An ultra-compact particle size analyser using a CMOS image sensor and machine learning

Vaccine process technology-A decade of progress

In the past decade, new approaches to the discovery and development of vaccines have transformed the field. Advances during the COVID-19 pandemic allowed the production of billions of vaccine doses per year using novel platforms such as messenger RNA and viral vectors. Improvements in the analytical toolbox, equipment, and bioprocess technology have made it possible to achieve both unprecedented speed in vaccine development and scale of vaccine manufacturing. Macromolecular structure-function characterization technologies, combined with improved modeling and data analysis, enable quantitative evaluation of vaccine formulations at single-particle resolution and guided design of vaccine drug substances and drug products. These advances play a major role in precise assessment of critical quality attributes of vaccines delivered by newer platforms. Innovations in label-free and immunoassay technologies aid in the characterization of antigenic sites and the development of robust in vitro potency assays. These methods, along with molecular techniques such as next-generation sequencing, will accelerate characterization and release of vaccines delivered by all platforms. Process analytical technologies for real-time monitoring and optimization of process steps enable the implementation of quality-by-design principles and faster release of vaccine products. In the next decade, the field of vaccine discovery and development will continue to advance, bringing together new technologies, methods, and platforms to improve human health.

Machine Learning Enhanced Optical Microscopy for the Rapid Morphology Characterization of Silver Nanoparticles

The rapid characterization of nanoparticles for morphological information such as size and shape is essential for material synthesis as they are the determining factors for the optical, mechanical, and chemical properties and related applications. In this paper, we report a computational imaging platform to characterize nanoparticle size and morphology under conventional optical microscopy. We established a machine learning model based on a series of images acquired by through-focus scanning optical microscopy (TSOM) on a conventional optical microscope. This model predicts the size of silver nanocubes with an estimation error below 5% on individual particles. At the ensemble level, the estimation error is 1.6% for the averaged size and 0.4 nm for the standard deviation. The method can also identify the tip morphology of silver nanowires from the mix of sharp-tip and blunt-tip samples at an accuracy of 82%. Furthermore, we demonstrated online monitoring for the evolution of the size distribution of nanoparticles during synthesis. This method can be potentially extended to more complicated nanomaterials such as anisotropic and dielectric nanoparticles.

Identification of Model Particle Mixtures Using Machine-Learning-Assisted Laser Diffraction

We put forward and demonstrate with model particles a smart laser-diffraction analysis technique aimed at particle mixture identification. We retrieve information about the size, shape, and ratio concentration of two-component heterogeneous model particle mixtures with an accuracy above 92%. We verify the method by detecting arrays of randomly located model particles with different shapes generated with a Digital Micromirror Device (DMD). In contrast to commonly-used laser diffraction schemes—In which a large number of detectors are needed—Our machine-learning-assisted protocol makes use of a single far-field diffraction pattern contained within a small angle (∼0.26°) around the light propagation axis. Therefore, it does not need to analyze particles of the array individually to obtain relevant information about the ensemble, it retrieves all information from the diffraction pattern generated by the whole array of particles, which simplifies considerably its implementation in comparison with alternative schemes. The method does not make use of any physical model of scattering to help in the particle characterization, which usually adds computational complexity to the identification process. Because of its reliability and ease of implementation, this work paves the way towards the development of novel smart identification technologies for sample classification and particle contamination monitoring in industrial manufacturing processes.

Prediction and Inverse Design of Structural Colors of Nanoparticle Systems via Deep Neural Network

Noniridescent and nonfading structural colors generated from metallic and dielectric nanoparticles with extraordinary optical properties hold great promise in applications such as image display, color printing, and information security. Yet, due to the strong wavelength dependence of optical constants and the radiation pattern, it is difficult and time-consuming to design nanoparticles with the desired hue, saturation, and brightness. Herein, we combined the Monte Carlo and Mie scattering simulations and a bidirectional neural network (BNN) to improve the design of gold nanoparticles' structural colors. The optical simulations provided a dataset including color properties and geometric parameters of gold nanoparticle systems, while the BNN was proposed to accurately predict the structural colors of gold nanoparticle systems and inversely design the geometric parameters for the desired colors. Taking the human chromatic discrimination ability as a criterion, our proposed approach achieved a high accuracy of 99.83% on the predicted colors and 98.5% on the designed geometric parameters. This work provides a general method to accurately and efficiently design the structural colors of nanoparticle systems, which can be exploited in a variety of applications and contribute to the development of advanced optical materials.

Decoding Optical Data with Machine Learning

Optical spectroscopy and imaging techniques play important roles in many fields such as disease diagnosis, biological study, information technology, optical science, and materials science. Over the past decade, machine learning (ML) has proved promising in decoding complex data, enabling rapid and accurate analysis of optical spectra and images. This review aims to shed light on various ML algorithms for optical data analysis with a focus on their applications in a wide range of fields. The goal of this work is to sketch the validity of ML-based optical data decoding. The review concludes with an outlook on unaddressed problems and opportunities in this emerging subject that interfaces optics, data science and ML.

