Abstract
Digital Whole Slide Imaging (WSI) systems allow scanning complete probes at microscopic resolutions, making image compression inevitable to reduce storage costs. While lossy image compression is readily incorporated in proprietary file formats as well as the open DICOM format for WSI, its impact on deep-learning algorithms is largely unknown. We compare the performance of several deep learning classification architectures on different datasets using a wide range and different combinations of compression ratios during training and inference. We use ImageNet pre-trained models, which is commonly applied in computational pathology. With this work, we present a quantitative assessment on the effects of repeated lossy JPEG compression for ImageNet pre-trained models. We show adverse effects for a classification task, when certain quality factors are combined during training and inference.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abels, E.,et al.: Computational pathology definitions, best practices, and recommendations for regulatory guidance: a white paper from the digital pathology association. J. Pathol. 249(3), 286–294 (2019). https://doi.org/10.1002/path.5331, https://onlinelibrary.wiley.com/doi/10.1002/path.5331
Chen, Y., Janowczyk, A., Madabhushi, A.: Quantitative assessment of the effects of compression on deep learning in digital pathology image analysis. JCO Clin. Cancer Inform. 4, 221–233 (2020). https://doi.org/10.1200/CCI.19.00068
Ciga, O., Xu, T., Martel, A.L.: Self supervised contrastive learning for digital histopathology. arXiv:2011.13971 [cs, eess] (2021)
Clunie, D.A.: DICOM format and protocol standardization-a core requirement for digital pathology success. Toxicol. Pathol. 49(4), 738–749 (2020). https://doi.org/10.1177/0192623320965893, https://journals.sagepub.com/doi/10.1177/0192623320965893
Cui, M., Zhang, D.Y.: Artificial intelligence and computational pathology. Lab. Invest. 101(4), 412–422 (2021). https://doi.org/10.1038/s41374-020-00514-0, https://www.nature.com/articles/s41374-020-00514-0
Dosovitskiy, A., et al.: An image is worth 16 \(\times \) 16 words: transformers for image recognition at scale. arXiv:2010.11929 [cs] (2021)
Doyle, S., et al.: Evaluation of effects of JPEG2000 compression on a computer-aided detection system for prostate cancer on digitized histopathology. In: 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 1313–1316. IEEE (2010). https://doi.org/10.1109/ISBI.2010.5490238, https://ieeexplore.ieee.org/document/5490238/
Ehteshami Bejnordi, B., et al.: The CAMELYON16 consortium: diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318(22), 2199 (2017). https://doi.org/10.1001/jama.2017.14585, https://jama.jamanetwork.com/article.aspx?doi=10.1001/jama.2017.14585
Fedorov, A., et al.: NCI imaging data commons. Can. Res. 81(16), 4188–4193 (2021). https://doi.org/10.1158/0008-5472.CAN-21-0950, https://aacrjournals.org/cancerres/article/81/16/4188/670283/NCI-Imaging-Data-CommonsNCI-Imaging-Data-Commons
Ghazvinian Zanjani, F., Zinger, S., Piepers, B., Mahmoudpour, S., Schelkens, P.: Impact of JPEG 2000 compression on deep convolutional neural networks for metastatic cancer detection in histopathological images. J. Med. Imaging 6(2), 1 (2019). https://doi.org/10.1117/1.JMI.6.2.027501
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv:1512.03385 [cs] (2015)
Herrmann, M.D., et al.: Implementing the DICOM standard for digital pathology. J. Pathol. Inform. 9, 37 (2018). https://doi.org/10.4103/jpi.jpi_42_18
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. arXiv:1608.06993 [cs] (2018)
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50\(\times \) fewer parameters and \(<\)0.5 mb model size. arXiv:1602.07360 [cs] (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017). https://doi.org/10.1145/3065386
Macenko, M., et al: A method for normalizing histology slides for quantitative analysis. In: 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 1107–1110 (2009). https://doi.org/10.1109/ISBI.2009.5193250
McBee, M.P., et al.: Deep learning in radiology. Acad. Radiol. 25(11), 1472–1480 (2018). https://doi.org/10.1016/j.acra.2018.02.018, https://linkinghub.elsevier.com/retrieve/pii/S1076633218301041
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge (2015). arxiv.org/abs/1409.0575
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs] (2015)
Sreelekha, G., Sathidevi, P.: An improved JPEG compression scheme using human visual system model. In: 2007 14th International Workshop on Systems, Signals and Image Processing and 6th EURASIP Conference focused on Speech and Image Processing, Multimedia Communications and Services, pp. 98–101 (2007). https://doi.org/10.1109/IWSSIP.2007.4381162
Stathonikos, N., Nguyen, T.Q., van Diest, P.J.: Rocky road to digital diagnostics: implementation issues and exhilarating experiences. J. Clin. Pathol. 74(7), 415–420 (2021). https://doi.org/10.1136/jclinpath-2020-206715, https://onlinelibrary.wiley.com/doi/10.1111/his.13953
Stathonikos, N., Nguyen, T.Q., Spoto, C.P., Verdaasdonk, M.A.M., Diest, P.J.: Being fully digital: perspective of a Dutch academic pathology laboratory. Histopathology 75(5), 621–635 (2019). https://doi.org/10.1111/his.13953, https://onlinelibrary.wiley.com/doi/10.1111/his.13953
Telegraph, T.I., Committee, T.C.: Digital compression and coding of continuous-tone still images - requirements and guidelines. https://www.w3.org/Graphics/JPEG/itu-t81.pdf
Vahadane, A., et al.: Structure-preserving color normalization and sparse stain separation for histological images. IEEE Trans. Med. Imaging 35(8), 1962–1971 (2016). https://doi.org/10.1109/TMI.2016.2529665, https://ieeexplore.ieee.org/document/7460968/
Wallace, G.: The JPEG still picture compression standard. IEEE Trans. Consum. Electron. 38(1), 18–34 (1992). https://doi.org/10.1109/30.125072
Acknowledgements
This work was partially supported by the DKTK Joint Funding UPGRADE, Project “Subtyping of pancreatic cancer based on radiographic and pathological features” (SUBPAN), and by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under the grant 410981386. Furthermore, we thank Tassilo Wald from the German Cancer Research Center for his feedback on the manuscript.
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
Fischer, M. et al. (2022). Deep Learning on Lossily Compressed Pathology Images: Adverse Effects for ImageNet Pre-trained Models. In: Huo, Y., Millis, B.A., Zhou, Y., Wang, X., Harrison, A.P., Xu, Z. (eds) Medical Optical Imaging and Virtual Microscopy Image Analysis. MOVI 2022. Lecture Notes in Computer Science, vol 13578. Springer, Cham. https://doi.org/10.1007/978-3-031-16961-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-16961-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16960-1
Online ISBN: 978-3-031-16961-8
eBook Packages: Computer ScienceComputer Science (R0)
