LiT-WSAG:2D训练联合3D重建的高精度肝脏肿瘤分割框架
针对CT肝脏肿瘤分割中三维标注成本高、计算负担大的问题,提出LiT-WSAG框架。该框架基于SAM-Med2D,结合小波引导双尺度通道适配器、L2.5D邻域融合及渐进GAN训练,仅用二维监督重建体素级三维分割。在LiTS数据集中切面DSC为89.74%、体积DSC为69.27%,在WAW-TACE数据集中分别为96.08%和82.03%。
要点
- LiT-WSAG仅用二维标注即可生成三维肝脏肿瘤分割,降低标注与计算成本。
- 在LiTS数据集中,体积DSC较SAM-Med2D提升33.64个百分点,达69.27%。
- 框架强调边界一致性与噪声鲁棒性,在低对比度CT中表现稳健。
核心结论
- LiT-WSAG能够从纯二维监督中重建体素级三维肝脏肿瘤分割,在边界准确性、噪声鲁棒性与计算效率之间取得平衡。
- 在LiTS与WAW-TACE数据集上,LiT-WSAG的切面DSC和体积DSC均显著高于SAM-Med2D基线。
研究设计与样本
- 研究类型为方法学实验研究,基座模型为SAM-Med2D,使用二维切面标注进行训练。
- 在LiTS、WAW-TACE及Synapse多器官数据集上验证,参考指标为Dice相似系数。
关键影像表现/征象
- LiT-WSAG通过小波解耦低频与高频内容,增强多尺度特征表达以改善肿瘤边界分割。
- L2.5D邻域融合在近二维计算成本下恢复层间上下文,减少层间不一致性。
- 渐进权重GAN训练用于约束三维形状与边界的一致性,提高分割连续性与抗噪能力。
诊断标准与关键数值
- LiTS数据集中,LiT-WSAG切面DSC为89.74%,体积DSC为69.27%,体积DSC较SAM-Med2D提升33.64个百分点。
- LiTS数据集中,切面DSC较SAM-Med2D提升8.85个百分点。
- WAW-TACE数据集中,LiT-WSAG切面DSC为96.08%,体积DSC为82.03%。
- Synapse多器官数据集中,LiT-WSAG平均DSC为88.23%。
临床应用与阅片要点
- 二维监督训练可降低三维肝脏肿瘤分割的标注门槛,提高临床部署可行性。
- 当CT图像边界弱、对比度低时,模型可在保持计算效率前提下仍取得较高分割性能。
局限性
- 原文未报告外部真实世界前瞻性验证,且数据集和基线比较范围受限于所纳入数据集。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Liver cancer remains a major cause of cancer mortality, and precise CT-based liver tumor segmentation is critical for early diagnosis and personalized treatment. In practice, fully 3D‑supervised training is limited by prohibitive annotation costs and memory and compute demands. Achieving 3D segmentation from purely 2D supervision is attractive yet challenging due to through-plane context loss, inter‑slice inconsistency, weak boundaries, and low contrast and noise. We propose LiT‑WSAG, a 2D‑trained framework that reconstructs voxel‑wise 3D masks. Built upon SAM‑Med2D, it incorporates a wavelet‑guided dual‑scale channel adapter (WDSC‑Adapter) to decouple low- and high-frequency content and enhance multi-scale representations, a lightweight L2.5D neighborhood fusion to recover through‑plane context at near‑2D cost, and adversarial training with a ramped GAN weight ('mean-loss' scheduling) to enforce shape and boundary consistency. Extensive experiments demonstrate significant gains over the baseline across multiple datasets. On the LiTS dataset, LiT‑WSAG achieves slice‑wise and volumetric DSC of 89.74% and 69.27% (+ 8.85 and + 33.64 percentage points over SAM-Med2D); on the WAW‑TACE dataset, the corresponding scores are 96.08% and 82.03%. Furthermore, on the Synapse multi-organ dataset, it attains a state-of-the-art average DSC of 88.23%. These results indicate that LiT‑WSAG delivers robust 3D liver tumor segmentation from 2D supervision, balancing boundary accuracy, noise robustness, and computational efficiency.
引用
- Yi, Li, Cao, et al. LiT-WSAG: high-precision 3D liver tumor segmentation via 2D training and 3D reconstruction. Radiol Med. 2026. PMID: 42406310. doi:10.1007/s11547-026-02247-4
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。