Robust deep learning optical autofocus system applied to automated multiwell plate single molecule localization microscopy.

We presenta robust, long-range optical autofocus system for microscopy utilizing machine learning. This can be useful for experiments with long image data acquisition times that may be impacted by defocusing resulting from drift of components, for example due to changes in temperature or mechanical drift. It is also useful for automated slide scanning or multiwell plate imaging where the sample(s) to be imaged may not be in the same horizontal plane throughout the image data acquisition. To address the impact of (thermal or mechanical) fluctuations over time in the optical autofocus system itself, we utilize a convolutional neural network (CNN) that is trained over multiple days to account for such fluctuations. To address the trade-off between axial precision and range of the autofocus, we implement orthogonal optical readouts with separate CNN training data, thereby achieving an accuracy well within the 600 nm depth of field of our 1.3 numerical aperture objective lens over a defocus range of up to approximately +/-100 µm. We characterize the performance of this autofocus system and demonstrate its application to automated multiwell plate single molecule localization microscopy.

Many microscopy experiments involve extended imaging of samples over timescales from minutes to days, during which the microscope can 'drift' out of focus. When imaging at high magnification, the depth of field is of the order of one micron and so the imaging system should keep the sample in the focal plane of the microscope objective lens to this precision. Unfortunately, temperature changes in the laboratory can cause thermal expansion of microscope components that can move the focal plane by more than a micron and such changes can occur on a timescale of minutes. This is a particular issue for super-resolved microscopy experiments using single molecule localization microscopy (SMLM) techniques, for which 1000s of images are acquired, and for automated imaging of multiple samples in multiwell plates. It is possible to maintain the sample in the focal plane focus position by either automatically moving the sample or adjusting the imaging system, for example by moving the objective lens. This is called 'autofocus' and is frequently achieved by reflecting a light beam from the microscope coverslip and measuring its position of beam profile as a function of defocus of the microscope. The correcting adjustment is then usually calculated analytically but there is recent interest in using machine learning techniques to determine the required focussing adjustment. Here, we present a system that uses a neural network to determine the required defocus correcting adjustment from camera images of a laser beam that is reflected from the coverslip. Unfortunately, this approach will only work when the microscope is in the same condition as it was when the neural network was trained - and this can be compromised by the same drift of the optical system that causes the defocus needing to be corrected. We show, however, that by training a neural network over an extended period, for example 10 days, this approach can 'learn' about the optical system drifts and provide the required autofocus function. We also show that an optical system utilizing a rectangular slit can make two measurements of the defocus simultaneously, with one measurement being optimized for high accuracy over a limited range (±10 µm) near focus and the other providing lower accuracy but over a much longer range (±100 µm). This robust autofocus system is suitable for automated super-resolved microscopy of arrays of samples in a multiwell plate using SMLM, for which an experiment routinely lasts more than 5 h.

Single-shot phase contrast microscopy using polarisation-resolved differential phase contrast.

We present a robust, low-cost single-shot implementation of differential phase microscopy utilising a polarisation-sensitive camera to simultaneously acquire four images from which phase contrast images can be calculated. This polarisation-resolved differential phase contrast (pDPC) microscopy technique can be easily integrated with fluorescence microscopy.

Application of direct stochastic optical reconstruction microscopy (dSTORM) to the histological analysis of human glomerular disease.

Electron microscopy (EM) following immunofluorescence (IF) imaging is a vital tool for the diagnosis of human glomerular diseases, but the implementation of EM is limited to specialised institutions and it is not available in many countries. Recent progress in fluorescence microscopy now enables conventional widefield fluorescence microscopes to be adapted at modest cost to provide resolution below 50 nm in biological specimens. We show that stochastically switched single-molecule localisation microscopy can be applied to clinical histological sections stained with standard IF techniques and that such super-resolved IF may provide an alternative means to resolve ultrastructure to aid the diagnosis of kidney disease where EM is not available. We have implemented the direct stochastic optical reconstruction microscopy technique with human kidney biopsy frozen sections stained with clinically approved immunofluorescent probes for the basal laminae and immunoglobulin G deposits. Using cases of membranous glomerulonephritis, thin basement membrane lesion, and lupus nephritis, we compare this approach to clinical EM images and demonstrate enhanced imaging compared to conventional IF microscopy. With minor modifications in established IF protocols of clinical frozen renal biopsies, we believe the cost-effective adaptation of conventional widefield microscopes can be widely implemented to provide super-resolved image information to aid diagnosis of human glomerular disease.