The invention relates to a method for generating a synthetic elastography image (18), the method comprising the steps of (a) receiving a B-mode ultrasound image (5) of a region of interest; (b) generating a synthetic elastography image (18) of the region of interest by applying a trained artificial neural network (16) to the B-mode ultrasound image (5). The invention also relates to a method for training an artificial neural network (16)5 useful in generating synthetic elastography images, and a related computer program and system.

An unsupervised machine learning method with self-supervision losses improves a slice-wise spatial resolution of 3D medical images with thick slices, and does not require high resolution images as the ground truth for training. The method utilizes information from high-resolution dimensions to increase a resolution of another desired dimension.

System for image correction in PET is provided. The system may acquire a PET image and a CT image of a subject. The system may generate, based on the PET image and the CT image, an attenuation-corrected PET image of the subject by application of an attenuation correction model. The attenuation correction model may be a trained cascaded neural network including a trained first model and at least one trained second model downstream to the trained first model. During the application of the attenuation correction model, an input of each of the at least one trained second model may include the PET image, the CT image, and an output image of a previous trained model that is upstream and connected to the trained second model.

An improved x-ray cone-beam CT image reconstruction by end-to-end training of a multi-layered neural network is proposed, which employs cone-beam CT images of many patients as input training data, and precalculated scattering projection images of the same patients as output training data. After the training is completed, scattering projection images for a new patient are estimated by inputting a cone-beam CT image of the new patient into the trained multi-layered neural network. Subsequently, scatter-free projection images for the new patient are obtained by subtracting the estimated scattering projection images from measured projection images, beam angle by beam angle. A scatter-free cone-beam CT image is reconstructed from the scatter-free projection images.

There are provided machine learning device and method which can prepare divided data suitable for machine learning from volume data for learning. A machine learning unit (15) calculates detection accuracy of each organ O(j,i) in a predicted mask Pj using a loss function Loss. However, the detection accuracy of the organ O(k,i) with a volume ratio A(k,i)<Th is not calculated. That is, in the predicted mask Pk, the detection accuracy of the organ O(k,i) with a volume ratio that is small to some extent is ignored. The machine learning unit (15) changes each connection load of a neural network (16) from an output layer side to an input layer side according to the loss function Loss.

The present invention discloses a low dose Sinogram denoising and PET image reconstruction method based on teacher-student generator, the adopted network model is divided into a Sinogram denoising module and a PET image reconstruction module, the entire network needs to be processed in a training stage and a test stage. In the training stage: the present invention uses the denoising module to denoise the low dose Sinogram, and then makes the reconstruction module use the denoised Sinogram to reconstruct, in which the teacher generator is introduced in the training stage to constrain the whole, the denoising module is decoupled from the reconstruction module, and a better reconstructed image is obtained through training. In the testing stage, the present invention only needs to input low-dose Sinogram to the denoising module to obtain the denoised Sinogram, and then input the denoised Sinogram to the student generator to get the final reconstruction image.

A deep neural network-based reconstruction system for accelerated magnetic resonance imaging of vessel walls. The system can comprise a magnetic resonance imaging (MRI) scanner configured to obtain an image of the vessel walls, and a computer having a processor. The processor comprises a first and second subnetwork implemented in a cascade fashion. The first subnetwork comprises a convolutional neural network (CNN) and an output correcting module. The first subnetwork receives the image and transforms the image to a reduced artifact image. The second subnetwork is an identical duplicate of the first network. The second subnetwork boosts an accuracy of the reduced artifact image to generate a visual representation of the vessel walls. A computer display terminal is connected to the processor and is configured to display the visual representation of the vessel walls.

A method for generating synthetic X-ray images is provided. A first neural network is provided to generate at least one synthetic X-ray image having specified quality. A second neural network is provided to ascertain characterizing properties from at least one secondary X-ray image for the first neural network. The first neural network and the second neural network may be trained by primary X-ray images of specified minimum quality. The at least one secondary X-ray image has a lower quality compared to primary X-ray images. The at least one synthetic X-ray image is generated with the aid of the provided characterizing properties by the first neural network. The at least one synthetic X-ray image is improved with regard to quality compared to the at least one secondary X-ray image.

Systems and methods are provided for simulating medical images based on previously acquired data and a defined imaging protocol. In an example, a method includes generating a simulated medical image of a patient via virtual imaging based on previously obtained medical images and a scan intent of the virtual imaging, and outputting an imaging protocol based on a virtual protocol of the virtual imaging.

The present disclosure provides a medical imaging method and system and a non-transitory computer-readable storage medium. The medical imaging method comprises obtaining an original image acquired by an X-ray imaging system, and post-processing the original image based on a trained network to obtain an optimized image after processing. The medical imaging system comprises a control module, configured to obtain an original image of an object; a learning network module, configured to post-process the original image to obtain a post-processed image based on user preferences selected by one or more users; and an optimized module, configured to optimize the learning network based on generated images sent to the learning network module, wherein the generated images comprise the post-processed image previously obtained by the learning network module.