Loading
Life sciences · Preprint
arXiv · August 10, 2026
Posted before peer review. The findings may change or fail to hold.
This preprint introduces CRPDNN, a coordinate-residual physics-driven neural network for 3-D electromagnetic inverse scattering, demonstrated on synthetic and simulated problems. The method shows lower reconstruction error (2.10% average relative error) and faster computation than two comparison approaches in noise-free synthetic cases, but has not been validated on real experimental or clinical data nor peer reviewed.
Computational algorithm development with synthetic benchmark validation. Synthetic electromagnetic inverse scattering problems; no human subjects or real clinical imaging data.. Intervention: Coordinate-Residual Physics-Driven Neural Network (CRPDNN) for 3-D electromagnetic inverse scattering. Compared with: CSI method (7.97% relative error) and L₂/₃-FBE-WCIE method (3.99% relative error).
CRPDNN achieves average relative error of 2.10% on noise-free 3-D synthetic cases CRPDNN provides 5.5-fold speedup over CSI baseline and 12.1-fold speedup over L₂/₃-FBE-WCIE baseline CSI baseline achieves 7.97% relative error; L₂/₃-FBE-WCIE achieves 3.99% relative error on same synthetic cases
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
Not applicable. This is a computational algorithm paper with no human subjects, clinical outcomes, or in vivo validation. Any eventual clinical application would require substantial additional experimental validation and peer review.
This is an unrefereed arXiv preprint presenting a novel computational method for electromagnetic imaging with synthetic validation; it has not undergone peer review.
As stated by the source record.
Quoted from the source exactly as published.
Not applicable. This is a computational algorithm paper with no human subjects, clinical outcomes, or in vivo validation. Any eventual clinical application would require substantial additional experimental validation and peer review.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Electromagnetic inverse scattering is a nonlinear and ill-posed problem, where accurate reconstruction is challenging due to measurement limitations, noise, and high computational costs, especially for 3-D imaging. Although physics-driven neural networks (PDNNs) reduce the dependence on labeled training data, existing accelerated PDNN frameworks often rely on preliminary reconstruction-based region selection, which may introduce instability when the selected region is inaccurate. In this paper, a coordinate-residual physics-driven neural network (CRPDNN) is proposed for 3-D electromagnetic inverse scattering. The proposed solver directly reconstructs the unknown contrast distribution using normalized spatial coordinates and a residual convolutional network, without requiring a preliminary reconstruction. For the reported noise-free 3-D synthetic cases, CRPDNN achieves an average relative error of 2.10\%, compared with 7.97\% for CSI and 3.99\% for $L_{2/3}$-FBE-WCIE, while providing approximately 5.5- and 12.1-fold speedups over the two baselines, respectively. Supplementary 2-D comparisons further confirm its stability and computational efficiency relative to existing PDNN frameworks. CRPDNN also maintains reliable reconstruction performance under noisy measurements, and the 3-D Fresnel experiments further indicate its potential for practical imaging applications. The related code is available at https://github.com/Physics-driven-methods.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.