Deriving Neural Network Architectures using Precision Learning: Parallel-to-fan beam Conversion
This work addresses image quality issues in interventional medical imaging by providing a more accurate conversion method, though it is incremental as it builds on existing precision learning concepts.
The paper tackled the parallel-to-fan beam conversion problem in hybrid MRI/X-ray imaging by deriving a neural network architecture using precision learning, which avoids interpolation and delivers sharper images compared to traditional methods.
In this paper, we derive a neural network architecture based on an analytical formulation of the parallel-to-fan beam conversion problem following the concept of precision learning. The network allows to learn the unknown operators in this conversion in a data-driven manner avoiding interpolation and potential loss of resolution. Integration of known operators results in a small number of trainable parameters that can be estimated from synthetic data only. The concept is evaluated in the context of Hybrid MRI/X-ray imaging where transformation of the parallel-beam MRI projections to fan-beam X-ray projections is required. The proposed method is compared to a traditional rebinning method. The results demonstrate that the proposed method is superior to ray-by-ray interpolation and is able to deliver sharper images using the same amount of parallel-beam input projections which is crucial for interventional applications. We believe that this approach forms a basis for further work uniting deep learning, signal processing, physics, and traditional pattern recognition.