患者内三维可变形多模态图像配准基准测试
Benchmarking Intra-Patient 3D Deformable Multimodal Image Registration
浏览论文内容
中文总结 AI 辅助
本研究提出了一个患者内三维多模态可变形配准基准,评估多种方法,发现学习法在合成数据上表现优异但真实场景提升有限,且几何与图像相似性指标不一致,表明该问题仍需多标准评估。
中文摘要 AI 辅助
多模态图像配准是许多临床工作流程中的关键组成部分,但由于不同模态下对应的解剖结构往往表现出显著不同的图像强度,其仍然具有挑战性。在本工作中,我们提出了一个全面的患者内三维多模态可变形配准方法基准测试,涵盖三个数据集,涉及不同的解剖区域和难度级别,包括合成形变恢复和真实临床场景。我们评估了经典的基于优化的方法和现代的基于学习的方法,包括最近的深度学习和基础模型,使用互补的指标:平均Dice相似系数(DSC)、平均第95百分位Hausdorff距离(HD95)以及基于MIND自相似性上下文(MIND-SSC)的模态无关结构相似性度量。结果显示不同数据集间存在高度变异性,基于学习的方法在大型合成基准上表现出优越性能,而在真实盆腔配准中仅观察到有限的改进。本研究的一个关键发现是几何指标(DSC、HD95)与基于图像的相似性指标(MIND-SSC)之间存在持续的不一致,突显了改善的重叠并不一定意味着更好的全局多模态对应。此外,解剖引导的方法实现了最高的重叠分数,但在分割区域之外表现出性能下降,揭示了标签驱动对齐与全局结构一致性之间的权衡。总体而言,我们的结果表明,目前没有方法能在不同解剖结构和模态间实现稳健性能。我们证明,患者内三维多模态配准需要多标准评估,包括基于形变的指标,并且仍然是一个开放性问题。
英文摘要
Multimodal image registration is a key component of many clinical workflows, yet it remains challenging because corresponding anatomical structures often exhibit substantially different image intensities across modalities. In this work, we present a comprehensive benchmark of intra-patient 3D multimodal deformable registration methods across three datasets covering different anatomical regions and difficulty levels, including both synthetic deformation recovery and real clinical scenarios. We evaluate classical optimization-based approaches and modern learning-based methods, including recent deep learning and foundation models, using complementary metrics: Average Dice similarity coefficient (DSC), average 95th-percentile Hausdorff distance (HD95), and a modality-independent structural similarity measure based on the MIND self-similarity context (MIND-SSC). Results show high variability across datasets, with learning-based methods demonstrating superior performance on large synthetic benchmarks, while only limited improvements are observed in real pelvic registration. A key finding of this study is the consistent disagreement between geometric metrics (DSC, HD95) and image-based similarity metrics (MIND-SSC), highlighting that improved overlap does not necessarily imply better global multimodal correspondence. Furthermore, anatomy-guided approaches achieve the highest overlap scores but exhibit degraded performance outside of segmented regions, revealing a trade-off between label-driven alignment and global structural coherence. Overall, our results indicate that no current method achieves robust performance across anatomies and modalities. We demonstrate that intra-patient 3D multimodal registration requires multi-criteria evaluation, including deformation-based metrics, and remains an open problem.
发表机构
- IMAG2, Institut IMAGINE, Université Paris Cité(IMAG2,IMAGINE研究所,巴黎西岱大学)
- Replico SAS(Replico公司)
- Université Paris Cité, Department of Pediatric Surgery, Hôpital Necker Enfants-Malades, Assistance Publique–Hôpitaux de Paris (AP-HP)(巴黎西岱大学,内克尔儿童医院小儿外科,巴黎公立医院集团)
- Sorbonne Université, CNRS, LIP6(索邦大学,法国国家科学研究中心,LIP6)
- LTCI, Télécom Paris, Institut Polytechnique de Paris(LTCI,巴黎电信,巴黎综合理工学院)
机构由 AI 辅助整理,请以论文原文为准。