Defogging computational ghost imaging via eliminating photon number fluctuation and a cycle generative adversarial network

Imaging through fluctuating scattering media such as fog is of challenge since it seriously degrades the image quality.We investigate how the image quality of computational ghost imaging is reduced by fluctuating fog and how to obtain a high-quality defogging ghost image. We show theoretically and experimentally that the photon number fluctuations introduced by fluctuating fog is the reason for ghost image degradation. An algorithm is proposed to process the signals collected by the computational ghost imaging device to eliminate photon number fluctuations of different measurement events. Thus, a high-quality defogging ghost image is reconstructed even though fog is evenly distributed on the optical path. A nearly 100% defogging ghost image is obtained by further using a cycle generative adversarial network to process the reconstructed defogging image.

Improving Brain Tumor Classification with Deep Learning Using Synthetic Data

Deep learning(DL)techniques,which do not need complex preprocessing and feature analysis,are used in many areas of medicine and achieve promising results.On the other hand,in medical studies,a limited dataset decreases the abstraction ability of the DL model.In this context,we aimed to produce synthetic brain images including three tumor types(glioma,meningioma,and pituitary),unlike traditional data augmentation methods,and classify them with DL.This study proposes a tumor classification model consisting of a Dense Convolutional Network(DenseNet121)-based DL model to prevent forgetting problems in deep networks and delay information flow between layers.By comparing models trained on two different datasets,we demonstrated the effect of synthetic images generated by Cycle Generative Adversarial Network(CycleGAN)on the generalization of DL.One model is trained only on the original dataset,while the other is trained on the combined dataset of synthetic and original images.Synthetic data generated by CycleGAN improved the best accuracy values for glioma,meningioma,and pituitary tumor classes from 0.9633,0.9569,and 0.9904 to 0.9968,0.9920,and 0.9952,respectively.The developed model using synthetic data obtained a higher accuracy value than the related studies in the literature.Additionally,except for pixel-level and affine transform data augmentation,synthetic data has been generated in the figshare brain dataset for the first time.