JenaBatteries (Germany)

AimsTo develop a generative adversarial network (GAN) capable of generating realistic high-resolution anterior segment optical coherence tomography (AS-OCT) images.MethodsThis study included 142 628 AS-OCT B-scans from the American University of Beirut Medical Center. The Style and WAvelet based GAN architecture was trained to generate realistic AS-OCT images and was evaluated through the Fréchet Inception Distance (FID) Score and a blinded assessment by three refractive surgeons who were asked to distinguish between real and generated images. To assess the suitability of the generated images for machine learning tasks, a convolutional neural network (CNN) was trained using a dataset of real and generated images over a classification task. The generated AS-OCT images were then upsampled using an enhanced super-resolution GAN (ESRGAN) to achieve high resolution.ResultsThe generated images exhibited visual and quantitative similarity to real AS-OCT images. Quantitative similarity assessed using FID scored an average of 6.32. Surgeons scored 51.7% in identifying real versus generated images which was not significantly better than chance (p value >0.3). The CNN accuracy improved from 78% to 100% when synthetic images were added to the dataset. The ESRGAN upsampled images were objectively more realistic and accurate compared with traditional upsampling techniques by scoring a lower Learned Perceptual Image Patch Similarity of 0.0905 compared with 0.4244 of bicubic interpolation.ConclusionsThis study successfully developed and leveraged GANs capable of generating high-definition synthetic AS-OCT images that are realistic and suitable for machine learning and image analysis tasks.

Aqueous organic redox-flow batteries are an emerging technological solution in the field of grid-scale energy storage, owing to their long lifetime, safety, chemical flexibility, potential for low cost and environmental friendliness. In this work we present a physics-based dimensionality reduced model for the performance prediction of aqueous organic redox flow batteries. The model allows for fast evaluations of the cell voltage and power density, which are expressed explicitly in terms of the electric current density and state of charge. The model takes into consideration important phenomena, such as the activation and concentration overpotentials in the electrodes as well as the non-negligible electro-osmotic drag of water through the membrane. A sensitivity analysis of the model indicates the influence of various model parameters at different current densities on the predicted cell voltage. In this work we found the formal potentials and ohmic cell resistance to be the most critical parameters for performance prediction. Experimental parameterization and validation on cycling and polarization experiments revealed good agreement with the experiments within a predicted range of validity due to the different simplifying assumptions.