VoxelSynth3D: Interpretable Volumetric Image-Domain Metal Artifact Reduction with a Paired Synthetic CLINIC-Metal Benchmark

2026-10-01

AI Summary

This study addresses the severe obscuration of bone-implant interfaces by metal artifacts in postoperative CT, a challenge for which existing methods typically require raw projection data or exhibit limited generalizability. We propose the first training-free, three-dimensional image-domain metal artifact reduction (MAR) framework that integrates support masking, normalized tissue synthesis, bias gating, and constrained edge refinement to achieve interpretable optimization of local structural trade-offs. Additionally, we construct a controlled paired synthetic benchmark for systematic evaluation. Across 40 test cases, our method reduces the root mean square error (RMSE) by 15.30 HU, yielding improvements on every sample and outperforming a Gaussian smoothing baseline (13.58 HU). These results establish an efficient and reliable new paradigm for clinical MAR.

Abstract

Metal artifacts in postoperative musculoskeletal CT obscure bone-implant and adjacent soft-tissue interfaces. Many metal artifact reduction (MAR) methods require unavailable raw projections or learned models that may shift across scanners and implants. We present VoxelSynth3D, a training-free 3D image-domain framework for reconstructed CT. The framework combines support masking, normalized tissue synthesis, deviation gating, and restricted edge refinement. Detected implant voxels are preserved in the output, while correction targets metal-induced artifacts in the surrounding tissue. We also construct Synthetic CLINIC-Metal, a controlled paired synthetic evaluation resource, from no-metal CTPelvic1K volumes with clean targets, metal/artifact masks, fixed seeds, and patient-level splits; 75 unpaired real metal cases receive qualitative/no-reference evaluation only. The operating point was fixed in a near-flat validation basin. With exact-mask oracle localization, all methods share a metal-excluded tissue ROI. On 40 held-out cases, VoxelSynth3D reduced RMSE from 801.48 to 786.18 HU (paired gain 15.30 HU, 95% CI 11.68-19.23), improving every case and exceeding the evaluated 3D Gaussian smoother by 13.58 HU. Clean-edge agreement decreased next to metal but exceeded input beyond 5 mm. Thus, VoxelSynth3D provides case-consistent within-distribution tissue-error reduction with a localized structural tradeoff. Spacing-aware sensitivity retained aggregate broad-region improvement and identified near-metal calibration as a target.

Problem

• Metal Artifact Reduction
• Musculoskeletal CT
• Image-domain MAR
• Implant artifacts

Innovation

• Metal Artifact Reduction
• Training-free Framework
• Image-domain Processing
• Synthetic Benchmark
• Interpretable