Search

We present a novel deep learning-based quantification pipeline for the analysis of cell culture images acquired by lens-free microscopy. The image reconstruction part of the pipeline features a convolutional neural network performing phase unwrapping and accelerating the inverse problem optimization. It allows phase retrieval at the 4K level (3,840 × 2,748 pixels) in 3 s. The analysis part of the pipeline features a suite of convolutional neural networks estimating different cell metrics from the reconstructed image, that is, cell surface area, cell dry mass, cell length, and cell thickness. The networks have been trained to predict quantitative representation of the cell measurements that can be next translated into measurement lists with a local maxima algorithm. In this article, we discuss the performance and limitations of this novel deep learning-based quantification pipeline in comparison with a standard image processing solution. The main advantage brought by this method is the fast processing time, that is, the analysis rate of ∼25.000 cells measurements per second. Although our proof of principle has been established with lens-free microscopy, the approach of using quantitative cell representation in a deep learning framework can be similarly applied to other microscopy techniques.

Nanostructured optical components, such as nanolenses, direct light at subwavelength scales to enable, among others, high-resolution lithography, miniaturization of photonic circuits, and nanoscopic imaging of biostructures. A major challenge in fabricating nanolenses is the appropriate positioning of the lens with respect to the sample while simultaneously ensuring it adopts the optimal size and shape for the intended use. One application of particular interest is the enhancement of contrast and signal-to-noise ratio in the imaging of nanoscale objects, especially over wide fields-of-view (FOVs), which typically come with limited resolution and sensitivity for imaging nano-objects. Here we present a self-assembly method for fabricating time- and temperature-tunable nanolenses based on the condensation of a polymeric liquid around a nanoparticle, which we apply to the high-throughput on-chip detection of spheroids smaller than 40 nm, rod-shaped particles with diameter smaller than 20 nm, and biofunctionalized nanoparticles, all across an ultralarge FOV of >20 mm(2). Previous nanoparticle imaging efforts across similar FOVs have detected spheroids no smaller than 100 nm, and therefore our results demonstrate the detection of particles >15-fold smaller in volume, which in free space have >240 times weaker Rayleigh scattering compared to the particle sizes detected in earlier wide-field imaging work. This entire platform, with its tunable nanolens condensation and wide-field imaging functions, is also miniaturized into a cost-effective and portable device, which might be especially important for field use, mobile sensing, and diagnostics applications, including, for example, the measurement of viral load in bodily fluids.

In vitro experiments with cultured cells are essential for studying their growth and migration pattern and thus, for gaining a better understanding of cancer progression and its treatment. Recent progress in lens-free microscopy (LFM) has rendered it an inexpensive tool for label-free, continuous live cell imaging, yet there is only little work on analysing such time-lapse image sequences. We propose (1) a cell detector for LFM images based on fully convolutional networks and residual learning, and (2) a probabilistic model based on moral lineage tracing that explicitly handles multiple detections and temporal successor hypotheses by clustering and tracking simultaneously. (3) We benchmark our method in terms of detection and tracking scores on a dataset of three annotated sequences of several hours of LFM, where we demonstrate our method to produce high quality lineages. (4) We evaluate its performance on a somewhat more challenging problem: estimating cell lineages from the LFM sequence as would be possible from a corresponding fluorescence microscopy sequence. We present experiments on 16 LFM sequences for which we acquired fluorescence microscopy in parallel and generated annotations from them. Finally, (5) we showcase our methods effectiveness for quantifying cell dynamics in an experiment with skin cancer cells. [ABSTRACT FROM AUTHOR]

