Institute of Applied Sciences and Intelligent Systems (ISASI), National Research Council (CNR) of Italy, Via Campi Flegrei 34, 80078 Pozzuoli, NA, Italy
Dr. Francesco Merola
Institute of Applied Sciences and Intelligent Systems (ISASI), National Research Council (CNR) of Italy, Via Campi Flegrei 34, 80078 Pozzuoli, NA, Italy
The label-free single cell analysis by machine and Deep Learning, in combination with digital holography in transmission microscope configuration, is becoming a powerful framework exploited for phenotyping biological samples. Usually, quantitative phase images of cells are retrieved from the reconstructed complex diffraction patterns and used as inputs of a deep neural network. However, the phase retrieval process can be very time consuming and prone to errors. Here we address the classification of cells by using learning strategies with images coming directly from the raw recorded digital holograms, i.e. without any data processing or refocusing involved. Indeed, in the raw digital hologram the entire complex amplitude information of the sample is intrinsically embedded in the form of modulated fringes. We develop a training strategy, based on deep and feature based machine learning models, in order extract such information by skipping the classical reconstruction process for classifying different neuroblastoma cells. We provided an experimental validation by using the proposed strategy to classify two neuroblastoma cell lines.
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.
Full-tomography in phase contrast modality of both sick and healthy cells flowing in microchannels is demonstrated. The proposed method can open the way for real-world biomedical diagnosis by quantitative coherent imaging. Results on Red Blood Cells (RBC), diatoms and tumor cells are reported.
Disruption of daily patterns of activity, physiology, or social interaction is associated with stress and reduced fitness across species. In social insects such as honey bees (Apis mellifera), circadian organisation extends to the colony level, where rhythms emerge from interactions among individual clocks, hive conditions, and environmental cues. Precision apiculture offers a mature sensor toolkit for measuring colony-level variables, and several data streams carry early-warning information about colony condition. Almost all alarms, however, are triggered against set points rather than against the daily rhythm of the signal. We review each sensor technology to establish whether its data have been, or could be, analysed with a chronobiological lens, describing the measurement principle, the achievable temporal resolution and record continuity, the rhythmic signature expected on biological grounds, and any evidence that such a signature has been reported. We then use a synthetic dataset to illustrate the workflow: in this simulated example, rhythm metrics flagged a gradually developing decline approximately three weeks before a conventional threshold alert on the same data. This lead time is a property of the simulation and awaits validation on real colonies. Wherever continuous behavioural monitoring is deployed, rhythm-based metrics may offer a route to earlier, more interpretable detection of change than set point comparisons.