Skip to main content
Springer Nature Link
Log in

Rigid and Elastic Registrations Benchmark on Re-stained Histologic Human Ileum Images

  • Conference paper
  • First Online:
Information Technology in Biomedicine (ITIB 2022)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1429))

Included in the following conference series:

Abstract

Registration of images from re-stained tissue sections is an initial step in generating ground truth image data for machine learning applications in histopathology. In this paper, we focused on evaluating existing feature-based and intensity-based registration methods using regions of interest (ROIs) extracted from whole slide images (n = 25) of human ileum that was first stained with hematoxylin and eosin (H&E) and then re-stained with immunohistochemistry (IHC). Elastic and moving least squares deformation models with rigid, affine and similarity feature matching were compared with intensity-based methods utilizing an optimizer to find rigid and affine transformation parameters. Corresponding color H&E and IHC ROIs were registered through gray-level luminance and deconvoluted hematoxylin images. Our goal was to identify methods that can yield a high number of correctly registered ROIs and low median (MTRE) and average (ATRE) target registration errors. Based on the benchmark landmarks (n = 5020) placed across the ROIs, the elastic deformation model with rigid matching and the intensity-based rigid registrations on color-deconvoluted hematoxylin channels yielded the highest (86%, 100%) rates of correctly registered ROIs. For these two methods, the MTRE was 2.00 and 2.12 pixels (\(0.982\) \(\,\upmu \) m, \(1.04\) \(\,\upmu \) m), and ATRE was 3.14 and 4.0 pixels (1.54\(\,\upmu \) m, 1.964\(\,\upmu \) m), respectively. Although the intensity-based rigid registration was the slowest of all methods tested, it may be more practical in use due to the highest rate of correctly registered ROIs and the second-best MTRE. The WSIs and ROIs with landmarks that we prepared can be valuable in benchmarking other image registration approaches.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Anand, D., et al.: Deep learning to estimate human epidermal growth factor receptor 2 status from hematoxylin and eosin-stained breast tissue images. J. Pathol. Inform. 11, 19 (2020). https://doi.org/10.4103/jpi.jpi_10_20

    Article  Google Scholar 

  2. Arganda-Carreras, I., Sorzano, C.O.S., Marabini, R., Carazo, J.M., Ortiz-de-Solorzano, C., Kybic, J.: Consistent and elastic registration of histological sections using vector-spline regularization. In: Beichel, R.R., Sonka, M. (eds.) CVAMIA 2006. LNCS, vol. 4241, pp. 85–95. Springer, Heidelberg (2006). https://doi.org/10.1007/11889762_8

    Chapter  Google Scholar 

  3. Borovec, J., et al.: Anhir: automatic non-rigid histological image registration challenge. IEEE Trans. Med. Imaging PP, 1–1 (2020). https://doi.org/10.1109/TMI.2020.2986331

  4. Bulten, W., et al.: Epithelium segmentation using deep learning in h&e-stained prostate specimens with immunohistochemistry as reference standard. Scientific Reports 9, 864 (2019). https://doi.org/10.1038/s41598-018-37257-4

  5. Bándi, P., Balkenhol, M., Ginneken, B., Laak, J., Litjens, G.: Resolution-agnostic tissue segmentation in whole-slide histopathology images with convolutional neural networks. PeerJ 7, e8242 (2019). https://doi.org/10.7717/peerj.8242

    Article  Google Scholar 

  6. Chen, C.T.: Radiologic image registration: old skills and new tools. Acad. Radiol. 10, 239–41 (2003)

    Article  MathSciNet  Google Scholar 

  7. Cooper, L., Sertel, O., Kong, J., Lozanski, G., Huang, K., Gurcan, M.: Feature-based registration of histopathology images with different stains: an application for computerized follicular lymphoma prognosis. Comput. Methods Programs Biomed. 96, 182–92 (2009). https://doi.org/10.1016/j.cmpb.2009.04.012

    Article  Google Scholar 

  8. Fedorov, A., et al.: 3D slicer as an image computing platform for the quantitative imaging network. Magnetic Resonance Imaging 30, 1323–41 (2012). https://doi.org/10.1016/j.mri.2012.05.001. https://www.slicer.org

  9. Fitzpatrick, J., West, J.: The distribution of target registration error in rigid-body point-based registration. IEEE Trans. Med. Imaging 20(9), 917–927 (2001). https://doi.org/10.1109/42.952729

    Article  Google Scholar 

  10. Gallego, J., Swiderska, Z., Markiewicz, T., Yamashita, M., Gabaldon, M., Gertych, A.: A u-net based framework to quantify glomerulosclerosis in digitized pas and h&e stained human tissues. Computerized Medical Imaging and Graphics 89, 101,865 (2021). https://doi.org/10.1016/j.compmedimag.2021.101865