Giardiasis leads to severe diarrhea, and its impacts are especially concerning in low-income sites that lack water and sanitation infrastructure. Monitoring water quality considering the infective form of Giardia is therefore an action that strongly aligns with public health. The standard protocol for cyst quantification in water involves immunofluorescence assays (IFA), which depend on fluorescent probes coupled to antibodies, making it an observer-dependent, and a relatively expensive method. Lens-free holographic microscopy (LHM) offers a possible alternative for imaging, as it relies on portable, lightweight, and low-cost equipment. It is based on phase and amplitude images of holograms recorded with partially coherent lighting. This study, therefore, aimed to test LHM for the detection and counting of Giardia cysts. Purified suspensions of G. duodenalis cysts, with known concentration, were quantified by IFA and LHM. Holograms were acquired by transmission, using three different wavelengths, and were then submitted to automated analysis, using an algorithm developed in Python. Slide preparation and cyst counting by IFA proved to be more laborious compared to LHM. Agglomerations of cysts impaired both methods. LHM quantification showed significant similarity with the reference number of cysts in suspension, which was not obtained by standard immunofluorescence. LHM proved to be an effective technique for detecting and counting Giardia cysts in purified samples and with high concentrations, showing potential for future application in water quality assessment targeting pathogens, but limitations include low sensitivity and a demand for future work considering matrix effect on real environmental samples. [Display omitted] • Lens-free holographic microscopy (LHM) was used for detection of Giardia cysts. • LHM was effective for counting purified cysts' suspensions. • There is potential for future application in monitoring protozoa in water. • Limitations mostly refer to future work with environmental samples. [ABSTRACT FROM AUTHOR]

They present results for lens-free microscopy for the imaging of dense cell culture. With this aim, they use a multiwavelength LED illumination with well separated wavelengths, together with the implementation of an appropriate holographic reconstruction algorithm. This allows for a fast and efficient reconstruction of the phase image of densely packed cells (up to 700 cells/mm2) over a large field of view of 29.4 mm2. Combined with the compactness of the system which fits altogether inside an incubator, lens-free microscopy becomes a unique tool to monitor cell cultures over several days. The high contrast phase shift images provide robust cell segmentation and tracking, and enable high throughput monitoring of individual cell dimensions, dry mass, and motility. They tested the multiwavelength lens-free video-microscope over a broad range of cell lines, including mesenchymal, endothelial, and epithelial cells. © 2017 International Society for Advancement of Cytometry [ABSTRACT FROM AUTHOR]

Summary Tuberculosis (TB) control efforts are hampered by a mismatch in diagnostic technology. Lack of adequate early diagnostics and Multi-drug resistant (MDR) detection is a critical problem in control efforts. Alternate and novel diagnostic approaches are required, especially in low-resources settings where they are needed most. The Microscopic Observation Drug Susceptibility (MODS) assay is a cost-effective, highly sensitive, and specific method based on the detection of characteristic cording growth patterns of Mycobacterium tuberculosis (MTB), in microscopic examination of a liquid culture under an inverted microscope. By adding antimicrobials to the wells, MODS also determines antimicrobial susceptibility in both MDR and Extreme Drug Resistant (XDR) tuberculosis. The interpretation of a MODS culture performed in a 24 well plate, requires an extensive inspection over the entire surface to detect TB cords. This process requires significant time and effort from a trained microscopist. We evaluated a lens-free imager system, able to render microscopic images of live specimens, for the proof of principle to be used for MODS culture interpretation. The lens-free imager system is able to digitalize a 24-mm 2 surface with approximately 40X magnification in a single capture. The evaluation of the lens-free imager found that it produced microscopic images that were adequate for MODS interpretation by a human expert. Compared to the average time that takes a microscopist to completely examine a MODS culture sample, the lens free imager notably reduced the time of inspection. Therefore, lens-free imager variants may constitute promising systems to aid in the diagnostics of tuberculosis, by simplifying and reducing the time of inspection and permitting automatization of MODS interpretation. [ABSTRACT FROM AUTHOR]

As the primary imaging tool to assist the examination of pathological samples, the conventional light microscope suffers from limited throughput, relatively high cost, bulky size, lack of portability, and requirement for focus adjustment. All of these drawbacks partially limit the use of light microscopy tools in resource-limited settings. Lens-free on-chip microscopy can help to address these drawbacks and achieve high-throughput pathology slide imaging without using lenses or objectives. Here, we review the performance of this lens-free imaging platform by showing examples of its performance with various samples including normal and sickle-cell disease blood smears and human carcinoma of the breast. This lens-free computational microscopy platform is a promising tool that can serve high-throughput pathology needs especially in resource-poor settings. [ABSTRACT FROM AUTHOR]