In-process analysis of pharmaceutical emulsions using computer vision and artificial intelligence

Artificial intelligence-driven pharmaceutical industry: A paradigm shift in drug discovery, formulation development, manufacturing, quality control, and post-market surveillance

The advent of artificial intelligence (AI) has catalyzed a profound transformation in the pharmaceutical industry, ushering in a paradigm shift across various domains, including drug discovery, formulation development, manufacturing, quality control, and post-market surveillance. This comprehensive review examines the multifaceted impact of AI-driven technologies on all stages of the pharmaceutical life cycle. It discusses the application of machine learning algorithms, data analytics, and predictive modeling to accelerate drug discovery processes, optimize formulation development, enhance manufacturing efficiency, ensure stringent quality control measures, and revolutionize post-market surveillance methodologies. By describing the advancements, challenges, and future prospects of harnessing AI in the pharmaceutical landscape, this review offers valuable insights into the evolving dynamics of drug development and regulatory practices in the era of AI-driven innovation.

Artificial intelligence and classic methods to segment and characterize spherical objects in micrographs of industrial emulsions

The stability of emulsions is a critical concern across multiple industries, including food products, agricultural formulations, petroleum, and pharmaceuticals. Achieving prolonged emulsion stability is challenging and depends on various factors, with particular emphasis on droplet size, shape, and spatial distribution. Addressing this issue necessitates an effective investigation of these parameters and finding solutions to enhance emulsion stability. Image analysis offers a powerful tool for researchers to explore these characteristics and advance our understanding of emulsion instability in different industries. In this review, we highlight the potential of state-of-the-art deep learning-based approaches in computer vision and image analysis to extract relevant features from emulsion micrographs. A comprehensive summary of classic and cutting-edge techniques employed for characterizing spherical objects, including droplets and bubbles observed in micrographs of industrial emulsions, has been provided. This review reveals significant deficiencies in the existing literature regarding the investigation of highly concentrated emulsions. Despite the practical importance of these systems, limited research has been conducted to understand their unique characteristics and stability challenges. It has also been identified that there is a scarcity of publications in multimodal analysis and a lack of a complete automated in-line emulsion characterization system. This review critically evaluates the existing challenges and presents prospective directions for future advancements in the field, aiming to address the current gaps and contribute to the scientific progression in this area.

Image Segmentation and Quantification of Droplet dPCR Based on Thermal Bubble Printing Technology

Thermal inkjet printing can generate more than 300,000 droplets of picoliter scale within one second stably, and the image analysis workflow is used to quantify the positive and negative values of the droplets. In this paper, the SimpleBlobDetector detection algorithm is used to identify and localize droplets with a volume of 24 pL in bright field images and suppress bright spots and scratches when performing droplet location identification. The polynomial surface fitting of the pixel grayscale value of the fluorescence channel image can effectively compensate and correct the image vignetting caused by the optical path, and the compensated fluorescence image can accurately classify positive and negative droplets by the k-means clustering algorithm. 20 µL of the sample solution in the result reading chip can produce more than 100,000 effective droplets. The effective droplet identification correct rate of 20 images of random statistical samples can reach more than 99% and the classification accuracy of positive and negative droplets can reach more than 98% on average. This paper overcomes the problem of effectively classifying positive and negative droplets caused by the poor image quality of photographed picolitre ddPCR droplets caused by optical hardware limitations.

Predicting bilgewater emulsion stability by oil separation using image processing and machine learning

Bilgewater is a shipboard multi-component oily wastewater, combining numerous wastewater sources. A better understanding of bilgewater emulsions is required for proper wastewater management to meet discharge regulations. In this study, we developed 360 emulsion samples based on commonly used Navy cleaner data and previous bilgewater composition studies. Oil value (OV) was obtained from image analysis of oil/creaming layer and validated by oil separation (OS) which was experimentally determined using a gravimetric method. OV (%) showed good agreement with OS (%), indicating that a simple image-based parameter can be used for emulsion stability prediction model development. An ANOVA analysis was conducted of the five variables (Cleaner, Salinity, Suspended Solids [SS], pH, and Temperature) that significantly impacted estimates of OV, finding that the Cleaner, Salinity, and SS variables were statistically significant (p < 0.05), while pH and Temperature were not. In general, most cleaners showed improved oil separation with salt additions. Novel machine learning (ML)-based predictive models of both classification and regression for bilgewater emulsion stability were then developed using OV. For classification, the random forest (RF) classifiers achieved the most accurate prediction with F1-score of 0.8224, while in regression-based models the decision tree (DT) regressor showed the highest prediction of emulsion stability with the average mean absolute error (MAE) of 0.1611. Turbidity also showed a good emulsion prediction with RF regressor (MAE of 0.0559) and RF classifier (F1-score of 0.9338). One predictor variable removal test showed that Salinity, SS, and Temperature are the most impactful variables in the developed models. This is the first study to use image processing and machine learning for the prediction of oil separation for the application of bilgewater assessment within the marine sector.

Deep learning in food science: An insight in evaluating Pickering emulsion properties by droplets classification and quantification via object detection algorithm

Understanding the complicated emulsion microstructures by microscopic images will help to further elaborate their mechanisms and relevance. The formidable goal of the classification and quantification of emulsion microstructure appears difficult to achieve. However, object detection algorithm in deep learning makes it feasible. This paper reports a new technique for evaluating Pickering emulsion properties through classification and quantification of the emulsion microstructure by object detection algorithm. The trained neural network models characterize the emulsion droplets by distinguishing between different individual emulsion droplets and morphological mechanisms from numerous microscopic images. The quantified results of the emulsion droplets presented in this study, provide details of statistical changes at different concentrations of the Pickering interface and storage temperatures enabling elucidation of the mechanisms involved. This methodology provides a new quantitative and statistical analysis of emulsion microstructure and properties.