Abstract
Since the introduction of digital and computational pathology as a field, one of the major problems in the clinical application of algorithms has been the struggle to generalize well to examples outside the distribution of the training data. Existing work to address this in both pathology and natural images has focused almost exclusively on classification tasks. We explore and evaluate the robustness of the 7 best performing nuclear segmentation and classification models from the largest computational pathology challenge for this problem to date, the CoNIC challenge. We demonstrate that existing state-of-the-art (SoTA) models are robust towards compression artifacts but suffer substantial performance reduction when subjected to shifts in the color domain. We find that using stain normalization to address the domain shift problem can be detrimental to the model performance. On the other hand, neural style transfer is more consistent in improving test performance when presented with large color variations in the wild.
Q. D. Vu and R. Jewsbury—Joint First Authors Contributed Equally.
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
Similar content being viewed by others
References
Ahn, H., Hong, Y.: Class-controlled copy-paste based cell segmentation for conic challenge. bioRxiv (2022)
Azzuni, H., Ridzuan, M., Xu, M., Yaqub, M.: Color space-based hover-net for nuclei instance segmentation and classification. arXiv preprint arXiv:2203.01940 (2022)
Böhland, M., et al.: CISCNet-a single-branch cell instance segmentation and classification network. arXiv preprint arXiv:2202.13960 (2022)
Ding, X., Zhang, X., Zhou, Y., Han, J., Ding, G., Sun, J.: Scaling up your kernels to \(31\times 31\): Revisiting large kernel design in CNNs. arXiv preprint arXiv:2203.06717 (2022)
Elston, C., Ellis, I.: Pathological prognostic factors in breast cancer. i. the value of histological grade in breast cancer: experience from a large study with long-term follow-up. Histopathology. 19(5), 403–410 (1991). https://doi.org/10.1111/j.1365-2559.1991.tb00229.x, https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1365-2559.1991.tb00229.x
Fusi, A., et al.: PD-L1 expression as a potential predictive biomarker. Lancet Oncol. 16(13), 1285–7 (2015)
Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. CoRR abs/1508.06576 (2015). arxiv.org:1508.06576
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. CoRR abs/1811.12231 (2018). arxiv.org:1811.12231
Graham, S., et al.: Lizard: a large-scale dataset for colonic nuclear instance segmentation and classification. arXiv preprint arXiv:2108.11195 (2021)
Graham, S., et al.: Conic: Colon nuclei identification and counting challenge 2022. CoRR abs/2111.14485 (2021). arxiv.org:abs/2111.14485
Hendrycks, D., et al.: The many faces of robustness: A critical analysis of out-of-distribution generalization. CoRR abs/2006.16241 (2020). arxiv.org:abs/2006.16241
Kirillov, A., He, K., Girshick, R.B., Rother, C., Dollár, P.: Panoptic segmentation. CoRR abs/1801.00868 (2018). arxiv.org:abs/1801.00868
Kumar, N., et al.: A multi-organ nucleus segmentation challenge. IEEE Trans. Med. Imaging 39(5), 1380–1391 (2019)
Li, J., Wang, C., Huang, B., Zhou, Z.: Convnext-backbone HoverNet for nuclei segmentation and classification. arXiv preprint arXiv:2202.13560 (2022)
Maier-Hein, et al.: Metrics reloaded: Pitfalls and recommendations for image analysis validation (2022). arxiv.org:abs/2206.01653
Ruifrok, A.C., Johnston, D.A., et al.: Quantification of histochemical staining by color deconvolution. Anal. Quant. Cytol. Histol. 23(4), 291–299 (2001)
Rumberger, J.L., Baumann, E., Hirsch, P., Kainmueller, D.: Panoptic segmentation with highly imbalanced semantic labels. arXiv preprint arXiv:2203.11692 (2022)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Shield, K.D., et al.: The global incidence of lip, oral cavity, and pharyngeal cancers by subsite in 2012. CA: Cancer J. Clin. 67(1), 51–64 (2017)
Solis, L.M., et al.: Histologic patterns and molecular characteristics of lung adenocarcinoma associated with clinical outcome. Cancer 118(11), 2889–2899 (2012)
Stacke, K., Eilertsen, G., Unger, J., Lundström, C.: Measuring domain shift for deep learning in histopathology. IEEE J. Biomed. Health Inform. 25(2), 325–336 (2020)
Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)
Vahadane, A., et al.: Structure-preserving color normalization and sparse stain separation for histological images. IEEE Trans. Med. Imaging 35(8), 1962–1971 (2016)
Verma, R., et al.: MoNuSAC 2020: a multi-organ nuclei segmentation and classification challenge. IEEE Trans. Med. Imaging 40(12), 3413–3423 (2021). https://doi.org/10.1109/TMI.2021.3085712
Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. CoRR abs/1809.00219 (2018). arxiv.org:abs/1809.00219
Weigert, M., Schmidt, U.: Nuclei segmentation and classification in histopathology images with stardist for the conic challenge 2022. arXiv preprint arXiv:2203.02284 (2022)
Yamaguchi, T., et al.: Inter-observer agreement among pathologists in grading the pathological response to neoadjuvant chemotherapy in breast cancer. Breast Cancer 25(1), 118–125 (2018)
Yamashita, R., Long, J., Banda, S., Shen, J., Rubin, D.L.: Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation. IEEE Trans. Med. Imaging 40(12), 3945–3954 (2021)
Zhang, W.: Conic solution. arXiv preprint arXiv:2203.03415 (2022)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Vu, Q.D. et al. (2022). Nuclear Segmentation and Classification: On Color and Compression Generalization. In: Lian, C., Cao, X., Rekik, I., Xu, X., Cui, Z. (eds) Machine Learning in Medical Imaging. MLMI 2022. Lecture Notes in Computer Science, vol 13583. Springer, Cham. https://doi.org/10.1007/978-3-031-21014-3_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-21014-3_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21013-6
Online ISBN: 978-3-031-21014-3
eBook Packages: Computer ScienceComputer Science (R0)