  11. Ghahremani, M., et al.: Rigid Registration, pp. 1087–1099. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-63416-2_184

  12. Gonzalez, D., Frafjord, A., Øynebråten, I., Corthay, A., Olivo-Marin, J.C., Meas-Yedid, V.: Multi-staining registration of large histology images. In: 2017 IEEE 14th International Symposium on Biomedical Imaging, pp. 345–348 (2017). https://doi.org/10.1109/ISBI.2017.7950534

  13. Hatipoglu, N., Bilgin, G.: Cell segmentation in histopathological images with deep learning algorithms by utilizing spatial relationships. Med. Biol. Eng. Comput. 55(10), 1829–1848 (2017). https://doi.org/10.1007/s11517-017-1630-1

    Article  Google Scholar 

  14. Hinton, J., et al.: A method to reuse archived h&e stained histology slides for a multiplex protein biomarker analysis. Methods Prot. 2, 86 (2019). https://doi.org/10.3390/mps2040086

    Article  Google Scholar 

  15. Ing, N., et al.: A novel machine learning approach reveals latent vascular phenotypes predictive of renal cancer outcome. Sci. Rep. 7 (2017). https://doi.org/10.1038/s41598-017-13196-4

  16. Jiang, J., Larson, N., Prodduturi, N., Flotte, T., Hart, S.: Robust hierarchical density estimation and regression for re-stained histological whole slide image co-registration. PLoS ONE 14, e0220,074 (2019). https://doi.org/10.1371/journal.pone.0220074

  17. Johnson, H., Christensen, G.: Consistent landmark and intensity-based image registration. IEEE Trans. Med. Imaging 21, 450–61 (2002). https://doi.org/10.1109/TMI.2002.1009381

    Article  Google Scholar 

  18. Kuska, J.P., et al.: Image registration of differently stained histological sections. In: 2006 International Conference on Image Processing, pp. 333–336 (2006). https://doi.org/10.1109/ICIP.2006.313161

  19. Kybic, J., Dolejší, M., Borovec, J.: Fast registration of segmented images by normal sampling. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (2015). https://doi.org/10.1109/CVPRW.2015.7301311

  20. Lotz, J., Weiss, N., van der Laak, J., Heldmann, S.: High-resolution image registration of consecutive and re-stained sections in histopathology (2021). ArXiv:2106.13150

  21. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004). https://doi.org/10.1023/b:visi.0000029664.99615.94

    Article  Google Scholar 

  22. Ma, Z., et al.: Semantic segmentation of colon glands in inflammatory bowel disease biopsies. In: Pietka, E., Badura, P., Kawa, J., Wieclawek, W. (eds.) ITIB 2018. AISC, vol. 762, pp. 379–392. Springer, Cham (2019). https://doi.org/10.1007/978-3-319-91211-0_34

    Chapter  Google Scholar 

  23. Maes, F., Vandermeulen, D., Suetens, P.: Medical image registration using mutual information. Proc. IEEE 91(10), 1699–1722 (2003). https://doi.org/10.1109/jproc.2003.817864

    Article  Google Scholar 

  24. Menon, H., Narayanankutty, K.A.: Applicability of non-rigid medical image registration using moving least squares. Int. J. Comput. Appl. 1, 85–92 (2010). https://doi.org/10.5120/138-256

    Article  Google Scholar 

  25. Mäkelä, T., et al.: A review of cardiac image registration methods. IEEE Trans. Med. Imaging 21, 1011–21 (2002). https://doi.org/10.1109/TMI.2002.804441

    Article  Google Scholar 

  26. Nirschl, J., et al.: Chapter 8 - Deep Learning Tissue Segmentation in Cardiac Histopathology Images, pp. 179–195. Academic Press (2017). https://doi.org/10.1016/B978-0-12-810408-8.00011-0

  27. Oliveira, F.P., Tavares, J.M.R.: Medical image registration: a review. Comput. Methods Biomech. Biomed. Engin. 17(2), 73–93 (2014). https://doi.org/10.1080/10255842.2012.670855

    Article  Google Scholar 

  28. Ourselin, S., Roche, A., Subsol, G., Pennec, X., Ayache, N.: Reconstructing a 3D structure from serial histological sections. Image Vis. Comput. 19, 25–31 (2001). https://doi.org/10.1016/S0262-8856(00)00052-4

    Article  Google Scholar 

  29. Pantanowitz, L., et al.: Review of the current state of whole slide imaging in pathology. J. Pathol. Inform. 2, 36 (2011). https://doi.org/10.4103/2153-3539.83746

