Segmenting subcellular structures in living cells from fluorescence microscope images is a ground truth (GT)-deficient problem. The microscopes’ three-dimensional blurring function, finite optical resolution due to light diffraction, finite pixel resolution and the complex morphological manifestations of the structures all contribute to GT-hardness. Unsupervised segmentation approaches are quite inaccurate. Therefore, manual segmentation relying on heuristics and experience remains the preferred approach. However, this process is tedious, given the countless structures present inside a single cell, and generating analytics across a large population of cells or performing advanced artificial intelligence tasks such as tracking are greatly limited. Here we bring modelling and deep learning to a nexus for solving this GT-hard problem, improving both the accuracy and speed of subcellular segmentation. We introduce a simulation-supervision approach empowered by physics-based GT, which presents two advantages. First, the physics-based GT resolves the GT-hardness. Second, computational modelling of all the relevant physical aspects assists the deep learning models in learning to compensate, to a great extent, for the limitations of physics and the instrument. We show extensive results on the segmentation of small vesicles and mitochondria in diverse and independent living- and fixed-cell datasets. We demonstrate the adaptability of the approach across diverse microscopes through transfer learning, and illustrate biologically relevant applications of automated analytics and motion analysis.

The dimensions of mitochondria are close to the diffraction limit of conventional light microscopy techniques, making the complex internal structures of mitochondria unresolvable. In recent years, new fluorescence‐based optical imaging techniques have emerged, which allow for optical imaging below the conventional limit, enabling super‐resolution (SR). Possibly the most promising SR and diffraction‐limited microscopy techniques for live‐cell imaging are structured illumination microscopy (SIM) and deconvolution microscopy (DV), respectively. Both SIM and DV are widefield techniques and therefore provide fast‐imaging speed as compared to scanning based microscopy techniques. We have exploited the capabilities of three‐dimensional (3D) SIM and 3D DV to investigate different sub‐mitochondrial structures in living cells: the outer membrane, the intermembrane space, and the matrix. Using different mitochondrial probes, each of these sub‐structures was first investigated individually and then in combination. We describe the challenges associated with simultaneous labeling and SR imaging and the optimized labeling protocol and imaging conditions to obtain simultaneous three‐color SR imaging of multiple mitochondrial regions in living cells. To investigate both mitochondrial dynamics and structural details in the same cell, the combined usage of DV for long‐term time‐lapse imaging and 3D SIM for detailed, selected time point analysis was a useful strategy.

Labelfree nanoscopy encompasses optical imaging with resolution in the 100 nm range using visible wavelengths. Here, we present a labelfree nanoscopy method that combines coherent imaging techniques with waveguide microscopy to realize a super-condenser featuring maximally inclined coherent darkfield illumination with artificially stretched wave vectors due to large refractive indices of the employed Si₃N₄ waveguide material. We produce the required coherent plane wave illumination for Fourier ptychography over imaging areas 400 μm² in size via adiabatically tapered single-mode waveguides and tackle the overlap constraints of the Fourier ptychography phase retrieval algorithm two-fold: firstly, the directionality of the illumination wave vector is changed sequentially via a multiplexed input structure of the waveguide chip layout and secondly, the wave vector modulus is shortend via step-wise increases of the illumination light wavelength over the visible spectrum. We test the method in simulations and in experiments and provide details on the underlying image formation theory as well as the reconstruction algorithm. While the generated Fourier ptychography reconstructions are found to be prone to image artefacts, an alternative coherent imaging method, rotating coherent scattering microscopy (ROCS), is found to be more robust against artefacts but with less achievable resolution.

Mitochondria play a crucial role in cellular metabolism. This paper presents a novel method to visualize mitochondria in living cells without the use of fluorescent markers. We propose a physics-guided deep learning approach for obtaining virtually labeled micrographs of mitochondria from bright-field images. We integrate a microscope’s point spread function in the learning of an adversarial neural network for improving virtual labeling. We show results (average Pearson correlation 0.86) significantly better than what was achieved by state-of-the-art (0.71) for virtual labeling of mitochondria. We also provide new insights into the virtual labeling problem and suggest additional metrics for quality assessment. The results show that our virtual labeling approach is a powerful way of segmenting and tracking individual mitochondria in bright-field images, results previously achievable only for fluorescently labeled mitochondria.

This three-dimensional structured illumination microscopy (3DSIM) dataset was generated to highlight the suitability of 3DSIM to investigate mitochondria-derived vesicles (MDVs) in H9c2 cardiomyoblasts in living or fixed cells. MDVs act as a mitochondria quality control mechanism. The cells were stably expressing the tandem-tag eGFP-mCherry-OMP25-TM (outer mitochondrial membrane) which can be used as a sensor for acidity. A part of the dataset is showing correlative imaging of lysosomes labeled using LysoTracker in fixed and living cells. The cells were cultivated in either normal or glucose-deprived medium containing galactose. The resulting 3DSIM data were of high quality and can be used to undertake a variety of studies. Interestingly, many dynamic tubules derived from mitochondria are visible in the 3DSIM videos under both glucose and galactose-adapted growth conditions. As the raw 3DSIM data, optical parameters, and reconstructed 3DSIM images are provided, the data is especially suitable for use in the development of SIM reconstruction algorithms, bioimage analysis methods, and for biological studies of mitochondria.

Mitochondria are essential energy‐providing organelles of particular importance in energy‐demanding tissue such as the heart. The production of mitochondria‐derived vesicles (MDVs) is a cellular mechanism by which cells ensure a healthy pool of mitochondria. These vesicles are small and fast‐moving objects not easily captured by imaging. In this work, we have tested the ability of the optical super‐resolution technique 3DSIM to capture high‐resolution images of MDVs. We optimized the imaging conditions both for high‐speed video microscopy and fixed‐cell imaging and analysis. From the 3DSIM videos, we observed an abundance of MDVs and many dynamic mitochondrial tubules. The density of MDVs in cells was compared for cells under normal growth conditions and cells during metabolic perturbation. Our results indicate a higher abundance of MDVs in H9c2 cells during glucose deprivation compared with cells under normal growth conditions. Furthermore, the results reveal a large untapped potential of 3DSIM in MDV research.