TransNSNet: A Transformer-Enhanced Multi-Scale Adversarial Framework for CT-to-PET Image Synthesis

Shaojun Li; Xiaoyu Deng; Ikuo Keshi

Home/Archive/arXiv

arXiv · 2610.23325

TransNSNet: A Transformer-Enhanced Multi-Scale Adversarial Framework for CT-to-PET Image Synthesis

Shaojun Li·Xiaoyu Deng·Ikuo Keshi

View original source ↗Read source document ↗Export metadata ↓

Abstract

This study investigates CT-to-PET image synthesis using TransNSNet, a Transformer-enhanced multi-scale adversarial framework. A paired CT-PET dataset was curated from the public non-small cell lung cancer (NSCLC) Radiogenomics collection through patient screening, slice-level matching, preprocessing, and patient-level train-test separation. The proposed framework generates PET-like predictions at multiple spatial scales and applies coarse-to-fine reconstruction supervision, while TransPatchGAN introduces contextual feature interaction into adversarial evaluation. A progressive ablation study compares Pix2Pix, NSNet-Base, NSNet-D, and TransNSNet. Image-level performance was summarized over a fixed convergence window (epochs 80-101) from one training run per model. TransNSNet achieved the best mean value in nine of ten metrics, whereas NSNet-Base achieved the highest visual saliency-induced index. For fixed-fraction high-intensity regions, NSNet-D was marginally higher in slice-level recall and balanced accuracy, but the equal-weight patient-level values were nearly identical and the highest Dice values shifted to TransNSNet. These differences were small relative to between-patient variability. In the separate adaptive patient-level analysis (n=10), no pairwise model difference remained statistically significant after Holm correction. TransNSNet also had a substantially smaller parameter footprint than the original next-scale models. These findings indicate promising image-quality trends, but they do not establish statistical superiority or clinical validity; synthesized PET-like images should not be interpreted as substitutes for clinically acquired PET.

Explore related subjects

eess.IV cs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Shaojun Li, Xiaoyu Deng, Ikuo Keshi. 2026-10-16. TransNSNet: A Transformer-Enhanced Multi-Scale Adversarial Framework for CT-to-PET Image Synthesis. https://arxiv.org/abs/2610.23325

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction

As a critical modality for structural biology, cryogenic electron microscopy (cryo-EM) facilitates the determination of macromolecular structures at near-atomic resolution. The core computational task in single-particle cryo-EM is to reconstruct the 3D electrostatic potential of a molecule from noisy 2D projections acquired at unknown orientations. Gaussian mixture models (GMMs) provide a continuous, compact, and physically interpretable representation for molecular density and have recently gained interest in cryo-EM reconstruction. However, existing methods rely on external consensus maps or atomic models for initialization, limiting their use in self-contained pipelines. In parallel, differentiable rendering techniques such as Gaussian splatting have demonstrated remarkable scalability and efficiency for volumetric representations, suggesting a natural fit for GMM-based cryo-EM reconstruction. However, off-the-shelf Gaussian splatting methods are designed for photorealistic view synthesis and remain incompatible with cryo-EM due to mismatches in the image formation physics, reconstruction objectives, and coordinate systems. Addressing these issues, we propose cryoSplat, a GMM-based method that integrates Gaussian splatting with the physics of cryo-EM image formation. In particular, we develop an orthogonal projection-aware Gaussian splatting, with adaptations such as a view-dependent normalization term and FFT-aligned coordinate system tailored for cryo-EM imaging. These innovations enable stable and efficient homogeneous reconstruction directly from raw cryo-EM particle images using random initialization. Experimental results on real datasets validate the effectiveness and robustness of cryoSplat over representative baselines. The code will be released at https://github.com/Chen-Suyi/cryosplat.

eess.IV↗

arXiv2026

Image Moment Estimation for Crowded Datasets

Single-particle cryogenic electron microscopy (cryo-EM) is an imaging technique capable of reconstructing high-resolution three-dimensional (3D) structure of biological macromolecules from a set of noisy projection images taken at random viewing directions. The mathematical model for cryo-EM images typically assumes that each image contains exactly one particle, which is centered at the origin. However, many experimental datasets contain particle images which include multiple particles: one central particle and a few crowding particles. This deviation from the model leads to inaccurate estimation of image statistics, such as the low-order image moments. To account for this, we propose a method to estimate image moments while correcting for the effect of crowding particles. This method can be run directly from a set of cryo-EM micrographs with picked particles, and we demonstrate its efficacy on a wide array of synthetic data.

eess.IV↗

arXiv2026

Measurement-Adaptive Light-Cone Transform for Robust Non-Line-of-Sight Imaging

Practical non-line-of-sight (NLOS) measurements are affected by noise and deviations from idealized light transport, which can degrade reconstruction with conventional light-cone transform (LCT) methods. We propose the Measurement-Adaptive Light-Cone Transform (MALCT), a physics-guided framework that retains the efficient Fourier-domain inversion structure of LCT. {Within a unified variational formulation, MALCT combines the analytical response with a shared learned response through measurement-conditioned weighting and predicts a measurement-conditioned, frequency-dependent regularization map.} An attention-enhanced spatio-temporal feature extraction module captures long-range temporal dependencies and local spatial correlations to support reconstruction under low-signal conditions. Experiments on synthetic data and real measurements from different NLOS systems demonstrate improved reconstruction quality. Controlled evaluations further assess robustness to temporal-response broadening and reduced acquisition time. MALCT also preserves scene structures with spatial sampling grids down to $32\times32$, supporting its potential for NLOS imaging under limited acquisition budgets.

eess.IV↗