Hostname: page-component-586b7cd67f-rdxmf Total loading time: 0 Render date: 2024-11-22T18:43:17.404Z Has data issue: false hasContentIssue false
  • English
  • Français

The Use of Neural Networks and Texture Analysis for Rapid Objective Selection of Regions of Interest in Cytoskeletal Images

Published online by Cambridge University Press:  12 January 2012

Amanda D. Felder Derkacs ,
Samuel R. Ward  and
Richard L. Lieber
Amanda D. Felder Derkacs
Affiliation:
Department of Bioengineering, University of California-San Diego, 9500 Gilman Drive, La Jolla, CA 92093-0863, USA
Samuel R. Ward
Affiliation:
Departments of Radiology, Orthopaedic Surgery, and Bioengineering, University of California-San Diego, 9500 Gilman Drive, La Jolla, CA 92093-0610, USA
Richard L. Lieber*
Affiliation:
Departments of Orthopaedic Surgery and Bioengineering, V.A. Medical Center, University of California-San Diego, 9500 Gilman Drive, La Jolla, CA 92093-0863, USA
*
Corresponding author. E-mail: [email protected]
Get access

Abstract

Understanding cytoskeletal dynamics in living tissue is prerequisite to understanding mechanisms of injury, mechanotransduction, and mechanical signaling. Real-time visualization is now possible using transfection with plasmids that encode fluorescent cytoskeletal proteins. Using this approach with the muscle-specific intermediate filament protein desmin, we found that a green fluorescent protein–desmin chimeric protein was unevenly distributed throughout the muscle fiber, resulting in some image areas that were saturated as well as others that lacked any signal. Our goal was to analyze the muscle fiber cytoskeletal network quantitatively in an unbiased fashion. To objectively select areas of the muscle fiber that are suitable for analysis, we devised a method that provides objective classification of regions of images of striated cytoskeletal structures into “usable” and “unusable” categories. This method consists of a combination of spatial analysis of the image using Fourier methods along with a boosted neural network that “decides” on the quality of the image based on previous training. We trained the neural network using the expert opinion of three scientists familiar with these types of images. We found that this method was over 300 times faster than manual classification and that it permitted objective and accurate classification of image regions.

Keywords

image analysisclassificationskeletal muscleconfocal microscopy
Type
Feature Article
Information
Microscopy and Microanalysis , Volume 18 , Issue 1 , February 2012 , pp. 115 - 122
Copyright
Copyright © Microscopy Society of America 2012

