Computationally Efficient CT Reconstruction via Structured Sparse Networks

Read full text Summarise with VIRAT
Authors: Jeroen van Dijk, Anneke Smit, Thomas de Vries
Cited by: 0
References: 18

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Clinical deployment of learned CT reconstruction models requires attention to runtime, memory footprint, and throughput. Building on convolution–self-attention architectures such as CTLformer, this paper introduces lightweight convolution–attention blocks with structured sparsity and low-rank attention approximation. The design reduces quadratic attention costs while keeping long-range dependency modeling. Experiments are conducted on two CT reconstruction datasets totaling 40,000 slices. Compared with transformer-heavy reconstruction models and standard hybrid baselines, the proposed approach reduces GPU memory usage by 28%–40% and improves inference throughput by 1.6×–2.1×, while keeping reconstruction accuracy within 0.2–0.4 dB PSNR of the full model.

Fields of Study & Subjects

Medical Imaging Techniques and Applications Advanced Neural Network Applications Advanced X-ray and CT Imaging

Publication details

Journal / source
American Journal of Artificial Intelligence and Neural Networks
Volume
7
Issue
1
Pages
133–140
Publication date
28 February 2026
Language
EN