Rapid Determination of Bacterial Abundance, Biovolume, Morphology, and Growth by Neural Network-Based Image Analysis

ABSTRACT Annual bacterial plankton dynamics at several depths and locations in the Baltic Sea were studied by image analysis. Individual bacteria were classified by using an artificial neural network which also effectively identified nonbacterial objects. Cell counts and frequencies of dividing cells were determined, and the data obtained agreed well with visual observations and previously published values. Cell volumes were measured accurately by comparison with bead standards. The survey included 690 images from a total of 138 samples. Each image contained approximately 200 bacteria. The images were analyzed automatically at a rate of 100 images per h. Bacterial abundance exhibited coherent patterns with time and depth, and there were distinct subsurface peaks in the summer months. Four distinct morphological classes were resolved by the image analyzer, and the dynamics of each could be visualized. The bacterial growth rates estimated from frequencies of dividing cells were different from the bacterial growth rates estimated by the thymidine incorporation method. With minor modifications, the image analysis technique described here can be used to analyze other planktonic classes.

[1]  Åke Hagström,et al.  Measurement of bacterial size via image analysis of epifluorescence preparations: description of an inexpensive system and solutions to some of the most common problems , 1997 .

[2]  Bart Kosko,et al.  Neural networks for signal processing , 1992 .

[3]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[4]  David C. Smith,et al.  A simple, economical method for measuring bacterial protein synthesis rates in seawater using 3H-leucine , 1992 .

[5]  M. Sieracki,et al.  Distributions and fluorochrome-staining properties of submicrometer particles and bacteria in the North Atlantic , 1992 .

[6]  P. K. Bjørnsen,et al.  Determination of bacterioplankton biomass, net production and growth efficiency in the Southern Ocean , 1991 .

[7]  J. Hobbie,et al.  Use of nuclepore filters for counting bacteria by fluorescence microscopy , 1977, Applied and environmental microbiology.

[8]  M. Sieracki,et al.  Measurement of marine picoplankton cell size by using a cooled, charge-coupled device camera with image-analyzed fluorescence microscopy , 1992, Applied and environmental microbiology.

[9]  P. Stokseth.  Properties of a Defocused Optical System , 1969 .

[10]  K. Porter,et al.  The use of DAPI for identifying and counting aquatic microflora1 , 1980 .

[11]  M. Sieracki,et al.  Color Image-Analyzed Fluorescence Microscopy: A New Tool For Marine Microbial Ecology , 1990 .

[12]  J. Fuhrman,et al.  Thymidine incorporation as a measure of heterotrophic bacterioplankton production in marine surface waters: Evaluation and field results , 1982 .

[13]  U. Larsson,et al.  Frequency of Dividing Cells, a New Approach to the Determination of Bacterial Growth Rates in Aquatic Environments , 1979, Applied and environmental microbiology.

[14]  U. Larsson,et al.  Diel and seasonal variation in growth rates of pelagic bacteria , 1984 .

[15]  J. Pinhassi,et al.  Dominant marine bacterioplankton species found among colony-forming bacteria , 1997, Applied and environmental microbiology.

[16]  P. Verity,et al.  A new staining technique for dual identification of plankton and detritus in seawater , 1995 .

[17]  C. Woldringh,et al.  Elongation of rod-shaped bacteria. , 1977, Journal of theoretical biology.

[18]  Phil F. Culverhouse,et al.  Automatic categorisation of five species of Cymatocylis (Protozoa, Tintinnida) by artificial neural network , 1994 .

[19]  R. J. Olson,et al.  Use of a neural net computer system for analysis of flow cytometric data of phytoplankton populations , 1989, International 1989 Joint Conference on Neural Networks.

[20]  J. Hobbie,et al.  Heterotrophic activity in the sea , 1984 .

[21]  J. Hollibaugh.  Limitations of the [3H]thymidine method for estimating bacterial productivity due to thymidine metabolism , 1988 .

[22]  U. Larsson,et al.  Size-selective grazing by a microflagellate on pelagic bacteria , 1986 .

[23]  Mar Ecol Ser Prog,et al.  Biological pattern recognition by neural networks , .

[24]  Å. Hagström,et al.  Total counts of marine bacteria include a large fraction of non-nucleoid-containing bacteria (ghosts) , 1995, Applied and environmental microbiology.

[25]  J. Bloem,et al.  Fully automatic determination of soil bacterium numbers, cell volumes, and frequencies of dividing cells by confocal laser scanning microscopy and image analysis , 1995, Applied and environmental microbiology.

[26]  J. Fuhrman,et al.  Bacterioplankton Secondary Production Estimates for Coastal Waters of British Columbia, Antarctica, and California , 1980, Applied and environmental microbiology.

[27]  Rekha Govil,et al.  Neural Networks in Signal Processing , 2000 .

[28]  J. Strickler,et al.  Automatic classification of field-collected dinoflagellates by artificial neural network , 1996 .