文献速递腹部泌尿生殖外周血管CT

使用深度学习模型在平扫CT图像上分割肾血管

Segmentation of renal vessels on non-enhanced CT images using deep learning models.
PubMed 文献 · Abdom Radiol (NY) · 2025-05-13

本研究纳入177例患者的平扫、动脉期和静脉期CT,按120/20/37分为训练集、验证集和测试集;训练深度学习模型在平扫CT上分割右肾动静脉,以动静脉期为参考标准,并与放射科医生在无对比期参考下的重建结果比较。模型与医生识别动静脉主干的准确率无显著差异,但模型识别副动脉的准确率显著低于医生(44.4% vs 77.8%,p=0.044)。

要点

  • 模型识别右肾动脉主干准确率97.3%,静脉主干91.9%,与医生无显著差异。
  • 模型识别副动脉准确率44.4%,显著低于医生的77.8%(p=0.044)。
  • 模型识别副静脉准确率64.3%,低于医生的85.7%,但差异不显著(p=0.094)。

核心结论

  • 深度学习模型能准确识别右肾动脉和静脉主干,准确率与放射科医生相当;但当前模型识别小的副血管仍有困难,进一步训练和模型优化有望解决这些问题。

研究设计与样本

  • 研究纳入177例患者的平扫期、动脉期和静脉期CT扫描,随机分为训练集(n=120)、验证集(n=20)和测试集(n=37);由放射科医生以对比期图像为参考在平扫CT上标记右肾动脉和静脉,训练深度学习模型并在测试集上评估,同时与放射科医生在无对比期参考下的肾血管重建结果比较,以动脉期和静脉期重建作为金标准。

诊断标准与关键数值

  • 无对比期参考时,模型与放射科医生识别动脉主干的准确率分别为97.3%和91.9%,差异不显著。
  • 无对比期参考时,模型与放射科医生识别静脉主干的准确率分别为91.9%和100%,差异不显著。
  • 模型与放射科医生识别副动脉的准确率分别为44.4%和77.8%,模型显著低于医生(p=0.044)。
  • 模型与放射科医生识别副静脉的准确率分别为64.3%和85.7%,差异不显著(p=0.094)。

临床应用与阅片要点

  • 作者指出,深度学习模型在平扫CT上识别右肾动静脉主干方面与放射科医生准确率相当。
  • 作者指出,当前模型识别小的副血管仍有困难,进一步训练和模型优化有望解决这些问题。

局限性

  • 当前模型识别小的副血管仍有困难。

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

OBJECTIVE: To evaluate the possibility of performing renal vessel reconstruction on non-enhanced CT images using deep learning models.

MATERIALS AND METHODS: 177 patients' CT scans in the non-enhanced phase, arterial phase and venous phase were chosen. These data were randomly divided into the training set (n = 120), validation set (n = 20) and test set (n = 37). In training set and validation set, a radiologist marked out the right renal arteries and veins on non-enhanced CT phase images using contrast phases as references. Trained deep learning models were tested and evaluated on the test set. A radiologist performed renal vessel reconstruction on the test set without the contrast phase reference, and the results were used for comparison. Reconstruction using the arterial phase and venous phase was used as the gold standard.

RESULTS: Without the contrast phase reference, both radiologist and model could accurately identify artery and vein main trunk. The accuracy was 91.9% vs. 97.3% (model vs. radiologist) in artery and 91.9% vs. 100% in vein, the difference was insignificant. The model had difficulty identify accessory arteries, the accuracy was significantly lower than radiologist (44.4% vs. 77.8%, p = 0.044). The model also had lower accuracy in accessory veins, but the difference was insignificant (64.3% vs. 85.7%, p = 0.094).

CONCLUSION: Deep learning models could accurately recognize the right renal artery and vein main trunk, and accuracy was comparable to that of radiologists. Although the current model still had difficulty recognizing small accessory vessels, further training and model optimization would solve these problems.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Zhong H, Zhao Y, Zhang Y, et al. Segmentation of renal vessels on non-enhanced CT images using deep learning models. Abdom Radiol (NY). 2025. PMID: 40358703. doi:10.1007/s00261-025-04984-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。