Application of Mobile Net Model to Assess the Phytoniosomes Loaded Sonchus Maritimus for Hepatocytes Targeting

Abstract

Lipid nanoparticles have received much attention owing to their applications as drug delivery systems. They can target specific tissues for delivering their contents and are secure as well as efficient. One kind of lipid nanoparticle known as niosomes is made up of non-ionic surfactants, which have been shown to be successful because of their long-term stability and biocompatibility. Sonchus maritimus is an important plant that exhibits various biological activities. The aim of this search is to use artificial intelligence in order to characterize the architecture of Sonchus maritimus loaded niosomes to target the affected liver tissue based on optical micrographs. It has been established that computerized examinations of the niosomes nanoparticle architecture were complex. A suggested approach automates the characterization of the niosome structure. Its foundation is the application of neural networks to the ability to recognize optical images of niosome nanomaterials and to determine the amount of S. maritimus extract contained in niosomes. The preliminary processing of the niosome nanostructure images is described, and the results of the use of neural networks to identify the niosomes' structural features are presented. The high accuracy of using neural networks to determine the niosomes' structural characteristics is demonstrated. The model has been developed for recognizing the images of nanostructures and determining the amount of the loaded extract in them. This investigation is important for determining the morphological characteristics of niosomes loaded plant extract and their differentiation from other niosomes. This study sets a solid foundation for applying deep learning models in nanomedicine, with potential implications for enhancing precision in niosomes characterization.