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

Barash, I.A., Mathew, L., Ryan, A.F., Chen, J. & Lieber, R.L. (2004). Rapid muscle-specific gene expression changes after a single bout of eccentric contractions in the mouse. Am J Physiol 286(2), C355–C364.CrossRefGoogle ScholarPubMed
Bergen, J., Anandan, P., Hanna, K. & Hingorani, R. (1992). Hierarchical model-based motion estimation. Proceedings of the Second European Conference on Computer Vision, pp. 237–252. Berlin: Springer-Verlag.Google Scholar
Desoky, A.H. & Hall, S.A. (1990). Entropy measures for texture analysis based on Hadamard transform. Proc IEEE Southeastcon, vol. 462, pp. 467–470.CrossRefGoogle Scholar
Eilbert, J.L., Gallistel, C.R. & McEachron, D.L. (1990). The variation in user drawn outlines on digital images: Effects on quantitative autoradiography. Comput Med Imaging Graph 14(5), 331–339.CrossRefGoogle ScholarPubMed
Freund, Y. & Schapire, R.E. (1996). Game theory, on-line prediction and boosting. Proceedings of the Ninth Annual Conference on Computational Learning Theory, pp. 325–332. Italy: Desenzano del Garda.CrossRefGoogle Scholar
Gannier, F., Bernengo, J.C., Jacquemond, V. & Garnier, D. (1993). Measurements of sarcomere dynamics simultaneously with auxotonic force in isolated cardiac cells. IEEE Trans Biomed Eng 40(12), 1226–1232.CrossRefGoogle ScholarPubMed
Gautel, M. (2011). The sarcomeric cytoskeleton: Who picks up the strain? Curr Opin Cell Biol 23(1), 39–46.CrossRefGoogle ScholarPubMed
Haralick, R.M. (1979). Statistical and structural appraoches to texture. Proceedings of the IEEE 67(5), 786–804.CrossRefGoogle Scholar
Helmes, M., Trombitas, K., Centner, T., Kellermayer, M., Labeit, S., Linke, W.A. & Granzier, H. (1999). Mechanically driven contour-length adjustment in rat cardiac titin's unique N2B sequence: titin is an adjustable spring. Circ Res 84(11), 1339–1352.CrossRefGoogle ScholarPubMed
Imanaka-Yoshida, K., Sanger, J.M. & Sanger, J.W. (1993). Contractile protein dynamics of myofibrils in paired adult rat cardiomyocytes. Cell Motil Cytoskeleton 26(4), 301–312.CrossRefGoogle ScholarPubMed
Infantolino, B.W., Ellis, M.J. & Challis, J.H. (2010). Individual sarcomere lengths in whole muscle fibers and optimal fiber length computation. Anat Record 293(11), 1913–1919.CrossRefGoogle ScholarPubMed
Kayser, K., Gortler, J., Bogovac, M., Bogovac, A., Goldmann, T., Vollmer, E. & Kayser, G. (2009). AI (artificial intelligence) in histopathology—From image analysis to automated diagnosis. Folia Histochem Cytobiol 47(3), 355–361.Google ScholarPubMed
Kim, Y.-J., Brox, T., Feiden, W. & Weickert, J. (2007). Fully automated segmentation and morphometrical analysis of muscle fiber images. Cytom Part A 71(1), 8–15.CrossRefGoogle ScholarPubMed
Klemenčič, A., Kovačič, S. & Pernuš, F. (1998). Automated segmentation of muscle fiber images using active contour models. Cytometry 32(4), 317–326.3.0.CO;2-E>CrossRefGoogle ScholarPubMed
Kueh, H.Y., Brieher, W.M. & Mitchison, T.J. (2010). Quantitative analysis of actin turnover in listeria comet tails: Evidence for catastrophic filament turnover. Biophys J 99(7), 2153–2162.CrossRefGoogle ScholarPubMed
Milner, D.J., Weitzer, G., Tran, D., Bradley, A. & Capetanaki, Y. (1996). Disruption of muscle architecture and myocardial degeneration in mice lacking desmin. J Cell Biol 134(5), 1255–1270.CrossRefGoogle ScholarPubMed
Ockleford, C.D., Cairns, H., Rowe, A.J., Byrne, S., Scott, J.J. & Willingale, R. (2002). The distribution of caveolin-3 immunofluorescence in skeletal muscle fibre membrane defined by dual channel confocal laser scanning microscopy, fast Fourier transform and image modelling. J Microsc 206(Pt 2), 93–105.CrossRefGoogle ScholarPubMed
Palmisano, M.G., Bremner, S.N., Shah, S., Ryan, A.F. & Lieber, R.L. (2007). Rescue of mechanical function in desmin knockout muscles by plasmid transfection. Proceedings of the Orthopaedic Research Society Annual Conference. San Diego, CA: ORS.Google Scholar
Portney, L.G. & Watkins, M.P. (1993). Foundations of Clinical Research: Applications to Practice. Upper Saddle River, NJ: Prentice Hall.Google Scholar
Shah, S.B., Davis, J., Weisleder, N., Kostavassili, I., McCulloch, A.D., Ralston, E., Capetanaki, Y. & Lieber, R.L. (2004). Structural and functional roles of desmin in mouse skeletal muscle during passive deformation. Biophys J 86(5), 2993–3008.CrossRefGoogle ScholarPubMed
Shah, S.B. & Lieber, R.L. (2003). Simultaneous imaging and functional assessment of cytoskeletal protein connections in passively loaded single muscle cells. J Histochem Cytochem 51(1), 19–29.CrossRefGoogle ScholarPubMed
Tzekis, P., Papastergiou, A., Hatzigaidas, A. & Cheva, A. (2007). A sophisticated edge detection method for muscle biopsy image analysis. Proceedings of the 7th WSEAS International Conference on Signal, Speech and Image Processing. Beijing, China: World Scientific and Engineering Academy and Society.Google Scholar
Unser, M. (1986). Local linear transforms for texture measurements. Sign Process 11(1), 61–79.CrossRefGoogle Scholar
Unser, M. (1995). Texture classification and segmentation using wavelet frames. IEEE Trans Image Process 4(11), 1549–1560.CrossRefGoogle ScholarPubMed
Vitadello, M., Schiaffino, M.V., Picard, A., Scarpa, M. & Schiaffino, S. (1994). Gene transfer in regenerating muscle. Hum Gene Ther 5(1), 11–18.CrossRefGoogle ScholarPubMed
Weibel, E.R. (1980). Practical methods for biological morphometry. In Stereological Methods. New York: Academic Press.Google Scholar
Weiwad, W.K., Linke, W.A. & Wussling, M.H. (2000). Sarcomere length-tension relationship of rat cardiac myocytes at lengths greater than optimum. J Mol Cell Cardiol 32(2), 247–259.Google ScholarPubMed
Zou, M. & Wang, D. (2001). Texture identification and image segmentation via Fourier transform. In Image Extraction, Segmentation, and Recognition, pp. 34–39. Wuhan, China: SPIE.CrossRefGoogle Scholar

Felder Derkacs Supplementary Material

Felder Derkacs Supplementary Material

Download Felder Derkacs Supplementary Material(Video)
Video 9.2 MB