用3D子体积融合提升MRI转CT的精度与效率
Enhancing Cross-Modality Synthesis: Subvolume Merging for MRI-to-CT Conversion
- 采用SwinUNETR框架，通过3D子体积拼接生成CT图像
- 重叠率50%-70%时MAE降至47.75 HU，比原方法降低4.9 HU
- 引入γ=0.9的加权函数，优化拼接质量，适合医学影像转换
从磁共振成像（MRI）生成合成计算机断层扫描（sCT）可提供更精确的组织衰减信息，从而改善放疗计划。本研究采用先进的SwinUNETR框架实现MRI到CT的转换，并在预测过程中引入三维子体积融合技术。通过选择最优重叠率，有效缓解了拼接伪影，使sCT与真实标签之间的平均绝对误差（MAE）从52.65 HU降至47.75 HU。此外，在相同重叠区域内，采用伽马值为0.9的加权函数可获得最低的MAE。将子体积重叠率设定在50%至70%之间，可在图像质量与计算效率间取得良好平衡。
原文摘要 · Abstract (English)
Providing more precise tissue attenuation information, synthetic computed tomography (sCT) generated from magnetic resonance imaging (MRI) contributes to improved radiation therapy treatment planning. In our study, we employ the advanced SwinUNETR framework for synthesizing CT from MRI images. Additionally, we introduce a three-dimensional subvolume merging technique in the prediction process. By selecting an optimal overlap percentage for adjacent subvolumes, stitching artifacts are effectively mitigated, leading to a decrease in the mean absolute error (MAE) between sCT and the labels from 52.65 HU to 47.75 HU. Furthermore, implementing a weight function with a gamma value of 0.9 results in the lowest MAE within the same overlap area. By setting the overlap percentage between 50% and 70%, we achieve a balance between image quality and computational efficiency.
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。