scholarly journals Effect of Processing/Formulation Parameters on Particle Size of Nanoemulsions Containing Ibuprofen - An Artificial Neural Networks Study

2020 ◽  
Vol 27 (2) ◽  
pp. 230-237
Author(s):  
Ali Hanafi ◽  
Amir Amani
Keyword(s):  
Neural Networks ◽  
Particle Size ◽  
Artificial Neural Networks ◽  
Droplet Size ◽  
Tween 80 ◽  
Homogenization Time ◽  
Minimum Particle Size ◽  
Artificial Neural ◽  
Formulation Parameters ◽  
Positive Effect

Background: Nanoemulsions are colloidal transparent systems for the delivery of hydrophobic drugs. This study aimed to determine the effect of parameters affecting particle size of a nanoemulsion containing ibuprofen using artificial neural networks (ANNs). Methods: Nanoemulsion samples with different values of independent variables, namely, concentration of ethanol, ibuprofen and Tween 80 as well as exposure (homogenization) time were prepared and their particle size was measured using dynamic light scattering (DLS). The data were then modelled by ANNs. Results: From the results, increasing the exposure time had a positive effect on reducing droplet size. The effect of concentration of ethanol and Tween 80 on droplet size depended on the amount of ibuprofen. Our results demonstrate that ibuprofen concentration also had a reverse relation with the size of the nanoemulsions. Conclusion: It was concluded that to obtain minimum particle size, exposure (homogenization)time should be maximized.

scholarly journals Workflow towards automated segmentation of agglomerated, non-spherical particles from electron microscopy images using artificial neural networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Bastian Rühle ◽  
Julian Frederic Krumrey ◽  
Vasile-Dan Hodoroaba
Keyword(s):  
Electron Microscopy ◽  
Neural Networks ◽  
Particle Size ◽  
Artificial Neural Networks ◽  
Generative Adversarial Networks ◽  
Size Distributions ◽  
Particle Size Distributions ◽  
Adversarial Networks ◽  
Artificial Neural ◽  
Microscopy Images

AbstractWe present a workflow for obtaining fully trained artificial neural networks that can perform automatic particle segmentations of agglomerated, non-spherical nanoparticles from scanning electron microscopy images “from scratch”, without the need for large training data sets of manually annotated images. The whole process only requires about 15 min of hands-on time by a user and can typically be finished within less than 12 h when training on a single graphics card (GPU). After training, SEM image analysis can be carried out by the artificial neural network within seconds. This is achieved by using unsupervised learning for most of the training dataset generation, making heavy use of generative adversarial networks and especially unpaired image-to-image translation via cycle-consistent adversarial networks. We compare the segmentation masks obtained with our suggested workflow qualitatively and quantitatively to state-of-the-art methods using various metrics. Finally, we used the segmentation masks for automatically extracting particle size distributions from the SEM images of TiO2 particles, which were in excellent agreement with particle size distributions obtained manually but could be obtained in a fraction of the time.

Sign in / Sign up

Export Citation Format

Share Document