Advertisement

Computer Assisted Segmentation Tool: A Machine Learning Based Image Segmenting Tool for TrakEM2

  • Augustus N. TropeaEmail author
  • Janey L. Valerio
  • Michael J. Camerino
  • Josh Hix
  • Emmalee Pecor
  • Peter G. Fuerst
  • S. Seth Long
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10330)

Abstract

The recent availability of serial block face scanning electron microscopy has permitted researchers to reconstruct cells and neurons by manually identifying and coloring objects. This technique was instrumental in work such as uncovering the anatomical basis for direction selectivity of vision [1]. Unfortunately, reconstruction involves an expenditure of time which can be expensive or prohibitive. We have developed the Computer Assisted Segmentation Tool (CAST), which produces results that appear similar to manual segmentation with reduced personnel time requirements. Results are shown for serial block face electron micrograph (SBEM) images of Mus musculus retinal axons; however, CAST is capable of operation on other image types. CAST is available under an open source license in a modified version of the TrakEM2 plugin for the popular Fiji image analysis suite. Usage and installation instructions can be found at http://isoptera.lcsc.edu/segmentation_tool/.

Keywords

Machine learning Image segmentation Neural network Fast marching algorithm Fiji Track EM2 Trainable Weka Segmentation Neuron 

Notes

Acknowledgments

We would like to thank the students of the Fall 2016 CS492 Bioinformatics class at Lewis-Clark State College for providing the manual outlines referenced in this study. This research was supported by the INBRE program, NIH Grant No. P20 GM103408 (National Institute of General Medical Sciences).

References

  1. 1.
    Briggman, K., Denk, W.: Towards neural circuit reconstruction with volume electron microscopy techniques. Curr. Opin. Neurobiol. 16, 562–570 (2006)CrossRefGoogle Scholar
  2. 2.
    Cardona, A., Saalfeld, S., Schindelin, J., Arganda-Carreras, I., Preibisch, S., Longair, M., Tomancak, P., Hartenstein, V., Douglas, R.: TrakEM2 software for neural circuit reconstruction. PLoS One 7, e38011 (2012)CrossRefGoogle Scholar
  3. 3.
    Platt, J.: U.S. Patent No. 6,380,929. U.S. Patent and Trademark Office, Washington, DC (2002)Google Scholar
  4. 4.
    Lee, K., Zlateski, A., Vishwanathan, A., Seung, H.: Recursive training of 2D-3D convolutional networks for neuronal boundary detection. arxiv preprint arXiv:1508.04843 (2015)
  5. 5.
    Jurrus, E., Watanabe, S., Giuly, R., Paiva, A., Ellisman, M., Jorgensen, E., Tasdizen, T.: Semi-automated neuron boundary detection and nonbranching process segmentation in electron microscopy images. Neuroinformatics 11, 5–29 (2012)CrossRefGoogle Scholar
  6. 6.
    Ciresan, D., Giusti, A., Gambardella, L.M., Schmidhuber, J.: Deep neural networks segment neuronal membranes in electron microscopy images. In: Advances in Neural Information Processing Systems, pp. 2843–2851 (2012)Google Scholar
  7. 7.
    Tschopp, F.: Efficient convolutional neural networks for pixelwise classification on heterogeneous hardware systems. arxiv preprint arXiv:1509.03371 (2015)
  8. 8.
    Tajoddin, B.: Semi-automatic segmentation for serial section electron microscopy images (2012)Google Scholar
  9. 9.
    Chalfoun, J., Majurski, M., Dima, A., Stuelten, C., Peskin, A., Brady, M.: FogBank: a single cell segmentation across multiple cell lines and image modalities. BMC Bioinform. 15 (2014)Google Scholar
  10. 10.
    Olbris, D., Winston, P., Chklovskii, D.: Raveler—a software for editing large segmented electron microscopy datasetsGoogle Scholar
  11. 11.
    Sommer, C., Straehle, C., Koethe, U., Hamprecht, F.: Ilastik: interactive learning and segmentation toolkit. In: 2011 IEEE International Symposium Biomedical Imaging: From Nano to Macro, pp. 230–233 (2011)Google Scholar
  12. 12.
    Knowles-Barley, S., Kaynig, V., Jones, T., Wilson, A., Morgan, J., Lee, D., Pfister, H.: RhoanaNet pipeline: dense automatic neural annotation. arxiv preprint arXiv:1611.06973 (2016)
  13. 13.
    Kornfeld, J., Svara, F., Nguyen, M.-T., Pfeiler, N., Pronkin, M., Shatz, O., Spaar, S., Alex, S., Valerio, J.: knossos-project/knossos. https://github.com/knossos-project/knossos
  14. 14.
    Li, S., Mitchell, J., Briggs, D., Young, J., Long, S., Fuerst, P.: Morphological diversity of the rod spherule: a study of serially reconstructed electron micrographs. PLoS One 11, e0150024 (2016)CrossRefGoogle Scholar
  15. 15.
    Denk, W., Horstmann, H.: Serial block-face scanning electron microscopy to reconstruct three-dimensional tissue nanostructure. PLoS Biol. 2, e329 (2004)CrossRefGoogle Scholar
  16. 16.
    Schindelin, J., Arganda-Carreras, I., Frise, E., Kaynig, V., Longair, M., Pietzsch, T., Preibisch, S., Rueden, C., Saalfeld, S., Schmid, B., Tinevez, J., White, D., Hartenstein, V., Eliceiri, K., Tomancak, P., Cardona, A.: Fiji: an open-source platform for biological-image analysis. Nat. Methods 9, 676–682 (2012)CrossRefGoogle Scholar
  17. 17.
    Ruck, D., Rogers, S., Kabrinsky, M.: Feature selection using a multilayer perceptron. J. Neural Netw. Comput. 2, 40–48 (1990)Google Scholar
  18. 18.
    Arganda-Carreras, I., Kaynig, V., Schindelin, J., Cardona, A., Seung, H.: Trainable weka segmentation: a machine learning tool for microscopy image segmentation (2014)Google Scholar
  19. 19.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.: The WEKA data mining software. ACM SIGKDD Explor. Newsl. 11, 10 (2009)CrossRefGoogle Scholar
  20. 20.
    Arganda-Carreras, I., Cardona, A., Kaynig, V., Rueden, C., Schindelin, J.: Trainable Weka Segmentation – ImageJ (2016). http://imagej.net/Trainable_Weka_Segmentation
  21. 21.
    Long, S., Holder, L.: Graph-based shape analysis for MRI classification. Int. J. Knowl. Discov. Bioinform. 2, 19–33 (2011)CrossRefGoogle Scholar
  22. 22.
    Cardinal, M., Meunier, J., Soulez, G., Maurice, R., Therasse, E., Cloutier, G.: Intravascular ultrasound image segmentation: a three-dimensional fast-marching method based on gray level distributions. IEEE Trans. Med. Imaging 25, 590–601 (2006)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Augustus N. Tropea
    • 1
    Email author
  • Janey L. Valerio
    • 1
  • Michael J. Camerino
    • 2
  • Josh Hix
    • 2
  • Emmalee Pecor
    • 2
  • Peter G. Fuerst
    • 3
  • S. Seth Long
    • 1
  1. 1.Department of Natural Sciences and MathematicsLewis-Clark State CollegeLewistonUSA
  2. 2.North Idaho CollegeCoeur d’AleneUSA
  3. 3.Department of Biological SciencesUniversity of IdahoMoscowUSA

Personalised recommendations