融合全局语义与局部特征，提升医学图像配准的鲁棒性
GLIDE-Reg: Global-to-Local Deformable Registration Using Co-Optimized Foundation and Handcrafted Features
- 联合优化配准场与可学习降维模块，保留压缩嵌入的配准相关性
- 在3个数据集上平均骰子系数达0.859~0.901，优于当前最优方法
- 对结节中心定位精准，适合肺癌早期诊断等挑战性下游任务
变形配准在医学影像中至关重要，广泛应用于病灶追踪、概率模板构建和治疗反应评估。然而，现有方法在空间分辨率差异和解剖覆盖范围不一致时普遍缺乏鲁棒性和泛化能力。本文提出联合优化配准场与可学习降维模块，确保压缩后的体积特征映射（VFM）嵌入仍具备配准相关性，并将这些全局语义线索与MIND局部描述符融合。GLIDE-Reg在两个公开队列（Lung250M和NLST）及一个机构队列（UCLA5DCT）上，对6个解剖结构的平均骰子相似系数（DSC）分别达到0.859、0.862和0.901，优于当前最优的DEEDS方法（0.834、0.858、0.900），相对提升分别为3.0%、0.5%和0.1%。目标配准误差方面，其在Lung250M数据集上的地标误差为1.58 mm（corrField为1.25 mm，DEEDS为1.91 mm），在NLST结节中心误差为1.11 mm（与DEEDS持平）。在结节中心定位上的优异表现，验证了其在结节追踪等关键下游任务中的鲁棒性，是早期肺癌诊断的重要前置步骤。
原文摘要 · Abstract (English)
Deformable registration is crucial in medical imaging. Several existing applications include lesion tracking, probabilistic atlas generation, and treatment response evaluation. However, current methods often lack robustness and generalizability across two key factors: spatial resolution and differences in anatomical coverage. We jointly optimize a registration field and a learnable dimensionality reduction module so that compressed VFM embeddings remain registration-relevant, and fuse these global semantic cues with MIND local descriptors. GLIDE-Reg achieves average dice similarity coefficients (DSC) across 6 anatomical structures of 0.859, 0.862, and 0.901 in two public cohorts (Lung250M and NLST) and one institution cohort (UCLA5DCT), and outperforms the state-of-the-art DEEDS (0.834, 0.858, 0.900) with relative improvements of 3.0%, 0.5%, and 0.1%. For target registration errors, GLIDE-Reg achieves 1.58 mm on Lung250M landmarks (compared to 1.25 mm on corrField and 1.91 mm on DEEDS) and 1.11 mm on NLST nodule centers (compared to 1.11 mm on DEEDS). The substantiated performance on the nodule centers also demonstrates its robustness across challenging downstream tasks, such as nodule tracking, which is an essential prior step for early-stage lung cancer diagnosis.
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。