Apparatus and method for image reconstruction using feature-aware deep learning

Abstract

A method and apparatus is provided to perform medical imaging in which feature-aware reconstruction is performed using a neural network. The neural network is trained to perform feature-aware reconstruction by using a training dataset in which the target data has a spatially-dependent degree of denoising and artifact reduction based on the features represented in the image. For example, a target image can be generated by reconstructing multiple images, each using a respective regularization parameter that is optimized for a different anatomy/organ (e.g., abdomen, lung, bone, etc.). And a target image can be generated using artifact reduction method (e.g. metal artifact reduction, aliasing artifact reduction, etc.). Then respective regions/features (e.g., abdomen, lung, and bone, artifact free, regions/features) can be extracted from the corresponding images and combined into a single combined image, which is used as the target data to train the neural network.