A Collaborative Study on the Classification of Silicone Oil Droplets and Protein Particles Using Flow Imaging Method

Past, Current, and Future: Application of Image Analysis in Small Molecule Pharmaceutical Development

The often-perceived limitations of image analysis have for many years impeded the widespread application of such systems as first line characterisation tools. Image analysis has, however, undergone a notable resurgence in the pharmaceutical industry fuelled by developments system capabilities and the desire of scientists to characterize the morphological nature of their particles more adequately. The importance of particle shape as well as size is now widely acknowledged. With the increasing use of modelling and simulations, and ongoing developments though the integration of machine learning and artificial intelligence, the utility of image analysis is increasing significantly driven by the richness of the data obtained. Such datasets provide means to circumvent the requirement to rely on less informative descriptors and enable the move towards the use of whole distributions. Combining the improved particle size and shape measurement and description with advances in modelling and simulations is enabling improved means to elucidate the link between particle and bulk powder properties. In addition to improved capabilities to describe input materials, approaches to characterize single components within multicomponent systems are providing scientists means to understand how their material may change during manufacture thus providing a means to link the behaviour of final dosage forms with the particle properties at the point of action. The aim is to provide an overview of image analysis and update readers with innovations and capabilities to other methods in the small molecule arena. We will also describe the use of AI for the improved analysis using image analysis.

Comparison of Protein-like Model Particles Fabricated by Micro 3D Printing to Established Standard Particles

Innovative analytical instruments and development of new methods has provided a better understanding of protein particle formation in biopharmaceuticals but have also challenged the ability to obtain reproducible and reliable measurements. The need for protein-like particle standards mimicking the irregular shape, translucent nature and near-to-neutral buoyancy of protein particles remained one of the hot topics in the field of particle detection and characterization in biopharmaceutical formulations. An innovative protein-like particle model has been developed using two photo polymerization (2PP) printing allowing to fabricate irregularly shaped particles with similar properties as protein particles at precise size of 50 µm and 150 µm, representative of subvisible particles and visible particles, respectively. A study was conducted to compare the morphological, physical, and optical properties of artificially generated protein particles, polystyrene spheres, ETFE, and SU-8 particle standards, along with newly developed protein-like model particles manufactured using 2PP printing. Our results suggest that 2PP printing can be used to produce protein-like particle standards that might facilitate harmonization and standardization of subvisible and visible protein particle characterization across laboratories and organizations.

Features in Backgrounds of Microscopy Images Introduce Biases in Machine Learning Analyses

Subvisible particles may be encountered throughout the processing of therapeutic protein formulations. Flow imaging microscopy (FIM) and backgrounded membrane imaging (BMI) are techniques commonly used to record digital images of these particles, which may be analyzed to provide particle size distributions, concentrations, and identities. Although both techniques record digital images of particles within a sample, FIM analyzes particles suspended in flowing liquids, whereas BMI records images of dry particles after collection by filtration onto a membrane. This study compared the performance of convolutional neural networks (CNNs) in classifying images of subvisible particles recorded by both imaging techniques. Initially, CNNs trained on BMI images appeared to provide higher classification accuracies than those trained on FIM images. However, attribution analyses showed that classification predictions from CNNs trained on BMI images relied on features contributed by the membrane background, whereas predictions from CNNs trained on FIM features were based largely on features of the particles. Segmenting images to minimize the contributions from image backgrounds reduced the apparent accuracy of CNNs trained on BMI images but caused minimal reduction in the accuracy of CNNs trained on FIM images. Thus, the seemingly superior classification accuracy of CNNs trained on BMI images compared to FIM images was an artifact caused by subtle features in the backgrounds of BMI images. Our findings emphasize the importance of examining machine learning algorithms for image analysis with attribution methods to ensure the robustness of trained models and to mitigate potential influence of artifacts within training data sets.

Supervised and unsupervised machine learning approaches for monitoring subvisible particles within an aluminum-salt adjuvanted vaccine formulation

Suspensions of protein antigens adsorbed to aluminum-salt adjuvants are used in many vaccines and require mixing during vial filling operations to prevent sedimentation. However, the mixing of vaccine formulations may generate undesirable particles that are difficult to detect against the background of suspended adjuvant particles. We simulated the mixing of a suspension containing a protein antigen adsorbed to an aluminum-salt adjuvant using a recirculating peristaltic pump and used flow imaging microscopy to record images of particles within the pumped suspensions. Supervised convolutional neural networks (CNNs) were used to analyze the images and create "fingerprints" of particle morphology distributions, allowing detection of new particles generated during pumping. These results were compared to those obtained from an unsupervised machine learning algorithm relying on variational autoencoders (VAEs) that were also used to detect new particles generated during pumping. Analyses of images conducted by applying both supervised CNNs and VAEs found that rates of generation of new particles were higher in aluminum-salt adjuvant suspensions containing protein antigen than placebo suspensions containing only adjuvant. Finally, front-face fluorescence measurements of the vaccine suspensions indicated changes in solvent exposure of tryptophan residues in the protein that occurred concomitantly with new particle generation during pumping.

