Abstract: In one approach, VDAMP is improved to allow multiple coils. The aliasing is modeled in the wavelet domain with spatial modulation for each of the frequency subbands. The spatial modulation uses the coil sensitivities. As a result of the spatial modulation, the aliasing modeling more closely models the variance allowing the regularization to use denoising operations. In another approach, the regularization computation may be simplified by using a machine-learned network in VDAMP. To account for the aliasing modeling of VDAMP, a convolutional neural network is trained with input of both the noisy image and the covariances of the aliasing model.

Abstract: In one approach, VDAMP is improved to allow multiple coils. The aliasing is modeled in the wavelet domain with spatial modulation for each of the frequency subbands. The spatial modulation uses the coil sensitivities. As a result of the spatial modulation, the aliasing modeling more closely models the variance allowing the regularization to use denoising operations. In another approach, the regularization computation may be simplified by using a machine-learned network in VDAMP. To account for the aliasing modeling of VDAMP, a convolutional neural network is trained with input of both the noisy image and the covariances of the aliasing model.

Abstract: Magnetic resonance compressed sensing data may be acquired and reconstructed into an image. Noise-like aliasing present in the compressed sensing data may be modeled. The reconstruction may include denoising the compressed sensing data based on a noise level of the compressed sensing data, a sampling density of the compressed sensing data, and the model of the noise-like aliasing. A result of the denoising is denoised image data. The reconstruction may further include generating updated image data based on the compressed sensing data and the denoised image data. An output image based on the updated image may be output.

Abstract: Magnetic resonance compressed sensing data may be acquired and reconstructed into an image. Noise-like aliasing present in the compressed sensing data may be modeled. The reconstruction may include denoising the compressed sensing data based on a noise level of the compressed sensing data, a sampling density of the compressed sensing data, and the model of the noise-like aliasing. A result of the denoising is denoised image data. The reconstruction may further include generating updated image data based on the compressed sensing data and the denoised image data. An output image based on the updated image may be output.

Abstract: Disclosed herein are polypeptides and variants thereof comprising a polypeptide sequence having substantial identity to ricin A chain (RTA) that lack detectable N-glycosidase-rRNA activity or exhibit reduced N-glycosidase-rRNA activity as compared to controls and methods of making and using thereof. The polypeptides and variants have a greater solubility in aqueous solutions of physiological pH and ionic strength than RTA and also retain the integrity of the neutralizing immunological epitope of wild type RTA. Also disclosed are immunogenic compositions that may be used to immunize a subject against ricin intoxication. Methods of immunizing against, treating, and preventing ricin intoxication are disclosed.