Data-Driven Filter Design in FBP: Transforming CT Reconstruction with Trainable Fourier Series

Sun Y, Schneider LS, Fan F, Thies M, Gu M, Mei S, Zhou Y, Bayer S, Maier A (2024)

Publication Language: English

Publication Status: Submitted

Publication Type: Conference contribution, Conference Contribution

Future Publication Type: Journal article

Publication year: 2024

Event location: Bamberg

DOI: 10.48550/arXiv.2401.16039

Abstract

In this study, we introduce a Fourier series-based trainable filter for computed tomography (CT) reconstruction within the filtered backprojection (FBP) framework. This method overcomes the limitation in noise reduction, inherent in conventional FBP methods, by optimizing Fourier series coefficients to construct the filter. This method enables robust performance across different resolution scales and maintains computational efficiency with minimal increment for the trainable parameters compared to other deep learning frameworks. Additionally, we propose Gaussian edge-enhanced (GEE) loss function that prioritizes the L1 norm of high-frequency magnitudes, effectively countering the blurring problems prevalent in mean squared error (MSE) approaches. The model's foundation in the FBP algorithm ensures excellent interpretability, as it relies on a data-driven filter with all other parameters derived through rigorous mathematical procedures. Designed as a plug-and-play solution, our Fourier series-based filter can be easily integrated into existing CT reconstruction models, making it a versatile tool for a wide range of practical applications. Our research presents a robust and scalable method that expands the utility of FBP in both medical and scientific imaging.

Authors with CRIS profile

Additional Organisation(s)

How to cite

APA:

Sun, Y., Schneider, L.-S., Fan, F., Thies, M., Gu, M., Mei, S.,... Maier, A. (2024). Data-Driven Filter Design in FBP: Transforming CT Reconstruction with Trainable Fourier Series. In Proceedings of the CT-Meeting. Bamberg, DE.

MLA:

Sun, Yipeng, et al. "Data-Driven Filter Design in FBP: Transforming CT Reconstruction with Trainable Fourier Series." Proceedings of the CT-Meeting, Bamberg 2024.

BibTeX: Download