文献速递腹部技术与安全CT

基于腹部计算机断层扫描的胆囊癌深度学习分割:一项多中心研究

Deep learning-based segmentation of gallbladder cancer on abdominal computed tomography scans: a multicenter study.
PubMed 文献 · Abdom Radiol (NY) · 2025-04-01

本回顾性多中心研究训练并验证了多种2D和3D深度学习模型,用于在增强CT图像上自动分割胆囊癌病灶,以手动分割为参考标准。2D模型表现优于3D模型,其中MedSAM在内外部测试集上获得最高Dice和IoU评分。分割性能与胆囊癌形态无关,与病灶大小的相关性弱。

要点

  • 2D分割模型整体优于3D模型,MedSAM表现最佳。
  • MedSAM内部测试集平均Dice为0.776,外部测试集为0.763。
  • 分割性能与胆囊癌形态无关,与病灶大小相关性弱。

核心结论

  • 在大型数据集上训练的2D和3D胆囊癌分割模型中,基于提示的2D基础模型MedSAM分割性能最佳,并在外部数据集上得到验证。

研究设计与样本

  • 回顾性研究,纳入四家三级转诊医院经病理证实的初治胆囊癌连续患者;训练与验证队列来自中心1的317例患者,内部测试集为中心1时间独立的29例,外部测试集来自三个中心的85例;参考标准为手动分割;评估指标为Dice评分和交并比(IoU)。

诊断标准与关键数值

  • MedSAM内部测试集平均Dice(标准差)0.776(0.106),平均IoU 0.653(0.133)。
  • MedSAM外部测试集平均Dice(标准差)0.763(0.098),平均IoU 0.637(0.116)。
  • 3D模型中TransUNet表现最佳,内部测试集平均Dice(标准差)0.479(0.268)、IoU(标准差)0.356(0.235),外部测试集平均Dice(标准差)0.409(0.339)、IoU(标准差)0.317(0.283)。

局限性

  • 原文未报告局限性。

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

OBJECTIVES: To train and validate segmentation models for automated segmentation of gallbladder cancer (GBC) lesions from contrast-enhanced CT images.

MATERIALS AND METHODS: This retrospective study comprised consecutive patients with pathologically proven treatment naïve GBC who underwent a contrast-enhanced CT scan at four different tertiary care referral hospitals. The training and validation cohort comprised CT scans of 317 patients (center 1). The internal test cohort comprised a temporally independent cohort (n = 29) from center 1 (internal test 1). The external test cohort comprised CT scans from three centers [ (n = 85)]. We trained the state-of-the-art 2D and 3D image segmentation models, SAM Adapter, MedSAM, 3D TransUNet, SAM-Med3D, and 3D-nnU-Net, for automated segmentation of the GBC. The models' performance for GBC segmentation on the test datasets was assessed via dice score and intersection over union (IoU) using manual segmentation as the reference standard.

RESULTS: The 2D models performed better than 3D models. Overall, MedSAM achieved the highest dice and IoU scores on both the internal [mean dice (SD) 0.776 (0.106) and mean IoU 0.653 (0.133)] and external [mean dice (SD) 0.763 (0.098) and mean IoU 0.637 (0.116)] test sets. Among the 3D models, TransUNet showed the best segmentation performance with mean dice (SD) and IoU (SD) of 0.479 (0.268) and 0.356 (0.235) in the internal test and 0.409 (0.339) and 0.317 (0.283) in the external test sets. The segmentation performance was not associated with GBC morphology. There was weak correlation between the dice/IoU and the size of the GBC lesions for any segmentation model.

CONCLUSION: We trained 2D and 3D GBC segmentation models on a large dataset and validated these models on external datasets. MedSAM, a 2D prompt-based foundational model, achieved the best segmentation performance.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Gupta P, Dutta N, Tomar A, et al. Deep learning-based segmentation of gallbladder cancer on abdominal computed tomography scans: a multicenter study. Abdom Radiol (NY). 2025. PMID: 40167645. doi:10.1007/s00261-025-04887-y

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。