The phylogeny of the family Selenastraceae was investigated by light microscopy, 18S rDNA, rbcL and ITS-2 analyses. Various morphological features traditionally used for species and genera identification were investigated. All selenastracean s...
6 October 2016 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
We describe a specialized methodology for segmenting 2D microscopy digital images of freshwater green microalgae. The goal is to obtain representative algae shapes to extract morphological features to be employed in a posterior step of taxonomical classification of the species. The proposed methodology relies on the seeded region growing principle and on a fine-tuned filtering preprocessing stage to smooth the input image. A contrast enhancement process then takes place to highlight algae regions on a binary pre-segmentation image. This binary image is also employed to determine where to place the seed points and to estimate the statistical probability distributions that characterize the target regions, i.e., the algae areas and the background, respectively. These preliminary stages produce the required information to set the homogeneity criterion for region growing. We evaluate the proposed methodology by comparing its resulting segmentations with a set of corresponding ground-truth segmentations (provided by an expert biologist) and also with segmentations obtained with existing strategies. The experimental results show that our solution achieves highly accurate segmentation rates with greater efficiency, as compared with the performance of standard segmentation approaches and with an alternative previous solution, based on level-sets, also specialized to handle this particular problem.
Organisms adapt to the environment by establishing themselves in suitable locations. Adaptation to the harsh Antarctic environment is no different. In this work the communities of epilithic diatoms in ice-free areas of water systems of five Antarctic islands are studied. The samples were oxidized, and permanent sheets were later prepared for analysis of the material. They were examined using an optical microscope and mounted on stubs for identification of the taxon in an electron microscope. Fifty-nine species distributed in 28 genera were collected. Only four species were observed in all study areas. Deception Island had unique species in comparison with those on other islands. Knowing the diatom community is a first step in understanding the systems that they inhabit. The polar environment is challenging due to the difficulty of sampling and low diversity and abundance.
We present a method for segmenting 2D microscopy images of freshwater green microalgae. Our approach is based on a specialized level set method, leading to efficient and highly accurate algae segmentation. The level set formulation of our problem allows us to generate an algae's boundary curve as the result of an evolving level curve, based on computed background and algae regions in a given image. By characterizing the distributions of image intensity values in local regions, we are able to automatically classify image regions into background and algae regions. We present results obtained with our method. These results are very promising as they document that we can achieve highly accurate algae segmentations when comparing ours against manually segmented images (segmented by an expert biologist) and with results derived by other approaches covered in the literature.