Evaluation of carrier size and surface morphology in carrier-based dry powder inhalation by surrogate modeling

Effect of drug load on the aerosolisation propensity of binary adhesive mixtures for inhalation

The aim of this study was to investigate how the propensity for aerosolisation in binary adhesive mixtures was affected by the drug load, and to determine whether these findings could be linked to different blend states. Binary blends of two different lactose carriers, each with varying size and morphology, were prepared together with budesonide. In vitro aerosolisation studies were conducted at four different pressure drops, ranging from 0.5 to 4 kPa, utilising a Next Generation Impactor. Several dispersion parameters were derived from the relationship between the quantity of dispersed API and the pressure drop. The evolution of the parameters with drug load was complex, especially at low drug loads. While similar responses were observed for both carriers, the range of drug load that could be used varied significantly. The choice of carrier not only influenced the capacity for drug loading but also affected the spatial distribution of the API within the mixture, which, in turn, affected its aerosolisation propensity. Thus, the drug dispersion process could be linked to different configurations of the lactose carrier and budesonide in the blends, i.e. blend states. In conclusion, the study suggests that the concept of blend states can provide an explanation for the complex dispersion process observed in adhesive blends.

Deep learning approach for chemistry and processing history prediction from materials microstructure

Finding the chemical composition and processing history from a microstructure morphology for heterogeneous materials is desired in many applications. While the simulation methods based on physical concepts such as the phase-field method can predict the spatio-temporal evolution of the materials’ microstructure, they are not efficient techniques for predicting processing and chemistry if a specific morphology is desired. In this study, we propose a framework based on a deep learning approach that enables us to predict the chemistry and processing history just by reading the morphological distribution of one element. As a case study, we used a dataset from spinodal decomposition simulation of Fe–Cr–Co alloy created by the phase-field method. The mixed dataset, which includes both images, i.e., the morphology of Fe distribution, and continuous data, i.e., the Fe minimum and maximum concentration in the microstructures, are used as input data, and the spinodal temperature and initial chemical composition are utilized as the output data to train the proposed deep neural network. The proposed convolutional layers were compared with pretrained EfficientNet convolutional layers as transfer learning in microstructure feature extraction. The results show that the trained shallow network is effective for chemistry prediction. However, accurate prediction of processing temperature requires more complex feature extraction from the morphology of the microstructure. We benchmarked the model predictive accuracy for real alloy systems with a Fe–Cr–Co transmission electron microscopy micrograph. The predicted chemistry and heat treatment temperature were in good agreement with the ground truth.