Biology subjects

Neil, M. A. A.

Publications and source records attributed to Neil, M. A. A..

3 recordsLinked to original sources

bioRxiv2024

Model-free machine learning-based 3D single molecule localisation microscopy

Single molecule localisation microscopy (SMLM) can provide two-dimensional super-resolved image data from conventional fluorescence microscopes, while three dimensional (3D) SMLM usually involves a modification of the microscope, e.g. to engineer a predictable axial variation in the point spread function. Here we demonstrate a 3D SMLM approach (we call "easyZloc") utilising a lightweight Convolutional Neural Network that is generally applicable, including with "standard" (unmodified) fluorescence microscopes, and which we consider may be practically useful in a high throughput SMLM workflow. We demonstrate the reconstruction of nuclear pore complexes with comparable performance to previously reported methods but with a significant reduction in computational power and execution time. 3D reconstructions of the nuclear envelope and a tubulin sample over a larger axial range are also shown.

biophysics↗

bioRxiv2022

Robust, single-shot, optical autofocus system utilizing cylindrical lenses to provide high precision and long range of operation

We present a robust, "real-time" optical autofocus system for microscopy that provides high accuracy (<230 nm) and long range ([~]130 {micro}m) with a 1.4 numerical aperture oil immersion objective lens. This autofocus can operate in a closed loop, single-shot functionality over a range of {+/-}37.5 {micro}m and can also operate as a 2-step process up to {+/-}68 {micro}m. A real-time autofocus capability is useful for experiments with long image data acquisition times, including single molecule localization microscopy, that may be impacted by defocusing resulting from drift of components, e.g., due to changes in temperature or mechanical drift. It is also vital for automated slide scanning or multiwell plate imaging where the sample may not be in the same horizontal plane for every field of view during the image data acquisition. To realise high precision and long range, we implement orthogonal optical readouts using cylindrical lenses. We demonstrate the performance of this new optical autofocus system with automated multiwell plate imaging and single molecule localisation microscopy and illustrate the benefit of using a superluminescent diode as the autofocus light source.

bioengineering↗

bioRxiv2021

Robust optical autofocus system utilizing neural networks trained for extended range and time-course and automated multiwell plate imaging including single molecule localization microscopy

We present a 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, e.g. 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 utilise 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 m. We characterise the performance of this autofocus system and demonstrate its application to automated multiwell plate single molecule localisation microscopy.

bioengineering↗