Article: Enhanced slicing adversarial network with attention and multi-resolution generators for high-fidelity MRI reconstruction Journal: International Journal of Biomedical Engineering and Technology (IJBET) 2026 Vol.50 No.4 pp.347 - 373 Abstract: We introduce SAN++, an enhanced slicing adversarial network for compressed-sensing MRI reconstruction that integrates three key novelties: a transformer-guided attention block (TGAB), an edge-aware adaptive sampling module (EAASM), and a self-supervised pretraining strategy using masked image modelling (MIM). SAN++ extends prior GAN-based MRI methods by incorporating global transformer-based attention to better capture long-range dependencies, and by learning dynamic k-space sampling masks guided by salient image edges, which preserves critical structural features. We pretrain the network with a masked reconstruction task on large unlabeled datasets, then fine-tune adversarially with multi-resolution generators and a sliced optimal transport loss. Experiments on MRI datasets under various undersampling ratios (4×, 8×) and noise levels demonstrate that SAN++ outperforms DAGAN, RefineGAN. SAN++ achieves higher PSNR/SSIM and lower LPIPS perceptual error across settings, and shows robust performance under noise and sampling variability. An ablation study confirms each component's benefit, notably a 2-3 dB PSNR gain from TGAB and EAASM. Our results (with quantitative tables and example reconstructions) highlight the efficacy of combining transformer-guided attention, adaptive sampling, and self-supervised pretraining in adversarial MRI reconstruction. Inderscience Publishers - linking academia, business and industry through research

Title: Enhanced slicing adversarial network with attention and multi-resolution generators for high-fidelity MRI reconstruction

Authors: Libya Thomas; Joseph Zacharias

Addresses: College of Engineering Trivandrum, Trivandrum, 695016, Kerala, India; Affiliated to: A.P.J. Abdul Kalam Technological University, India ' College of Engineering Trivandrum, Trivandrum, 695016, Kerala, India; Affiliated to: A.P.J. Abdul Kalam Technological University, India

Abstract: We introduce SAN++, an enhanced slicing adversarial network for compressed-sensing MRI reconstruction that integrates three key novelties: a transformer-guided attention block (TGAB), an edge-aware adaptive sampling module (EAASM), and a self-supervised pretraining strategy using masked image modelling (MIM). SAN++ extends prior GAN-based MRI methods by incorporating global transformer-based attention to better capture long-range dependencies, and by learning dynamic k-space sampling masks guided by salient image edges, which preserves critical structural features. We pretrain the network with a masked reconstruction task on large unlabeled datasets, then fine-tune adversarially with multi-resolution generators and a sliced optimal transport loss. Experiments on MRI datasets under various undersampling ratios (4×, 8×) and noise levels demonstrate that SAN++ outperforms DAGAN, RefineGAN. SAN++ achieves higher PSNR/SSIM and lower LPIPS perceptual error across settings, and shows robust performance under noise and sampling variability. An ablation study confirms each component's benefit, notably a 2-3 dB PSNR gain from TGAB and EAASM. Our results (with quantitative tables and example reconstructions) highlight the efficacy of combining transformer-guided attention, adaptive sampling, and self-supervised pretraining in adversarial MRI reconstruction.

Keywords: CS-MRI; undersampling pattern; trade-off; neural network modified GAN.

DOI: 10.1504/IJBET.2026.154181

International Journal of Biomedical Engineering and Technology, 2026 Vol.50 No.4, pp.347 - 373

Received: 18 Jul 2025
Accepted: 27 Nov 2025
Published online: 15 Jun 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Enhanced slicing adversarial network with attention and multi-resolution generators for high-fidelity MRI reconstruction

Keep up-to-date