roshanpoor, A.: Machine learning in detection and classification of leukemia using smear blood images: a systematic review. Sci. Program. 2021(06), 1–14 (2021). https://doi.org/10.1155/2021/9933481
Sharif, M., et al.: Recognition of different types of leukocytes using YOLOv2 and optimized bag-of-features. IEEE Access 8, 167448–167459 (2020). https://doi.org/10.1109/ACCESS.2020.3021660
Vogado, L.H.S., Veras, R.M.S., Araujo, F.H.D., Silva, R.R.V., Aires, K.R.T.: Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification. Eng. Appl. Artif. Intell. 72, 415–422 (2018). https://doi.org/10.1016/j.engappai.2018.04.024
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261–2269 (2017). https://doi.org/10.1109/CVPR.2017.243
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2015). https://doi.org/10.1109/CVPR.2016.90
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Acknowledgements
We wish to show our gratitude to Evotec for supporting this research, and specifically thank Michael Bodkin and Daniel Grindrod for providing useful insights and asking the right questions throughout the research, allowing this project to develop. We also thank Karsten Kottig for providing training masks for DO-U-Net for the Cell Painting Dataset, as well as sharing industry insight throughout the project.
We are also immensely grateful to the Department of Information Technology at Universitá degli Studi di Milano for providing the ALL_IDB1 dataset from the Acute Lymphoblastic Leukemia Image Database for Image Processing.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Overton, T., Tucker, A., James, T., Hristozov, D. (2022). dunXai: DO-U-Net for Explainable (Multi-label) Image Classification. In: Bouadi, T., Fromont, E., Hüllermeier, E. (eds) Advances in Intelligent Data Analysis XX. IDA 2022. Lecture Notes in Computer Science, vol 13205. Springer, Cham. https://doi.org/10.1007/978-3-031-01333-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-01333-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-01332-4
Online ISBN: 978-3-031-01333-1
eBook Packages: Computer ScienceComputer Science (R0)