ADVANCING NANO DRUG DELIVERY SYSTEM DETECTION THROUGH DEEPLEARNING: A MOBILENET MODEL APPROACH

An AI-based approach has the potential to improve treatment outcomes, increase patient satisfaction, and advance the field of pharmaceutical science. This study aims to address the existing limitations in NDDS classification,such as the variability in nanoparticle formulations and the complex nature of their interactions with biological systems by leveraging MobileNet's capabilities. The pre-processing pipeline implemented for this study comprises Gaussian blurring, Contrast Limited Adaptive Histogram Equalization (CLAHE), Otsu's thresholding, and image resizing, alongside conversion to a format suitable for input into the MobileNet architecture. The evaluation of the model on the set aside for testing produced an accuracy of 84.37% and a loss of 0.5543.In conclusion, we have succeeded in combining nanotechnology and pharmaceutical sciences with artificial intelligence to prepare a trained model to recognize the liposomes as Novel Drug Delivery System (NDDS) and to evaluate the nature and concentration of active ingredients carried inside them by utilizing a MobileNet model