Abstract: A mechanism for generating a partially denoised image. A residual noise image, obtained by processing an image using a convolutional neural network, is weighted. The blending or combination of the weighted residual noise image and the (original) image generates the partially denoised image.

Abstract: A method is provided for processing medical images, the method including receiving a first image and a second image different from the first image, where the second image is of the same subject matter as the first image. The method further includes identifying a plurality of anatomical structures in the first image and defining a plurality of image segments in the second image based N on locations of the anatomical structures identified in the first image. The method then applies a processing routine associated with a first anatomical structure to the first image segment in the second image and a processing routine associated with a second anatomical structure to the second image segment in the second image. Also provided is an imaging system for implementing the described method and a non-transitory computer readable medium storing a program for processing medical images.

Abstract: Disclosed herein is a medical system (100, 300, 400) comprising a memory (110) storing a trainable machine learning module (122) trained using training data descriptive of a training data distribution (600) to output a reconstructed medical image (136) in response to receiving measured medical image data (128) as input. The medical system comprises a computational system (104). The execution of machine executable instructions (120) causes the computational system to: receive (200) the measured medical image data and determine (202) the out-of-distribution score and the in-distribution accuracy score consecutively in an order determined a sequence, detect (204) a rejection of the measured medical image data using the out-of-distribution score and/or the in-distribution accuracy score during execution of the sequence, provide (206) a warning signal (134) if the rejection of the measured medical image data is detected.

Abstract: One embodiment of the present disclosure may provide a method for training and tuning a neural network model, including: adding simulated noise to an initial image of an object to generate a noisy image (601, 603), the simulated noise taking the same form as natural noise in the initial image; training a neural network model on the noisy image using the initial image as ground truth (605), wherein in the neural network model is trained on the noisy work model a tuning variable is extracted or generated, the tuning variable defining an amount of noise removed during use (607); identifying a first value for the tuning variable that minimizes a training cost function for the tuning variable is identified or for the initial image; and assigning a second value for the tuning variable (611), the second value different than the first value, wherein the neural network model identifies more noise in the noisy image when using the second value than when using the first value.

Abstract: An image processing system (IPS) and related method for supporting tomographic imaging. The system comprises an input interface (IN) for receiving, for a given projection direction (pi), a plurality of input projection images at different phase steps acquired by a tomographic X-ray imaging apparatus configured for dark-field and/or phase-contrast imaging. A machine learning component (MLC) processes the said plurality into output projection imagery that includes a dark-field projection image and/or a phase contrast projection image for the said given projection direction.

Abstract: System and related methods for de-noising 3D imagery. The system (IPS) comprises a pre-trained discriminative neural network (NN). The network includes a sequence of 3D convolutional operators (CV) for processing a received 3D image volume into a 3D output image. The 3D output image has a lower noise level than the 3D input image.