Sub-Visible Particle Classification and Label Consistency Analysis for Flow-Imaging Microscopy Via Machine Learning Methods

Sub-visible particles can be a quality concern in pharmaceutical products, especially parenteral preparations. To quantify and characterize these particles, liquid samples may be passed through a flow-imaging microscopy instrument that also generates images of each detected particle. Machine learning techniques have increasingly been applied to this kind of data to detect changes in experimental conditions or classify specific types of particles, primarily focusing on silicone oil. That technique generally requires manual labeling of particle images by subject matter experts, a time-consuming and complex task. In this study, we created artificial datasets of silicone oil, protein particles, and glass particles that mimicked complex datasets of particles found in biopharmaceutical products. We used unsupervised learning techniques to effectively describe particle composition by sample. We then trained independent one-class classifiers to detect specific particle populations: silicone oil and glass particles. We also studied the consistency of the particle labels used to evaluate these models. Our results show that one-class classifiers are a reasonable choice for handling heterogeneous flow-imaging microscopy data and that unsupervised learning can aid in the labeling process. However, we found agreement among experts to be rather low, especially for smaller particles (< 8 µm for our Micro-Flow Imaging data). Given the fact that particle label confidence is not usually reported in the literature, we recommend more careful assessment of this topic in the future.

Particle sorting method based on swirl induction

Fluid-based methods for particle sorting demonstrate increasing appeal in many areas of biosciences due to their biocompatibility and cost-effectiveness. Herein, we construct a microfluidic sorting system based on a swirl microchip. The impact of microchannel velocity on the swirl stagnation point as well as particle movement is analyzed through simulation and experiment. Moreover, the quantitative mapping relationship between flow velocity and particle position distribution is established. With this foundation established, a particle sorting method based on swirl induction is proposed. Initially, the particle is captured by a swirl. Then, the Sorting Region into which the particle aims to enter is determined according to the sorting condition and particle characteristic. Subsequently, the velocities of the microchannels are adjusted to control the swirl, which will induce the particle to enter its corresponding Induction Region. Thereafter, the velocities are adjusted again to change the fluid field and drive the particle into a predetermined Sorting Region, hence the sorting is accomplished. We have extensively conducted experiments taking particle size or color as a sorting condition. An outstanding sorting success rate of 98.75% is achieved when dealing with particles within the size range of tens to hundreds of micrometers in radius, which certifies the effectiveness of the proposed sorting method. Compared to the existing sorting techniques, the proposed method offers greater flexibility. The adjustment of sorting conditions or particle parameters no longer requires complex chip redesign, because such sorting tasks can be successfully realized through simple microchannel velocities control.

Evaluation of subvisible particles in human immunoglobulin and lipid nanoparticles repackaged from a multi-dose vial using plastic syringes

The multi-dose vial (MDV) is widely used for most biopharmaceuticals that are repackaged in plastic syringes before use. However, subvisible particle formation with the use of plastic syringes containing silicone oil (SO syringes) for handling therapeutic proteins can be problematic. This study aimed to evaluate the extent of and trends in microparticle (>1 μm) formation and accumulation in repackaged syringes from MDVs containing human immunoglobulin (IgG) and lipid nanoparticles (LNPs). Light obscuration (LO) and flow imaging (FI) were used to analyze the microparticles. The number of microparticles observed with the use SO syringes was greater than that with SO-free syringes, and the number of microparticles continuously increased as did the number of times of repackaging in syringes for both drugs. However, a large variation was observed across different brands of SO syringes. In contrast, using a different technique of drug withdrawal from the vial significantly reduced the number of microparticles. Furthermore, the use of filter-integrated needles or the inclusion of stabilizers such as acetyl-arginine and Tween 20 into the formulation also helped reduce particle formation.

Evaluation of a Self-Supervised Machine Learning Method for Screening of Particulate Samples: A Case Study in Liquid Formulations

Imaging is commonly used as a characterization method in the pharmaceuticals industry, including for quantifying subvisible particles in solid and liquid formulations. Extracting information beyond particle size, such as classifying morphological subpopulations, requires some type of image analysis method. Suggested methods to classify particles have been based on pre-determined morphological features or use supervised training of convolutional neural networks to learn image representations in relation to ground truth labels. Complications arising from highly complex morphologies, unforeseen classes, and time-consuming preparation of ground truth labels, are some of the challenges faced by these methods. In this work, we evaluate the application of a self-supervised contrastive learning method in studying particle images from therapeutic solutions. Unlike with supervised training, this approach does not require ground truth labels and representations are learned by comparing particle images and their augmentations. This method provides a fast and easily implementable tool of coarse screening for morphological attribute assessment. Furthermore, our analysis shows that in cases with relatively balanced datasets, a small subset of an image dataset is sufficient to train a convolutional neural network encoder capable of extracting useful image representations. It is also demonstrated that particle classes typically observed in protein solutions administered by pre-filled syringes emerge as separated clusters in the encoder's embedding space, facilitating performing tasks such as training weakly-supervised classifiers or identifying the presence of new subpopulations.