Computationally Efficient CT Reconstruction via Structured Sparse Networks
American Journal of Artificial Intelligence and Neural Networks · 28.02.2026 · 7 (1) · 133-140
DOI: 10.71465/ajainn3633 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Artificial Intelligence and Neural Networks, online erschienen am 28.02.2026. Verfasst von Jeroen van Dijk und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Dijk, J. V., Smit, A., & Vries, T. D. (2026). Computationally Efficient CT Reconstruction via Structured Sparse Networks. American Journal of Artificial Intelligence and Neural Networks, 7(1), 133-140. https://doi.org/10.71465/ajainn3633
Vancouver
Dijk JV, Smit A, Vries TD. Computationally Efficient CT Reconstruction via Structured Sparse Networks. American Journal of Artificial Intelligence and Neural Networks. 2026;7(1):133-140. doi:10.71465/ajainn3633
BibTeX
@article{Dijk2026,
author = {Dijk, Jeroen van and Smit, Anneke and Vries, Thomas de},
title = {Computationally Efficient CT Reconstruction via Structured Sparse Networks},
journal = {American Journal of Artificial Intelligence and Neural Networks},
year = {2026},
volume = {7},
number = {1},
pages = {133--140},
doi = {10.71465/ajainn3633}
}
EUVIMED