文献速递腹部外周血管技术与安全CT

深度学习算法应用于平扫CT图像识别肠系膜上动脉异常

Deep learning algorithm applied to plain CT images to identify superior mesenteric artery abnormalities.
PubMed 文献 · Eur J Radiol · 2024-02-23

研究开发基于YOLOv8的深度学习模型,用于在平扫CT上检测肠系膜上动脉异常,并与临床模型和放射科医生评估进行比较。内部测试集AUC为0.990,外部测试集AUC为0.967;YOLOv8x子模型的敏感度和特异度均高于放射科医生评估。

要点

  • YOLOv8x在平扫CT上识别肠系膜上动脉异常的AUC内部测试集0.990、外部测试集0.967。
  • 与放射科医生评估相比,YOLOv8x敏感度更高(内部100.0% vs 70.7%,外部96.0% vs 68.8%)。
  • YOLOv8x特异度亦高于放射科医生评估(内部90.7% vs 66.0%,外部88.0% vs 66.0%)。

核心结论

  • 使用平扫CT图像,YOLOv8x能够有效识别肠系膜上动脉异常病例,可能提高早期诊断准确性从而改善临床结局。

研究设计与样本

  • 研究纳入1048例患者,包括内部队列(474例肠系膜上动脉异常患者和474例对照)和外部测试队列(50例肠系膜上动脉异常患者和50例对照);内部队列分为训练队列776例、验证队列86例和内部测试队列86例;开发了5个基于YOLOv8的深度学习子模型,并将最佳子模型与临床模型及经验丰富的放射科医生评估进行比较。

诊断标准与关键数值

  • YOLOv8x子模型AUC高于临床模型(内部测试集0.990 vs 0.878,P=.002;外部测试集0.967 vs 0.912,P=.140),且高于所有放射科医生(P<.001);与放射科医生评估相比,YOLOv8x敏感度更高(内部测试集100.0% vs 70.7%,P=.002;外部测试集96.0% vs 68.8%,P<.001),特异度更高(内部测试集90.7% vs 66.0%,P=.025;外部测试集88.0% vs 66.0%,P<.001)。

临床应用与阅片要点

  • 作者认为YOLOv8x可高效识别平扫CT上的肠系膜上动脉异常病例,可能提高早期诊断准确性并改善临床结局。

局限性

  • 外部测试集YOLOv8x与临床模型AUC比较P=.140,未达统计学显著。

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: Atypical presentations, lack of biomarkers, and low sensitivity of plain CT can delay the diagnosis of superior mesenteric artery (SMA) abnormalities, resulting in poor clinical outcomes. Our study aims to develop a deep learning (DL) model for detecting SMA abnormalities in plain CT and evaluate its performance in comparison with a clinical model and radiologist assessment.

MATERIALS AND METHODS: A total of 1048 patients comprised the internal (474 patients with SMA abnormalities, 474 controls) and external testing (50 patients with SMA abnormalities, 50 controls) cohorts. The internal cohort was divided into the training cohort (n = 776), validation cohort (n = 86), and internal testing cohort (n = 86). A total of 5 You Only Look Once version 8 (YOLOv8)-based DL submodels were developed, and the performance of the optimal submodel was compared with that of a clinical model and of experienced radiologists.

RESULTS: Of the submodels, YOLOv8x had the best performance. The area under the curve (AUC) of the YOLOv8x submodel was higher than that of the clinical model (internal test set: 0.990 vs 0.878, P =.002; external test set: 0.967 vs 0.912, P =.140) and that of all radiologists (P <.001). The YOLOv8x submodel, when compared with radiologist assessment, demonstrated higher sensitivity (internal test set: 100.0 % vs 70.7 %, P =.002; external test set: 96.0 % vs 68.8 %, P <.001) and specificity (internal test set: 90.7 % vs 66.0 %, P =.025; external test set: = 88.0 % vs 66.0 %, P <.001).

CONCLUSION: Using plain CT images, YOLOv8x was able to efficiently identify cases of SMA abnormalities. This could potentially improve early diagnosis accuracy and thus improve clinical outcomes.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Mei J, Yan H, Tang Z, et al. Deep learning algorithm applied to plain CT images to identify superior mesenteric artery abnormalities. Eur J Radiol. 2024. PMID: 38412582. doi:10.1016/j.ejrad.2024.111388

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。