Abstract
In this paper, we consider a type of image quality assessment (IQA) as a task-specific measurement, which can be used to select images that are more amenable to a given target task, such as image classification or segmentation. We propose to train simultaneously two neural networks for image selection and a target task using reinforcement learning. A controller network learns an image selection policy by maximising an accumulated reward based on the target task performance on the controller-selected validation set, whilst the target task predictor is optimised using the training set. The trained controller is therefore able to reject images that lead to poor accuracy in the target task. In this work, we show that controller-predicted IQA can be significantly different from task-specific quality labels manually defined by humans. Furthermore, we demonstrate that it is possible to learn effective IQA without a “clean” validation set, thereby avoiding the requirement for human labels of task amenability. Using 6712, labelled and segmented, clinical ultrasound images from 259 patients, experimental results on holdout data show that the proposed IQA achieved a mean classification accuracy of \(0.94\pm 0.01\) and a mean segmentation Dice of \(0.89\pm 0.02\), by discarding \(5\%\) and \(15\%\) of the acquired images, respectively. The significantly improved performance was observed for both tested tasks, compared with the respective \(0.90\pm 0.01\) and \(0.82\pm 0.02\) from networks without considering task amenability. This enables IQA feedback during real-time ultrasound acquisition among many other medical imaging applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Davis, H., Russell, S., Barriga, E., Abramoff, M., Soliz, P.: Vision-based, real-time retinal image quality assessment. In: 2009 22nd IEEE International Symposium on Computer-Based Medical Systems, pp. 1–6 (2009)
Wu, L., Cheng, J., Li, S., Lei, B., Wang, T., Ni, D.: FUIQA: fetal ultrasound image quality assessment with deep convolutional networks. IEEE Trans. Cybern. 47(5), 1336–1349 (2017)
Chow, L.S., Paramesran, R.: Review of medical image quality assessment. Biomed. Sig. Process. Control 27, 145–154 (2016)
Loizou, C.P., Pattichis, C.S., Pantziaris, M., Tyllis, T., Nicolaides, A.: Quality evaluation of ultrasound imaging in the carotid artery based on normalization and speckle reduction filtering. Med. Biol. Eng. Comput. 44, 414 (2006). https://doi.org/10.1007/s11517-006-0045-1
Köhler, T., Budai, A., Kraus, M.F., Odstrčilik, J., Michelson, G., Hornegger, J.: Automatic no-reference quality assessment for retinal fundus images using vessel segmentation. In: Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems, pp. 95–100 (2013)
Zago, G.T., Andreão, R.V., Dorizzi, B., Ottoni, E., Salles, T.: Retinal image quality assessment using deep learning. Comput. Biol. Med. 103, 64–70 (2018)
Esses, S.J., et al.: Automated image quality evaluation of T2-weighted liver MRI utilizing deep learning architecture. J. Magn. Reson. Imaging 47(3), 723–728 (2018)
Baum, Z.M.C.: Image quality assessment for closed-loop computer-assisted lung ultrasound. arXiv: 2008.08840 (2020)
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation policies from data. arXiv: 1805.09501 (2019)
Zhang, X., Wang, Q., Zhang, J., Zhong, Z.: Adversarial autoAugment. arXiv: 1912.11188 (2019)
Li, C., et al.: AM-LFS: AutoML for loss function search. In: 2019 ICCV, pp. 8409–8418 (2019)
Yoon, J., Arik, S., Pfister, T.: Data valuation using reinforcement learning. arXiv: 1909.11671 (2020)
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv: 1611.01578 (2017)
Wang, J., et al.: Auto-weighting for breast cancer classification in multimodal ultrasound. In: Matyel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12266, pp. 190–199. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59725-2_19
Yang, D., Roth, H., Xu, Z., Milletari, F., Zhang, L., Xu, D.: Searching learning strategy with reinforcement learning for 3D medical image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 3–11. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_1
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229–256 (1992)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv: 1707.06347 (2017)
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv: 1509.02971 (2019)
Uhlenbeck, G.E., Ornstein, L.S.: On the theory of the brownian motion. Phys. Rev. 36(5), 823–841 (1930)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: NeurIPS (2012)
Bressem, K.K., Adams, L.C., Erxleben, C., Hamm, B., Niehues, S.M., Vahldiek, J.L.: Comparing different deep learning architectures for classification of chest radiographs. Scientific Report. 10 (2020)
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
This work is supported by the Wellcome/EPSRC Centre for Interventional and Surgical Sciences [203145Z/16/Z], the CRUK International Alliance for Cancer Early Detection (ACED) [C28070/A30912; C73666/A31378], EPSRC CDT in i4health [EP/S021930/1], the Departments of Radiology and Urology, Stanford University, the Natural Sciences and Engineering Research Council of Canada Postgraduate Scholarships-Doctoral Program (ZMCB), the University College London Overseas and Graduate Research Scholarships (ZMCB), GE Blue Sky Award (MR), and the generous philanthropic support of our patients (GAS).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Saeed, S.U. et al. (2021). Learning Image Quality Assessment by Reinforcing Task Amenable Data Selection. In: Feragen, A., Sommer, S., Schnabel, J., Nielsen, M. (eds) Information Processing in Medical Imaging. IPMI 2021. Lecture Notes in Computer Science(), vol 12729. Springer, Cham. https://doi.org/10.1007/978-3-030-78191-0_58
Download citation
DOI: https://doi.org/10.1007/978-3-030-78191-0_58
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78190-3
Online ISBN: 978-3-030-78191-0
eBook Packages: Computer ScienceComputer Science (R0)