Developments and opportunities in continuous biopharmaceutical manufacturing

Today's biologics manufacturing practices incur high costs to the drug makers, which can contribute to high prices for patients. Timely investment in the development and implementation of continuous biomanufacturing can increase the production of consistent-quality drugs at a lower cost and a faster pace, to meet growing demand. Efficient use of equipment, manufacturing footprint, and labor also offer the potential to improve drug accessibility. Although technological efforts enabling continuous biomanufacturing have commenced, challenges remain in the integration, monitoring, and control of traditionally segmented unit operations. Here, we discuss recent developments supporting the implementation of continuous biomanufacturing, along with their benefits.

Machine-learning-based computationally efficient particle size distribution retrieval from bulk optical properties

Retrieval of particle size distribution from bulk optical properties based on evolutionary algorithms is usually computationally expensive. In this paper, we report an efficient numerical approach to solving the inverse scattering problem by accelerating the calculation of bulk optical properties based on machine learning. With the assumption of spherical particles, the forward scattering by particles is first solved by Mie scattering theory and then approximated by machine learning. The particle swarm optimization algorithm is finally employed to optimize the particle size distribution parameters by minimizing the deviation between the target and simulated bulk optical properties. The accuracies of machine learning and particle swarm optimization are separately investigated. Meanwhile, both monomodal and bimodal size distributions are tested, considering the influences of random noise. Results show that machine learning is capable of accurately predicting the scattering efficiency for a specific size distribution in approximately 0.5 µs on a standalone computer. Therefore, the proposed method has the potential to serve as a powerful tool in real-time particle size measurement due to its advantages of simplicity and high efficiency.

An Adaptive Feature Selection Algorithm for Fuzzy Clustering Image Segmentation Based on Embedded Neighbourhood Information Constraints

This paper addresses the lack of robustness of feature selection algorithms for fuzzy clustering segmentation with the Gaussian mixture model. Assuming that the neighbourhood pixels and the centre pixels obey the same distribution, a Markov method is introduced to construct the prior probability distribution and achieve the membership degree regularisation constraint for clustering sample points. Then, a noise smoothing factor is introduced to optimise the prior probability constraint. Second, a power index is constructed by combining the classification membership degree and prior probability since the Kullback–Leibler (KL) divergence of the noise smoothing factor is used to supervise the prior probability; this probability is embedded into Fuzzy Superpixels Fuzzy C-means (FSFCM) as a regular factor. This paper proposes a fuzzy clustering image segmentation algorithm based on an adaptive feature selection Gaussian mixture model with neighbourhood information constraints. To verify the segmentation performance and anti-noise robustness of the improved algorithm, the fuzzy C-means clustering algorithm Fuzzy C-means (FCM), FSFCM, Spatially Variant Finite Mixture Model (SVFMM), EGFMM, extended Gaussian mixture model (EGMM), adaptive feature selection robust fuzzy clustering segmentation algorithm (AFSFCM), fast and robust spatially constrained Gaussian mixture model (GMM) for image segmentation (FRSCGMM), and improve method are used to segment grey images containing Gaussian noise, salt-and-pepper noise, multiplicative noise and mixed noise. The peak signal-to-noise ratio (PSNR) and the error rate (MCR) are used as the theoretical basis for assessing the segmentation results. The improved algorithm indicators proposed in this paper are optimised. The improved algorithm yields increases of 0.1272–12.9803 dB, 1.5501–13.4396 dB, 1.9113–11.2613 dB and 1.0233–10.2804 dB over the other methods, and the Misclassification rate (MSR) decreases by 0.32–37.32%, 5.02–41.05%, 0.3–21.79% and 0.9–30.95% compared to that with the other algorithms. It is verified that the segmentation results of the improved algorithm have good regional consistency and strong anti-noise robustness, and they meet the needs of noisy image segmentation.

A Local Neighborhood Robust Fuzzy Clustering Image Segmentation Algorithm Based on an Adaptive Feature Selection Gaussian Mixture Model

Since the fuzzy local information C-means (FLICM) segmentation algorithm cannot take into account the impact of different features on clustering segmentation results, a local fuzzy clustering segmentation algorithm based on a feature selection Gaussian mixture model was proposed. First, the constraints of the membership degree on the spatial distance were added to the local information function. Second, the feature saliency was introduced into the objective function. By using the Lagrange multiplier method, the optimal expression of the objective function was solved. Neighborhood weighting information was added to the iteration expression of the classification membership degree to obtain a local feature selection based on feature selection. Each of the improved FLICM algorithm, the fuzzy C-means with spatial constraints (FCM_S) algorithm, and the original FLICM algorithm were then used to cluster and segment the interference images of Gaussian noise, salt-and-pepper noise, multiplicative noise, and mixed noise. The performances of the peak signal-to-noise ratio and error rate of the segmentation results were compared with each other. At the same time, the iteration time and number of iterations used to converge the objective function of the algorithm were compared. In summary, the improved algorithm significantly improved the ability of image noise suppression under strong noise interference, improved the efficiency of operation, facilitated remote sensing image capture under strong noise interference, and promoted the development of a robust anti-noise fuzzy clustering algorithm.