Skip to main content
SpringerLink
Log in

Automated Method for Optimum Scale Search when Using Trained Models for Histological Image Analysis

  • Published:
Programming and Computer Software Aims and scope Submit manuscript

Abstract

Preparation of input data for an artificial neural network is a key step to achieve a high accuracy of its predictions. It is well known that convolutional neural models have low invariance to changes in the scale of input data. For instance, processing multiscale whole-slide histological images by convolutional neural networks naturally poses a problem of choosing an optimal processing scale. In this paper, this problem is solved by iterative analysis of distances to a separating hyperplane that are generated by a convolutional classifier at different input scales. The proposed method is tested on the DenseNet121 deep architecture pre-trained on PATH-DT-MSU data, which implements patch classification of whole-slide histological images.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.

Similar content being viewed by others

Notes

  1. https://imaging.cs.msu.ru/en/research/histology/path-dt-msu

REFERENCES

  1. Park, S., Pantanowitz, L., and Parwani, A.V., Digital imaging in pathology, Clin. Lab. Med., 2012, vol. 32, no. 4, pp. 557–584.

    Article  Google Scholar 

  2. Pantanowitz, L., Valenstein, P.N., Evans, A.J., Kaplan, K.J., Pfeifer, J.D., Wilbur, D.C., Collins, L.C., and Colgan, T.J., Review of the current state of whole slide imaging in pathology, J. Pathol. Inf., 2012, vol. 2, no. 1, p. 36.

    Article  Google Scholar 

  3. Saco, A., Bombi, J.A., Garcia, A., Ramírez, J., and Ordi, J., Current status of whole-slide imaging in education, Pathobiol., 2016, vol. 83, nos. 2–3, pp. 79–88.

    Article  Google Scholar 

  4. Farahani, N., Parwani, A.V., and Pantanowitz, L., Whole slide imaging in pathology: Advantages, limitations, and emerging perspectives, Pathol. Lab. Med. Int., 2015, vol. 7, nos. 23–33, p. 4321.

  5. Rojo, M.G., García, G.B., Mateos, C.P., García, J.G., and Vicente, M.C., Critical comparison of 31 commercially available digital slide systems in pathology, Int. J. Surg. Pathol., 2006, vol. 14, no. 4, pp. 285–305.

    Article  Google Scholar 

  6. Ronneberger, O., Fischer, P., and Brox, T., U-Net: Convolutional networks for biomedical image segmentation, Proc. Int. Conf. Medical Image Computing and Computer-Assisted Intervention, 2015, pp. 234–241.

  7. Khvostikov, A., Krylov, A.S., Mikhailov, I., and Malkov, P., CNN assisted hybrid algorithm for medical images segmentation, Proc. 5th Int. Conf. Biomedical Signal and Image Processing, 2020, pp. 14–19.

  8. Getmanskaya, A.A., Sokolov, N.A., and Turlapov, V.E., Multiclass U-Net segmentation of brain electron microscopy data using original and semi-synthetic training datasets, Program. Comput. Software, 2022, vol. 48, no. 3, pp. 164–171.

    Article  Google Scholar 

  9. Gong, Y., Wang, L., Guo, R., and Lazebnik, S., Multi-scale orderless pooling of deep convolutional activation features, Proc. Eur. Conf. Computer Vision, 2014, pp. 392–407.

  10. Khvostikov, A.V., Krylov, A.S., Mikhailov, I.A., and Malkov, P.G., Visualization of whole slide histological images with automatic tissue type recognition, Pattern Recognit. Image Anal., 2022, vol. 32, no. 3, pp. 483–488.

    Article  Google Scholar 

  11. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q., Densely connected convolutional networks, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2017, pp. 4700–4708.

  12. Kingma, D.P. and Ba, J., Adam: A method for stochastic optimization, 2014.

  13. He, K., Zhang, X., Ren, S., and Sun, J., Deep residual learning for image recognition, Proc. CVPR IEEE Conf., 2016, pp. 770–778.

  14. Simonyan, K. and Zisserman, A., Very deep convolutional networks for large-scale image recognition, 2014.

  15. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A., Going deeper with convolutions, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2015, pp. 1–9.

  16. Penkin, M.A., Khvostikov, A.V., and Krylov, A.S., Optimal input scale transformation search for deep classification neural networks, Proc. Conf. Computer Graphics and Vision (GraphiCon), 2022, vol. 32, pp. 668–677.

  17. Krizhevsky, A., Sutskever, I., and Hinton, G.E., Imagenet classification with deep convolutional neural networks, Commun. ACM, 2017, vol. 60, no. 6, pp. 84–90.

    Article  Google Scholar 

  18. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L., Imagenet: A large-scale hierarchical image database, Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009, pp. 248–255.

  19. Bolme, D.S., Beveridge, J.R., Draper, B.A., and Lui, Y.M., Visual object tracking using adaptive correlation filters, Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 2010, pp. 2544–2550.

  20. Mohri, M., Rostamizadeh, A., and Talwalkar, A., Foundations of Machine Learning, MIT Press, 2018.

    MATH  Google Scholar 

Download references

Funding

This work was supported by the Russian Science Foundation, project no. 22-41-02002.

Author information

Authors and Affiliations

  1. Laboratory of Mathematical Methods of Image Processing, Faculty of Computational Mathematics and Cybernetics, Moscow State University, Moscow, Russia

    M. A. Penkin, A. V. Khvostikov & A. S. Krylov

Authors
  1. M. A. Penkin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. V. Khvostikov
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. A. S. Krylov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to M. A. Penkin, A. V. Khvostikov or A. S. Krylov.

Ethics declarations

The authors declare that they have no conflicts of interest.

Additional information

Translated by Yu. Kornienko

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Penkin, M.A., Khvostikov, A.V. & Krylov, A.S. Automated Method for Optimum Scale Search when Using Trained Models for Histological Image Analysis. Program Comput Soft 49, 172–177 (2023). https://doi.org/10.1134/S0361768823030039

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S0361768823030039

Search

Navigation