Abstract: This invention discloses an auxiliary diagnostic model and an image processing method for detecting acute ischemic stroke. This refers to the technical field of medical image processing. The technical essentials are described as follow: the presented deep-learning model is based on generative adversarial networks (GANs), comprising a generator (G) and a discriminator (D). G is the first three-dimensional convolutional neural network, used to synthesize realistic images from raw data, while D is the second three-dimensional convolutional neural network, used to classify images as real or fake (synthetic). The presented GAN model can learn the mapping relationship from non-enhanced computed tomography (NECT) images to T2-weighted fluid-attenuation inversion recovery (FLAIR) magnetic resonance imaging (MRI), then converting the raw CT to synthetic FLAIR with high sensitivity.

Abstract: One example includes a scanning system. The system includes a phase-decorrelation optical coherence tomography (PhD-OCT) scanner configured to implement a scanning sequence via an optical signal on a sample medium. The system also includes a scanning controller configured to provide control signals to the PhD-OCT scanner to implement the scanning sequence and to obtain phase and amplitude information associated with a reflected version of the optical signal. The phase and amplitude information can be indicative of microscale dynamics of the sample medium. The scanning controller can also implement an algorithm to calculate a quantitative parameter of the sample medium based on the phase and amplitude information associated with the sample medium.

Abstract: One example includes a scanning system. The system includes a phase-decorrelation optical coherence tomography (PhD-OCT) scanner configured to implement a scanning sequence via an optical signal on a sample medium. The system also includes a scanning controller configured to provide control signals to the PhD-OCT scanner to implement the scanning sequence and to obtain phase and amplitude information associated with a reflected version of the optical signal. The phase and amplitude information can be indicative of microscale dynamics of the sample medium. The scanning controller can also implement an algorithm to calculate a quantitative parameter of the sample medium based on the phase and amplitude information associated with the sample medium.