Abstract: The present application discloses a label-free adaptive CT super-resolution reconstruction method, device and system based on a generative network, which comprises the following modules: an acquisition module configured for acquiring low-resolution original CT image data; a preprocessing module configured for performing super-resolution reconstruction on original CT images based on total variation to obtain an initial value; and a super-resolution reconstruction module configured for performing high-resolution reconstruction on the initial value. According to the present application, a parameter fine-tuning method is adopted, and a CT reconstruction network which is not suitable for a certain patient is adjusted into a network which is suitable for the patient's situation on the premise of not using a large number of data sets for training; only the low-resolution CT data of the patient is used in this process, and the corresponding high-resolution CT data is not needed as a label.

Abstract: Disclosed is an image denoising method and apparatus based on wavelet high-frequency channel synthesis. Image data are expanded to a plurality of frequency-domain channels, a plurality of “less-noise” channels and a plurality of “more-noise” channels are grouped through a noise-sort algorithm, and a denoising submodule and a synthesis submodule based on style transfer are combined to form a generative network. A discriminative network is established to add a constraint to the global loss function. After iteratively training the GAN model described above, the denoised image data can be obtained through wavelet inverse transformation. The disclosed algorithm can effectively solve the problem of “blurring” and “loss of details” introduced by traditional filtering or CNN-based deep learning methods, which is especially suitable for noise-overwhelmed image data or high dimensional image data.

Abstract: The present invention discloses an automatic pancreas CT segmentation method based on a saliency-aware densely connected dilated convolutional neural network. Under a coarse-to-fine two-step segmentation framework, the method uses a densely connected dilated convolutional neural network as a basis network architecture to obtain multi-scale image feature expression of the target. An initial segmentation probability map of the pancreas is predicted in the coarse segmentation stage. A saliency map is then calculated through saliency transformation based on a geodesic distance transformation. A saliency-aware module is introduced into the feature extraction layer of the densely connected dilated convolutional neural network, and the saliency-aware densely connected dilated convolutional neural network is constructed as the fine segmentation network model. A coarse segmentation model and the fine segmentation model are trained using a training set, respectively.

Abstract: The present invention discloses an automatic pancreas CT segmentation method based on a saliency-aware densely connected dilated convolutional neural network. Under a coarse-to-fine two-step segmentation framework, the method uses a densely connected dilated convolutional neural network as a basis network architecture to obtain multi-scale image feature expression of the target. An initial segmentation probability map of the pancreas is predicted in the coarse segmentation stage. A saliency map is then calculated through saliency transformation based on a geodesic distance transformation. A saliency-aware module is introduced into the feature extraction layer of the densely connected dilated convolutional neural network, and the saliency-aware densely connected dilated convolutional neural network is constructed as the fine segmentation network model. A coarse segmentation model and the fine segmentation model are trained using a training set, respectively.