Fetching the paper…

Reading the bibliography…

2019

A Closer Look at Domain Shift for Deep Learning in Histopathology

Stacke, Karin, Eilertsen, Gabriel, Unger, Jonas et al.

Original
PDF
Post on X

Understand

Domain shift is a significant problem in histopathology.

There can be large differences in data characteristics of whole-slide images between medical centers and scanners, making generalization of deep learning to unseen data difficult.
To gain a better understanding of the problem, we present a study on convolutional neural networks trained for tumor classification of H&E stained whole-slide images.
We analyze how augmentation and normalization strategies affect performance and learned representations, and what features a trained model respond to.

A Closer Look at Domain Shift for Deep Learning in Histopathology · Around

Built on

Frosst, N., et al.: Analyzing and Improving Representations with the Soft Nearest Neighbor Loss. arXiv:1902.01889 [cs, stat] (Feb 2019), arXiv: 1902.01889
Original
1902
Earlier work this paper cites.
Raghu, M., et al.: Transfusion: Understanding Transfer Learning with Applications to Medical Imaging. arXiv:1902.07208 [cs, stat] (Feb 2019), arXiv: 1902.07208
Original
1902
Earlier work this paper cites.
Tellez, D., et al.: Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology. arXiv:1902.06543 [cs] (Feb 2019), arXiv: 1902.06543
Original
1902
Earlier work this paper cites.
Deng, J., et al.: ImageNet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. pp. 248–255 (Jun 2009). https://doi.org/10.1109/CVPR.2009.5206848
2009
Earlier work this paper cites.
Erhan, D., et al.: Visualizing Higher-Layer Features of a Deep Network. University of Montreal (Jan 2009)
2009
Earlier work this paper cites.
Quiñonero-Candela, J. (ed.): Dataset shift in machine learning. Neural information processing series, MIT Press, Cambridge, Mass (2009), oCLC: ocn227205909
2009
Earlier work this paper cites.
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR 2011. pp. 1521–1528 (Jun 2011)
2011
Earlier work this paper cites.
Yagi, Y.: Color standardization and optimization in Whole Slide Imaging. Report, BioMed Central (Dec 2011)
2011
Earlier work this paper cites.
Szegedy, C., et al.: Going Deeper with Convolutions. arXiv:1409.4842 [cs] (Sep 2014), arXiv: 1409.4842
Original
2014
Earlier work this paper cites.

Similar

He, K., et al.: Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 770–778 (Jun 2016)
2016
Cited alongside, same era.
Keskar, N.S., et al.: On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arXiv:1609.04836 [cs, math] (Sep 2016), arXiv: 1609.04836
Original
2016
Cited alongside, same era.
Kurakin, A., et al.: Adversarial examples in the physical world. arXiv:1607.02533 [cs, stat] (Jul 2016), arXiv: 1607.02533
Original
2016
Cited alongside, same era.
Szegedy, C., et al.: Rethinking the Inception Architecture for Computer Vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2818–2826. IEEE, Las Vegas, NV, USA (Jun 2016)
2016
Cited alongside, same era.

Then

Schultheiss, A., et al.: Finding the Unknown: Novelty Detection with Extreme Value Signatures of Deep Neural Activations. In: Roth, V., Vetter, T. (eds.) Pattern Recognition. pp. 226–238. Lecture Notes in Computer Science, Springer International Publishing (2017)
2017
Later among the works it cites.
Zhu, J.Y., et al.: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. arXiv:1703.10593 [cs] (Mar 2017), arXiv: 1703.10593
Original
2017
Later among the works it cites.
Arvidsson, I., et al.: Generalization of prostate cancer classification for multiple sites using deep learning. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). pp. 191–194 (Apr 2018)
2018
Later among the works it cites.
Bentaieb, A., Hamarneh, G.: Adversarial Stain Transfer for Histopathology Image Analysis. IEEE Transactions on Medical Imaging 37
2018
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Vahadane, A., et al.: Structure-Preserving Color Normalization and Sparse Stain Separation for Histological Images. IEEE Transactions on Medical Imaging 35

2016

Cited alongside, same era.

Ciompi, F., et al.: The importance of stain normalization in colorectal tissue classification with convolutional networks. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). pp. 160–163 (Apr 2017)

2017

Cited alongside, same era.

Lafarge, M.W., et al.: Domain-adversarial neural networks to address the appearance variability of histopathology images. arXiv:1707.06183 [cs] 10553

2017

Cited alongside, same era.

Olah, C., Mordvintsev, A., Schubert, L.: Feature Visualization. Distill 2

2017

Cited alongside, same era.

Geirhos, R., et al.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv:1811.12231 [cs, q-bio, stat] (Nov 2018), arXiv: 1811.12231

2018

Later among the works it cites.

Litjens, G., et al.: 1399 H&E-stained sentinel lymph node sections of breast cancer patients: the CAMELYON dataset. Gigascience 7

2018

Later among the works it cites.

Papernot, N., McDaniel, P.: Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning. arXiv:1803.04765 [cs, stat] (Mar 2018), arXiv: 1803.04765

2018

Later among the works it cites.

Tellez, D., et al.: H and E stain augmentation improves generalization of convolutional networks for histopathological mitosis detection. In: Medical Imaging 2018: Digital Pathology. vol. 10581, p. 105810Z. International Society for Optics and Photonics (Mar 2018)

2018

Later among the works it cites.