Abstract
Virtually all endoscopic AI models are developed with clean, high-quality imagery from expert centers, however, the clinical data quality is much more heterogeneous. Endoscopic image quality can degrade by e.g. poor lighting, motion blur, and image compression. This disparity between training, validation data, and real-world clinical practice can have a substantial impact on the performance of deep neural networks (DNNs), potentially resulting in clinically unreliable models. To address this issue and develop more reliable models for automated cancer detection, this study focuses on identifying the limitations of current DNNs. Specifically, we evaluate the performance of these models under clinically relevant and realistic image corruptions, as well as on a manually selected dataset that includes images with lower subjective quality. Our findings highlight the importance of understanding the impact of a decrease in image quality and the need to include robustness evaluation for DNNs used in endoscopy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, J.-N., Sun, S., He, J., Torr, P., Yuille, A., Bai, S.: TransMix: attend to mix for vision transformers, June 2022. https://arxiv.org/abs/2111.09833
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding, April 2016. https://arxiv.org/abs/1604.01685
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248–255. IEEE (2009)
Dodge, S.F., Karam, L.J.: A study and comparison of human and deep learning recognition performance under visual distortions. CoRR, abs/1705.02498 (2017). https://arxiv.org/abs/1705.02498
Dodge, S.F., Karam, L.J.: Understanding how image quality affects deep neural networks. CoRR, abs/1604.04004 (2016). https://arxiv.org/abs/1604.04004
U.S. Food and Drug Administration. FDA authorizes marketing of first device that uses artificial intelligence to help detect potential signs of colon cancer (2021). https://www.fda.gov/news-events/press-announcements/fda-authorizes-marketing-first-device-uses-artificial-intelligence-help-detect-potential-signs-colon
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, pp. 770–778. IEEE, June 2016. https://doi.org/10.1109/CVPR.2016.90, https://ieeexplore.ieee.org/document/7780459
Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=HJz6tiCqYm
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 2261–2269. IEEE Computer Society (2017). ISBN 978-1-5386-0457-1. https://dblp.uni-trier.de/db/conf/cvpr/cvpr2017.html#HuangLMW17
Iakubovskii, P.: Segmentation models pytorch (2019). https://github.com/qubvel/segmentation_models.pytorch
Karahan, Ş., Yildirim, M.K., Kirtaç, K., Rende, F.Ş., Bütün, G., Ekenel, H.K.: How image degradations affect deep CNN-based face recognition? vol. P-260. Gesellschaft fur Informatik (GI), November 2016. ISBN 9783885796541. https://doi.org/10.1109/BIOSIG.2016.7736924
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). arxiv:1412.6980Comment. Published as a Conference Paper at the 3rd International Conference for Learning Representations, San Diego (2015)
Krizhevsky, A.: Learning multiple layers of features from tiny images (2009)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context, May 2014. https://arxiv.org/abs/1405.0312
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library, December 2019. https://arxiv.org/abs/1912.01703
Pei, Y., Huang, Y., Zou, Q., Zhang, X., Wang, S.: Effects of image degradation and degradation removal to CNN-based image classification. IEEE Trans. Pattern Anal. Mach. Intell. 43, 1239–1253 (2021). ISSN 19393539. https://doi.org/10.1109/TPAMI.2019.2950923
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation, pp. 234–241, May 2015. https://arxiv.org/abs/1505.04597
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556 (2014). https://arxiv.org/abs/1409.1556
Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. CoRR, abs/1905.11946 (2019). https://arxiv.org/abs/1905.11946
Yuba, M., Iwasaki, K.: Systematic analysis of the test design and performance of AI/ML-based medical devices approved for triage/detection/diagnosis in the USA and Japan. Sci. Rep. 12, 16874 (2022). ISSN 20452322. https://doi.org/10.1038/s41598-022-21426-7
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jaspers, T.J.M. et al. (2024). Investigating the Impact of Image Quality on Endoscopic AI Model Performance. In: Wu, S., Shabestari, B., Xing, L. (eds) Applications of Medical Artificial Intelligence. AMAI 2023. Lecture Notes in Computer Science, vol 14313. Springer, Cham. https://doi.org/10.1007/978-3-031-47076-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-47076-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47075-2
Online ISBN: 978-3-031-47076-9
eBook Packages: Computer ScienceComputer Science (R0)