Researchers have developed JSolver, a novel framework for multi-material decomposition (MMD) using single-energy CT (SECT) projections. Unlike traditional methods that require spectral CT scanners, JSolver jointly reconstructs material compositions and estimates the X-ray energy spectrum in a single step. This approach mitigates artifacts from conventional two-step processes and improves decomposition accuracy. The framework utilizes implicit neural representations (INRs) as an unsupervised deep learning solver, enhancing estimation quality through inductive bias towards continuous image patterns. Experiments demonstrate JSolver's superior accuracy and computational efficiency compared to existing SEMMD methods. AI
IMPACT This new method could improve the accuracy and efficiency of medical imaging analysis by enabling multi-material decomposition from standard CT scans.
RANK_REASON The item is an arXiv preprint detailing a new computational method. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
