用于3D CBCT分割的3D CT基础模型的无监督适配
Unsupervised Adaptation of 3D CT Foundation Models for 3D CBCT Segmentation
浏览论文内容
中文总结 AI 辅助
该研究针对3D CBCT分割面临的标注数据稀缺与跨模态域偏移问题，提出基于降冗余特征对齐的无监督域适应框架，适配CNN及ViT基础模型，在肝脏分割基准上表现优于现有策略，且公开了相关资源。
中文摘要 AI 辅助
锥形束CT（CBCT）的准确3D分割对介入治疗和放射治疗应用至关重要，但仍受两个叠加挑战限制：带标注的CBCT数据稀缺，以及与诊断CT存在较大的域偏移。介入CBCT因采集方式、物理效应及特定造影剂血管内容，与常规CT存在根本模态差异，从而限制了跨模态模型的有效迁移。我们提出一种基于降冗余特征对齐的新型无监督域适应（UDA）框架，无需目标域标注或推理时适配即可实现3D CBCT分割。该框架与架构无关，可无缝适配基于CNN和ViT的基础模型。我们在两个具有挑战性的CT-CBCT肝脏分割基准上评估了该方法：一个用于介入血管手术，一个用于放射治疗，结果表明，即使是大规模预训练的分割网络也需要明确的特征空间桥接才能在不同采集模态间泛化，且我们的方法始终优于现有预训练基础模型和UDA策略。为支持可复现性和基准测试，我们发布了公开CBCT数据集的肝脏分割结果，以及代码、训练模型和权重。
英文摘要
Accurate 3D segmentation of cone-beam CT (CBCT) is critical for interventional and radiation therapy applications, yet it remains limited by two compounding challenges: the scarcity of annotated CBCT data and the large domain shift from diagnostic CT. Interventional CBCT exhibits fundamental modality differences from conventional CT, driven by acquisition and physics effects as well as contrast-specific vascular content, thereby limiting effective cross-modality model transfer. We propose a novel unsupervised domain adaptation (UDA) framework based on redundancy-reducing feature alignment, enabling 3D CBCT segmentation with no target-domain annotations or inference-time adaptation. Our framework is architecture-agnostic, seamlessly adapting both CNN-based and ViT-based foundation models. We evaluate our method on two challenging CT-CBCT liver segmentation benchmarks: one for interventional vascular procedures and one for radiation therapy, demonstrating that even large-scale pretrained segmentation networks require explicit feature-space bridging to generalize across acquisition modalities, and that our approach consistently outperforms existing pretrained foundation model and UDA strategies. To support reproducibility and benchmarking, we release the liver segmentations for a public CBCT dataset, along with the code, trained models, and weights.
发表机构
- LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎综合理工学院电信学院LTCI研究所）
- GE HealthCare（GE医疗）
机构由 AI 辅助整理，请以论文原文为准。
