文献速递骨肌技术与安全CT

椎体压缩性骨折与骨密度:CT 图像上的自动检测与分类

Vertebral Body Compression Fractures and Bone Density: Automated Detection and Classification on CT Images.
PubMed 文献 · Radiology · 2017-03-16

本回顾性研究纳入150例患者(75例有压缩性骨折、75例对照),采用全自动脊柱分割与骨折检测原型软件分析CT图像。系统检测或定位压缩性骨折的敏感度为95.7%(201/210,95%CI:87.0%,98.9%),每例患者假阳性率0.29;基于病例的ROC分析敏感度98.7%、特异度77.3%;Genant分型准确率0.95(107/113,95%CI:0.89,0.98),加权κ=0.90(95%CI:0.81,0.99);Genant高度丢失分级分类准确率0.68(77/113,95%CI:0.59,0.76),加权κ=0.59(95%CI:0.47,0.71)。病例组T12-L4椎体平均骨密度为146 HU±29,对照组为173 HU±42,差异有统计学意义(P<.001)。

要点

  • 自动系统检测或定位椎体压缩性骨折敏感度95.7%(201/210),每例假阳性0.29。
  • Genant分型(前、中、后高度丢失)准确率0.95(107/113),加权κ=0.90。
  • Genant高度丢失分级分类准确率0.68(77/113),加权κ=0.59。

核心结论

  • 研究创建了自动机器学习计算机系统,可在CT图像上以高敏感度和低假阳性率检测、解剖定位并分类椎体压缩性骨折,同时计算椎体骨密度。

研究设计与样本

  • 经机构审查委员会批准、豁免知情同意、符合HIPAA的回顾性研究。
  • 纳入150例患者(平均年龄73岁,范围55-96岁;92例女性、58例男性),其中75例有压缩性骨折、75例无骨折,病例与对照按年龄和性别匹配。
  • 由放射科医师对210个胸椎和腰椎压缩性骨折椎体进行电子标记和分类,作为参考标准。
  • 采用全自动脊柱分割与骨折检测原型软件分析研究集,以自由响应受试者工作特征分析评价系统性能。

关键影像表现/征象

  • 系统检测或定位压缩性骨折的敏感度为95.7%(201/210;95%CI:87.0%,98.9%),每例患者假阳性率为0.29。
  • 基于病例的ROC曲线分析敏感度为98.7%、特异度为77.3%。
  • 病例组T12-L4椎体平均骨密度为146 HU±29,对照组为173 HU±42,差异有统计学意义(P<.001)。

诊断标准与关键数值

  • Genant分型(前、中或后高度丢失)准确率为0.95(107/113;95%CI:0.89,0.98),加权κ为0.90(95%CI:0.81,0.99)。
  • Genant高度丢失分级分类准确率为0.68(77/113;95%CI:0.59,0.76),加权κ为0.59(95%CI:0.47,0.71)。

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

Purpose To create and validate a computer system with which to detect, localize, and classify compression fractures and measure bone density of thoracic and lumbar vertebral bodies on computed tomographic (CT) images. Materials and Methods Institutional review board approval was obtained, and informed consent was waived in this HIPAA-compliant retrospective study. A CT study set of 150 patients (mean age, 73 years; age range, 55-96 years; 92 women, 58 men) with (n = 75) and without (n = 75) compression fractures was assembled. All case patients were age and sex matched with control subjects. A total of 210 thoracic and lumbar vertebrae showed compression fractures and were electronically marked and classified by a radiologist. Prototype fully automated spinal segmentation and fracture detection software were then used to analyze the study set. System performance was evaluated with free-response receiver operating characteristic analysis. Results Sensitivity for detection or localization of compression fractures was 95.7% (201 of 210; 95% confidence interval [CI]: 87.0%, 98.9%), with a false-positive rate of 0.29 per patient. Additionally, sensitivity was 98.7% and specificity was 77.3% at case-based receiver operating characteristic curve analysis. Accuracy for classification by Genant type (anterior, middle, or posterior height loss) was 0.95 (107 of 113; 95% CI: 0.89, 0.98), with weighted κ of 0.90 (95% CI: 0.81, 0.99). Accuracy for categorization by Genant height loss grade was 0.68 (77 of 113; 95% CI: 0.59, 0.76), with a weighted κ of 0.59 (95% CI: 0.47, 0.71). The average bone attenuation for T12-L4 vertebrae was 146 HU ± 29 (standard deviation) in case patients and 173 HU ± 42 in control patients; this difference was statistically significant (P < .001). Conclusion An automated machine learning computer system was created to detect, anatomically localize, and categorize vertebral compression fractures at high sensitivity and with a low false-positive rate, as well as to calculate vertebral bone density, on CT images. © RSNA, 2017 Online supplemental material is available for this article.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Burns JE, Yao J, Summers RM, et al. Vertebral Body Compression Fractures and Bone Density: Automated Detection and Classification on CT Images. Radiology. 2017. PMID: 28301777. doi:10.1148/radiol.2017162100

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。