Application of Artificial Intelligence in the Classification of Microscopical Starch Images for Drug Formulation
This work addresses the need for accurate identification of starches in pharmaceuticals, but it is incremental as it applies existing transfer learning methods to a new domain-specific dataset.
The study tackled the problem of classifying microscopical starch images for drug formulation by applying AI techniques, achieving an accuracy of 81% with a model pretrained on ImageNet, compared to 61% with a model pretrained on a specialized dataset.
Starches are important energy sources found in plants with many uses in the pharmaceutical industry such as binders, disintegrants, bulking agents in drugs and thus require very careful physicochemical analysis for proper identification and verification which includes microscopy. In this work, we applied artificial intelligence techniques (using transfer learning and deep convolution neural network CNNs to microscopical images obtained from 9 starch samples of different botanical sources. Our approach obtained an accuracy of 61% when the machine learning model was pretrained on microscopic images from MicroNet dataset. However the accuracy jumped to 81% for model pretrained on random day to day images obtained from Imagenet dataset. The model pretrained on the imagenet dataset also showed a better precision, recall and f1 score than that pretrained on the imagenet dataset.