通过梯度相关优化，提升脑部MRI配准的稳定性与解剖一致性。
Fine-Tuning TransMorph with Gradient Correlation for Anatomical Alignment
- 在相似性度量中引入梯度相关，增强结构变化的一致性。
- 相比基线模型，NDV降低显著，Dice和HdDist95略有提升。
- 适合需要高精度、平滑变形的跨患者脑MRI配准任务。
无监督深度学习在脑部MRI配准中具有潜力，可减少对解剖标签的依赖，同时实现精确的解剖对齐。针对Learn2Reg2024 LUMIR挑战，我们提出对预训练的TransMorph模型进行微调，以提升收敛稳定性与形变平滑性。前者通过FAdam优化器实现，后者通过在相似性度量中加入梯度相关项来增强结构变化的一致性，从而改善解剖对齐效果。结果表明，本方法在Dice和HdDist95指标上略有提升，且NDV（非重叠体积差）显著降低，边界检查也验证了其优势。该方法证明了引入梯度相关对实现更平滑、结构一致的形变的有效性，适用于跨患者脑部MRI配准。
原文摘要 · Abstract (English)
Unsupervised deep learning is a promising method in brain MRI registration to reduce the reliance on anatomical labels, while still achieving anatomically accurate transformations. For the Learn2Reg2024 LUMIR challenge, we propose fine-tuning of the pre-trained TransMorph model to improve the convergence stability as well as the deformation smoothness. The former is achieved through the FAdam optimizer, and consistency in structural changes is incorporated through the addition of gradient correlation in the similarity measure, improving anatomical alignment. The results show slight improvements in the Dice and HdDist95 scores, and a notable reduction in the NDV compared to the baseline TransMorph model. These are also confirmed by inspecting the boundaries of the tissue. Our proposed method highlights the effectiveness of including Gradient Correlation to achieve smoother and structurally consistent deformations for interpatient brain MRI registration.
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。