Spatially-Adaptive Reconstruction in Computed Tomography using Neural Networks
This work addresses image quality enhancement in medical imaging for computed tomography applications, but it is incremental as it builds on existing reconstruction methods.
The authors tackled the problem of improving image reconstruction quality in computed tomography by proposing a supervised machine learning approach that fuses multiple image estimates with different bias/variance trade-offs using a neural network, resulting in improved reconstruction quality compared to existing methods.
We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in computed tomography. Our technique is based on a local nonlinear fusion of several image estimates, all obtained by applying a chosen reconstruction algorithm with different values of its control parameters. Usually such output images have different bias/variance trade-off. The fusion of the images is performed by feed-forward neural network trained on a set of known examples. Numerical experiments show an improvement in reconstruction quality relatively to existing direct and iterative reconstruction methods.