Task-based Generation of Optimized Projection Sets using Differentiable Ranking
This work addresses the challenge of optimizing projection selection in CT imaging for non-destructive testing, but it is incremental as it builds on existing methods without major breakthroughs.
The paper tackles the problem of selecting valuable projections in CT scans to improve image reconstruction and diagnosis by integrating projection-based detectability and data completeness into a neural network with differentiable ranking, achieving comparable results to previous methods on simulated data.
We present a method for selecting valuable projections in computed tomography (CT) scans to enhance image reconstruction and diagnosis. The approach integrates two important factors, projection-based detectability and data completeness, into a single feed-forward neural network. The network evaluates the value of projections, processes them through a differentiable ranking function and makes the final selection using a straight-through estimator. Data completeness is ensured through the label provided during training. The approach eliminates the need for heuristically enforcing data completeness, which may exclude valuable projections. The method is evaluated on simulated data in a non-destructive testing scenario, where the aim is to maximize the reconstruction quality within a specified region of interest. We achieve comparable results to previous methods, laying the foundation for using reconstruction-based loss functions to learn the selection of projections.