Display Field-Of-View Agnostic Robust CT Kernel Synthesis Using Model-Based Deep Learning

TL;DR

The study addresses the challenge of DFOV-dependent image-domain kernel synthesis in CT, where robust cross-kernel conversion is difficult when raw sinograms are unavailable. It introduces a model-based deep learning framework that embeds the forward operator $y = H x + n$, with $H = F^T Λ F$ and Λ encoding the DFOV-dependent MTF, and enforces data consistency within an unrolled network. Training incorporates DFOV-dependent noise via water phantoms and uses five shared unrolls to achieve DFOV-agnostic performance. Experiments on clinical lung data and wire-phantom MTF analyses show sharper outputs and improved MTF fidelity compared with direct learning, suggesting real-time, DFOV-robust kernel synthesis is feasible.

Abstract

In X-ray computed tomography (CT) imaging, the choice of reconstruction kernel is crucial as it significantly impacts the quality of clinical images. Different kernels influence spatial resolution, image noise, and contrast in various ways. Clinical applications involving lung imaging often require images reconstructed with both soft and sharp kernels. The reconstruction of images with different kernels requires raw sinogram data and storing images for all kernels increases processing time and storage requirements. The Display Field-of-View (DFOV) adds complexity to kernel synthesis, as data acquired at different DFOVs exhibit varying levels of sharpness and details. This work introduces an efficient, DFOV-agnostic solution for image-based kernel synthesis using model-based deep learning. The proposed method explicitly integrates CT kernel and DFOV characteristics into the forward model. Experimental results on clinical data, along with quantitative analysis of the estimated modulation transfer function using wire phantom data, clearly demonstrate the utility of the proposed method in real-time. Additionally, a comparative study with a direct learning network, that lacks forward model information, shows that the proposed method is more robust to DFOV variations.

Figures (5)

• Figure 1: Input (smooth) and target (sharp) kernel MTFs corresponding to different DFOVs. An increase in DFOV leads to high frequency content in the image.
• Figure 2: A $100 \times 100$ patch of a water phantom scanned at different DFOV values demonstrates significant texture changes as the DFOV increases. This dependency makes it challenging to develop a image-based kernel synthesis model that is agnostic to DFOV.
• Figure 3: The proposed training pipeline explicitly utilizes DFOV dependent water phantom data as noise together with input and target slice pairs. The network based project step acts as a generic DFOV agnostic denoiser that is shared across five unrolls used during network training. The analytical solution to the Data Consistency (DC) step is shown in Eq. \ref{['eq:dc']}. Incorporating the DC step explicitly into the learning framework helps in developing DFOV agnostic deep model.
• Figure 4: The top row shows inference results at a DFOV of 5 cm, and the bottom row at a DFOV of 10 cm. The proposed method in (c) produces sharper output compared to the direct learning method in (b). The green circle highlights artifacts (in zoomed version) in the DFOV 5 cm output of the direct learning method. The red arrow indicates hallucinations in the direct learning method, whereas the proposed method retains the structure well.
• Figure 5: (a) Estimated wire phantom images visually show that proposed method results in sharper output compared to a direct learning method. (b) Quantitative results at DFOV 10 cm on wire phantom data demonstrate that the proposed method produces sharper output compared to the direct learning method. The orange curve represents the direct learning method, which has less mid-frequency boost compared to the green curve representing the proposed method.