    Article  Google Scholar 

  30. Pitiot, A., Bardinet, E., Thompson, P., Malandain, G.: Piecewise affine registration of biological images for volume reconstruction. Med. Image Anal. 10, 465–83 (2006). https://doi.org/10.1016/j.media.2005.03.008

    Article  MATH  Google Scholar 

  31. Pyciński, B., Yagi, Y., Walts, A.E., Gertych, A.: 3-D tissue image reconstruction from digitized serial histologic sections to visualize small tumor nests in lung adenocarcinomas. In: Pietka, E., Badura, P., Kawa, J., Wieclawek, W. (eds.) Information Technology in Biomedicine. AISC, vol. 1186, pp. 55–70. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-49666-1_5

    Chapter  Google Scholar 

  32. Ruifrok, A.C., Johnston, D.A.: Quantification of histochemical staining by color deconvolution. Anal. Quant. Cytol. Histol. 23(4), 291–299 (2001)

    Google Scholar 

  33. Ruusuvuori, P., et al.: Spatial analysis of histology in 3D: quantification and visualization of organ and tumor level tissue environment. Heliyon p. e08762 (2022). https://doi.org/10.1016/j.heliyon.2022.e08762

  34. Schaefer, S., McPhail, T., Warren, J.: Image deformation using moving least squares. In: ACM SIGGRAPH 2006 Papers on - SIGGRAPH 2006. ACM Press (2006). https://doi.org/10.1145/1179352.1141920

  35. Schindelin, J., et al.: Fiji: an open-source platform for biological-image analysis. Nat. Methods 9(7), 676–682 (2012). https://doi.org/10.1038/nmeth.2019

    Article  Google Scholar 

  36. Styner, M., Brechbuhler, C., Szckely, G., Gerig, G.: Parametric estimate of intensity inhomogeneities applied to MRI. IEEE Trans. Med. Imaging 19(3), 153–165 (2000). https://doi.org/10.1109/42.845174

    Article  Google Scholar 

  37. Williams, J.M., Duckworth, C.A., Vowell, K., Burkitt, M.D., Pritchard, D.M.: Intestinal preparation techniques for histological analysis in the mouse. Curr. Prot. Mouse Biol. 6(2), 148–168 (2016). https://doi.org/10.1002/cpmo.2

    Article  Google Scholar 

Download references

Acknowledgement

This project was in part supported by the grant from the Helmsley Charitable Trust and the grants from the Silesian University of Technology no. BK-231/RIB1/2022 and 31/010/SDU20/0006-10 (Excellence Initiative – Research University). The authors would also like to thank the Cedars-Sinai Biobank for preparation and digitization of slides.

Author information

Authors and Affiliations

  1. Department of Cardiac Anaesthesiology and Intensive Care, Faculty of Medical Sciences in Zabrze, Medical University of Silesia in Katowice, ul. M. Curie-Skłodowskiej 9, 41-800, Zabrze, Poland

    Paweł Cyprys

  2. Faculty of Biomedical Engineering, Silesian University of Technology, ul. Roosevelta 40, 41-800, Zabrze, Poland

    Natalia Wyleżoł, Adrianna Jagodzińska, Julia Uzdowska, Bartłomiej Pyciński & Arkadiusz Gertych

  3. Department of Surgery, Cedars-Sinai Medical Center, Los Angeles, USA

    Arkadiusz Gertych

  4. Department of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, 90048, USA

    Arkadiusz Gertych

Authors
  1. Paweł Cyprys
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Natalia Wyleżoł
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Adrianna Jagodzińska
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Julia Uzdowska
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bartłomiej Pyciński
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Arkadiusz Gertych
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Arkadiusz Gertych .

Editor information

Editors and Affiliations

  1. Faculty of Biomedical Engineering, Silesian University of Technology, Gliwice, Poland

    Ewa Pietka

  2. Faculty of Biomedical Engineering, Silesian University of Technology, Gliwice, Poland

    Pawel Badura

  3. Faculty of Biomedical Engineering, Silesian University of Technology, Gliwice, Poland

    Jacek Kawa

  4. Faculty of Biomedical Engineering, Silesian University of Technology, Gliwice, Poland

    Wojciech Wieclawek

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Cyprys, P., Wyleżoł, N., Jagodzińska, A., Uzdowska, J., Pyciński, B., Gertych, A. (2022). Rigid and Elastic Registrations Benchmark on Re-stained Histologic Human Ileum Images. In: Pietka, E., Badura, P., Kawa, J., Wieclawek, W. (eds) Information Technology in Biomedicine. ITIB 2022. Advances in Intelligent Systems and Computing, vol 1429. Springer, Cham. https://doi.org/10.1007/978-3-031-09135-3_23

Download citation

Publish with us

Policies and ethics