| Popis: |
Cerebral Organoids (CO) are brain-like structures that are paving the way to promising alternatives to in vivomodels for brain structure analysis. Available microscopic image databases of CO cultures contain only afew tens of images and are not widespread due to their recency. However, developing and comparing reliableanalysis methods, be they semi-automatic or learning-based, requires larger datasets with a trusted groundtruth. We extend a small database of bright-field CO using an Adversarial Autoencoder(AAEGAN) aftercomparing various Generative Adversarial Network (GAN) architectures. We test several loss variations,by metric calculations, to overcome the generation of blurry images and to increase the similitude betweenoriginal and generated images. To observe how the optimization could enrich the input dataset in variability,we perform a dimensional reduction by t-distributed Stochastic Neighbor Embedding (t-SNE). To highlight apotential benefit effect of one of these optimizations we implement a U-Net segmentation task with the newlygenerated images compared to classical data augmentation strategies. The Perceptual wasserstein loss proveto be an efficient baseline for future investigations of bright-field CO database augmentation in term of qualityand similitude. The segmentation is the best perform when training step include images from this generativeprocess. According to the t-SNE representation we have generated high quality images which enrich theinput dataset regardless of loss optimization. We are convinced each loss optimization could bring a differentinformation during the generative process that are still yet to be discovered. |
