New splat-based method reduces metal artifacts in CT scans

Researchers have developed a novel splat-based framework for reducing metal artifacts in cone-beam CT scans. This method incorporates a physically grounded polychromatic forward model within a continuous Gaussian representation, allowing for efficient joint optimization of geometric and material properties. The framework effectively captures energy-dependent attenuation across biological tissues and metallic implants, enabling it to explain metal-induced nonlinearity while preserving fine structures. Experiments demonstrate that this approach converges faster and suppresses artifacts more effectively than existing reconstruction and neural field-based methods. AI

IMPACT This research could lead to clearer medical imaging, improving diagnostic accuracy for patients with metallic implants.

RANK_REASON The item is an academic paper detailing a new method for artifact reduction in medical imaging. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv cs.CV →

• arXiv
• computed tomography
• Cone Beam Ct
• Gaussian function
• Metallic implants

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →