Faculty of Engineering & Design, Atlantic Technological University (ATU), Ash Ln, Ballytivnan, Sligo, F91 YW50, Ireland; Center of Precision Engineering, Materials and Manufacturing Research (PEM), Atlantic Technological University (ATU), Sligo, Ireland.
Department Of Chemical Science, Faculty Of Science & Engineering, University of Limerick, Ireland.
Int J Pharm. 2024 Jan 5;649:123633. doi: 10.1016/j.ijpharm.2023.123633. Epub 2023 Nov 22.
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.
乳液的稳定性是多个行业（包括食品产品、农业制剂、石油和制药）都非常关注的一个关键问题。实现长期的乳液稳定性是具有挑战性的，取决于各种因素，特别是液滴的大小、形状和空间分布。解决这个问题需要对这些参数进行有效的研究，并找到增强乳液稳定性的解决方案。图像分析为研究人员提供了一种强大的工具，用于探索这些特性，并深入了解不同行业中乳液的不稳定性。在这篇综述中，我们强调了基于深度学习的现代计算机视觉和图像分析方法在从乳液显微照片中提取相关特征方面的潜力。我们提供了经典和前沿技术的全面总结，这些技术用于对球形物体（包括在工业乳液的显微照片中观察到的液滴和气泡）进行特征描述。这篇综述揭示了现有文献在研究高浓度乳液方面存在的显著缺陷。尽管这些系统具有实际重要性，但对理解它们的独特特性和稳定性挑战的研究却非常有限。此外，还发现多模态分析方面的出版物较少，也缺乏完整的自动化在线乳液特性描述系统。这篇综述批判性地评估了现有挑战，并提出了未来该领域发展的前瞻性方向，旨在解决当前的差距，并为该领域的科学进步做出贡献。
