Problem
Research questions and friction points this paper is trying to address.
Cross-Modal PET Attenuation Correction
Pseudo-CT Synthesis
NAC-PET
DIXON MRI
Region-Weighted Losses and Model Fusion for Cross-Modal PET Attenuation Correction
🤖 AI Summary
研究通过区域加权损失和模型融合方法，改进了基于NAC-PET、DIXON MRI及topogram生成伪CT的3D U-Net基线模型，提高了PET衰减校正效果。
📝 Abstract
We describe our approach to the Big Cross-Modal Attenuation Correction (BIC-MAC) challenge, which asks for a pseudo-CT in Hounsfield Units to be synthesized from Non-Attenuation-Corrected PET (NAC-PET), DIXON MRI and a topogram, and scores both the pseudo-CT and the Attenuation-Corrected PET (AC-PET) reconstructed from it. Three ideas carried our improvements over the organizers' 3D U-Net baseline. The loss matters more than the architecture: we compute the $L_1$ error in the Carney attenuation-coefficient ($μ$) space that the CT metric itself uses, weighted by anatomical region. Only once that loss was in place did the unregistered DIXON MRI work as extra input channels. A fixed convex combination of two independently trained models then beat both of its members on three of the four metrics and ranks first overall on the public validation leaderboard.
Innovation
Methods, ideas, or system contributions that make the work stand out.
region-weighted loss
model fusion
cross-modal PET attenuation correction
🔎 Similar Papers
