Learning Diatoms Classification from a Dry Test Slide by Holographic Microscopy

Diatoms are among the dominant phytoplankters in marine and freshwater habitats, and important biomarkers of water quality, making their identification and classification one of the current challenges for environmental monitoring. To date, taxonomy of the species populating a water column is still conducted by marine biologists on the basis of their own experience. On the other hand, deep learning is recognized as the elective technique for solving image classification problems. However, a large amount of training data is usually needed, thus requiring the synthetic enlargement of the dataset through data augmentation. In the case of microalgae, the large variety of species that populate the marine environments makes it arduous to perform an exhaustive training that considers all the possible classes. However, commercial test slides containing one diatom element per class fixed in between two glasses are available on the market. These are usually prepared by expert diatomists for taxonomy purposes, thus constituting libraries of the populations that can be found in oceans. Here we show that such test slides are very useful for training accurate deep Convolutional Neural Networks (CNNs). We demonstrate the successful classification of diatoms based on a proper CNNs ensemble and a fully augmented dataset, i.e., creation starting from one single image per class available from a commercial glass slide containing 50 fixed species in a dry setting. This approach avoids the time-consuming steps of water sampling and labeling by skilled marine biologists. To accomplish this goal, we exploit the holographic imaging modality, which permits the accessing of a quantitative phase-contrast maps and a posteriori flexible refocusing due to its intrinsic 3D imaging capability. The network model is then validated by using holographic recordings of live diatoms imaged in water samples i.e., in their natural wet environmental condition.

Live diatoms facing Ag nanoparticles: surface enhanced Raman scattering of bulk cylindrotheca closterium pennate diatoms and of the single cells

Live diatoms exposed to AgNPs revealed SERS mechanism dependent on the nanoparticles type while the SERS output allowed detection of extracellular substances.

The effects of diazepam on mitosis and the microtubule cytoskeleton. I. Observations on the diatoms Hantzschia amphioxys and Surirella robusta

The effects of diazepam (DZP) on mitosis and the microtubule (MT) cytoskeleton in the live diatoms Hantzschia amphioxys and Surirella robusta were followed using time-lapse video microscopy. Similarly treated cells were fixed and later examined for immunoflouresence staining of MTs or for transmission electron microscopy. DZP treatment (250 microM) had no effect on interphase cells but affected mitosis, resulting in the majority of prometaphase and metaphase chromosomes releasing from one or both spindle poles and collecting irregularly along the central spindle. Chromosomes remaining attached to one pole continued to display slight prometaphase oscillations; however, this activity was never observed in metaphase spindles. Following removal of DZP, some chromosomes still bipolarly attached, immediately released elastically from one pole. Within the first 2 minutes of recovery, all chromosomes recommenced spindle attachment, exhibiting normal prometaphase oscillations and proceeded through mitosis. DZP treatment during anaphase had no detectable effect on chromosome motion or cell cleavage. These results suggest that DZP acts as an anti-MT agent, selectively affecting polar MTs at prophase, prometaphase and metaphase, and thereby weakening kinetochore connection to the poles. From these and other results (unpublished), its mode of action is different to that of most anti-MT agents.

Lipids as indicators of the origin of organic matter in fine marine particulate matter

The lipid compositions of fine particulate matter (<35 �m diameter) have been analysed from two temperate sites (Western Port Bay, WPB, and Corner Inlet, CI, Victoria) and two tropical sites (Bowling Green Bay, BGB, and Lizard Island Lagoon, LIL, North Queensland) in the Australian coastal zone. Identification of lipid biomarker molecules (especially fatty acids, fatty alcohols and sterols) has, in conjunction with microscopy, enabled identification and, in some instances, quantification of a range of biological inputs. Estimated contributions of biomass to total particulate mass in the temperate samples were: seagrass detritus (~10-15%) > bacteria (~34%) > live diatoms (≤ 1%). Similar estimations for the tropical samples were: BGB, bacteria (- 1%) > live diatoms (< 1%); and LIL, bacteria (~20-30%) > copepod detritus (≥ 1%) > live diatoms (< 1 %). Biomarkers also indicated the presence of coral mucus and a distinctive bacterial chemotype, possessing branched chain alcohols, in the LIL sample.