用区域加权损失提升跨模态PET衰减校正精度
Region-Weighted Losses and Model Fusion for Cross-Modal PET Attenuation Correction
- 在衰减系数空间计算加权L1损失，按解剖区域调整误差权重
- 融合两个独立训练模型，使伪CT和校正后PET质量显著提升
- 适合医学影像重建、多模态图像融合方向的研究者
我们针对大跨模态衰减校正挑战（BIC-MAC），提出从非衰减校正PET（NAC-PET）、DIXON MRI和顶图合成以豪斯菲尔德单位表示的伪CT，并评估伪CT及其生成的衰减校正PET（AC-PET）。相较于组织者提供的3D U-Net基线，三个关键改进带来性能提升：损失函数比网络结构更重要——在卡尼衰减系数（μ）空间中计算加权L1误差，按解剖区域分配权重；仅当该损失建立后，未配准的DIXON MRI才能作为额外输入通道有效使用；最后，采用固定凸组合方式融合两个独立训练模型，在四个指标中的三个超越单个模型，整体排名位列公开验证排行榜首位。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。