Quantitative phase imaging has gained popularity in bioimaging because it can avoid the need for cell staining, which, in some cases, is difficult or impossible. However, as a result, quantitative phase imaging does not provide the labelling of various specific intracellular structures. Here we show a novel computational segmentation method based on statistical inference that makes it possible for quantitative phase imaging techniques to identify the cell nucleus. We demonstrate the approach with refractive index tomograms of stain-free cells reconstructed using tomographic phase microscopy in the flow cytometry mode. In particular, by means of numerical simulations and two cancer cell lines, we demonstrate that the nucleus can be accurately distinguished within the stain-free tomograms. We show that our experimental results are consistent with confocal fluorescence microscopy data and microfluidic cyto-fluorimeter outputs. This is a remarkable step towards directly extracting specific three-dimensional intracellular structures from the phase contrast data in a typical flow cytometry configuration.

Tomographic flow cytometry by digital holography is an emerging imaging modality capable of collecting multiple views of moving and rotating cells with the aim of recovering their refractive index distribution in 3D. Although this modality allows us to access high-resolution imaging with high-throughput, the huge amount of time-lapse holographic images to be processed (hundreds of digital holograms per cell) constitutes the actual bottleneck. This prevents the system from being suitable for lab-on-a-chip platforms in real-world applications, where fast analysis of measured data is mandatory. Here we demonstrate a significant speeding-up reconstruction of phase-contrast tomograms by introducing in the processing pipeline a multi-scale fully-convolutional context aggregation network. Although it was originally developed in the context of semantic image analysis, we demonstrate for the first time that it can be successfully adapted to a holographic lab-on-chip platform for achieving 3D tomograms through a faster computational process. We trained the network with input–output image pairs to reproduce the end-to-end holographic reconstruction process, i.e. recovering quantitative phase maps (QPMs) of single cells from their digital holograms. Then, the sequence of QPMs of the same rotating cell is used to perform the tomographic reconstruction. The proposed approach significantly reduces the computational time for retrieving tomograms, thus making them available in a few seconds instead of tens of minutes, while essentially preserving the high-content information of tomographic data. Moreover, we have accomplished a compact deep convolutional neural network parameterization that can fit into on-chip SRAM and a small memory footprint, thus demonstrating its possible exploitation to provide onboard computations for lab-on-chip devices with low processing hardware resources.

Fourier ptychographic microscopy probes label-free samples from multiple angles and achieves super resolution phase-contrast imaging according to a synthetic aperture principle. Thus, it is particularly suitable for high-resolution imaging of tissue slides over a wide field of view. Recently, in order to make the optical setup robust against misalignments-induced artefacts, numerical multi-look has been added to the conventional phase retrieval process, thus allowing the elimination of related phase errors but at the cost of a long computational time. Here we train a generative adversarial network to emulate the process of complex amplitude estimation. Once trained, the network can accurately reconstruct in real-time Fourier ptychographic images acquired using a severely misaligned setup. We benchmarked the network by reconstructing images of animal neural tissue slides. Above all, we show that important morphometric information, relevant for diagnosis on neural tissues, are retrieved using the network output. These are in very good agreement with the parameters calculated from the ground-truth, thus speeding up significantly the quantitative phase-contrast analysis of tissue samples.

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.

Despite remarkable progresses in quantitative phase imaging (QPI) microscopes, their wide acceptance is limited due to the lack of specificity compared with the well-established fluorescence microscopy. In fact, the absence of fluorescent tag prevents to identify subcellular structures in single cells, making challenging the interpretation of label-free 2D and 3D phase-contrast data. Great effort has been made by many groups worldwide to address and overcome such limitation. Different computational methods have been proposed and many more are currently under investigation to achieve label-free microscopic imaging at single-cell level to recognize and quantify different subcellular compartments. This route promises to bridge the gap between QPI and FM for real-world applications.