中国组织工程研究 ›› 2020, Vol. 24 ›› Issue (30): 4841-4846.doi: 10.3969/j.issn.2095-4344.2846

• 骨与关节图像与影像 bone and joint imaging • 上一篇    下一篇

腰椎磁共振影像组学对女性骨质疏松症的诊断价值

何  丽,刘  斋,高志梅,刘春颖,赵君禄,任庆云   

  1. 河北医科大学第一医院放射科,河北省石家庄市  050031
  • 收稿日期:2020-01-10 修回日期:2020-01-16 接受日期:2020-03-06 出版日期:2020-10-28 发布日期:2020-09-19
  • 通讯作者: 任庆云,主任医师/教授,河北医科大学第一医院放射科,河北省石家庄市 050031
  • 作者简介:何丽,女,1980年生,河北省石家庄市人,汉族,2011年河北医科大学毕业,硕士,副主任医师/副教授,主要从事 MRI及CT诊断方面的研究。
  • 基金资助:
    河北省重点研究计划项目(182777126D)

Radiomics for diagnostic value of osteoporosis in female patients based on lumbar magnetic resonance imaging

He Li, Liu Zhai, Gao Zhimei, Liu Chunying, Zhao Junlu, Ren Qingyun   

  1. Department of Radiology, First Hospital of Hebei Medical University, Shijiazhuang 050031, Hebei Province, China
  • Received:2020-01-10 Revised:2020-01-16 Accepted:2020-03-06 Online:2020-10-28 Published:2020-09-19
  • Contact: Ren Qingyun, Chief physician, Professor, Department of Radiology, First Hospital of Hebei Medical University, Shijiazhuang 050031, Hebei Province, China
  • About author:He Li, Master, Associate chief physician, Associate professor, Department of Radiology, First Hospital of Hebei Medical University, Shijiazhuang 050031, Hebei Province, China
  • Supported by:
    the Key Research Plan Project of Hebei Province, No. 182777126D

摘要:

文题释义:

骨质疏松症:是一种以骨量减低、骨组织微结构损坏,导致骨脆性增加、易发生骨折为特征的全身性骨病。

影像组学该概念最早由荷兰学者在2012年提出,其强调的深层次含义是指从影像(CTMRIPET)中高通量地提取大量影像信息,实现肿瘤分割、特征提取与模型建立,凭借对海量影像数据信息进行更深层次的挖掘、预测和分析来辅助医师做出最准确的诊断。影像组学可直观地理解为将视觉影像信息转化为深层次的特征来进行量化研究。

背景:磁共振成像(MRI)在骨质疏松症诊断中发挥着越来越重要的作用。影像组学作为一种新的图像分析方法在骨质疏松症诊断中有潜在的临床意义。

目的:探讨基于腰椎磁共振影像组学模型对骨质疏松症的诊断价值。

方法纳入20172月至201810月河北医科大学第一医院门诊女性患者50例,年龄40-84岁,同期进行腰椎MRI及双能X射线骨密度测量。双能X射线骨密度测量结果显示骨质疏松症28例及骨质正常22例,分别在腰椎MRI矢状位T1WIT2WI序列图像选取L2-4椎体中间连续5个层面进行图像分割,提取影像组学特征,建立诊断模型,并与临床特征结合建立影像临床特征模型,使用曲线下面积(AUC)评估模型效能。试验获河北医科大学第一医院伦理委员会批准。

结果与结论:①在50例受试者T1WI、T2WI序列及联合序列分别提取出396×3个特征,通过特征降维后分别筛选出最相关的T1WI序列 4个特征、T2WI序列 6个特征,T1WI及T2WI联合序列图像筛选出4特征,建立诊断模型,T1WI、T2WI单序列诊断模型AUC值分别为0.810,0.820,T1WI+T2WI联合序列诊断模型AUC值为0.937,高于单个序列;②将T1WI+T2WI组学特征与临床资料结合构建了适用于女性的联合临床资料的影像组学诊断模型,其AUC值为0.960;③结果表明,基于常规腰椎MRI的影像组学特征可以区分骨质疏松及骨量正常,结合临床特征建立的联合诊断模型能够提高诊断效能,对诊断骨质疏松症有较高的临床价值。

ORCID: 0000-0001-8685-9059(何丽)

中国组织工程研究杂志出版内容重点:人工关节;骨植入物;脊柱;骨折;内固定;数字化骨科;组织工程

关键词: 骨, 影像组学, 腰椎, 磁共振, 骨质疏松症, 骨密度, 模型

Abstract:

BACKGROUND: Magnetic resonance imaging (MRI) plays an increasingly important role in the diagnosis of osteoporosis. As a new method of image analysis, radiomics has potential clinical significance in the diagnosis of osteoporosis.

OBJECTIVE: To explore the diagnostic value of osteoporosis based on lumbar MRI imaging model.

METHODS: Fifty female patients who underwent both lumbar-spine MRI and dual-energy X-ray absorptiometry in Outpatient Department of First Hospital of Hebei Medical University from February 2017 to October 2018 at the age of 40-84 years were enrolled in this study. Dual-energy X-ray absorptiometry showed 28 osteoporosis patients, and 22 normal bone mineral density. In the sagittal plane T1WI and T2WI images of lumbar MRI, five consecutive layers in the middle of L2-4 vertebral body were selected for image segmentation; radiomics features were extracted; diagnostic models were constructed. Combined with clinical risk factors, the clinical-radiomics model was constructed. The area under the receiver operating characteristic curve was used to assess the model performance. The experiment was approved by the Ethics Committee of First Hospital of Hebei Medical University.

RESULTS AND CONCLUSION: (1) The 396 × 3 features were extracted from T1WI, T2WI and combined sequences respectively in 50 subjects. After feature dimensionality reduction, four features of T1WI sequence, six features of T2WI sequence and four features of T1WI and T2WI combined sequence were screened out respectively. After diagnostic model establishment, the areas under the receiver operating characteristic curve of T1WI and T2WI models were 0.810 and 0.820, respectively. The area under the receiver operating characteristic curve of combined T1WI+T2WI model was 0.937, which was higher than that of a independent sequence. (2) Combining the T1WI + T 2WI radiomics features with clinical data, the diagnostic model suitable for female combined with clinical factors was constructed, and the area under the receiver operating characteristic curve of clinical-radiomics model was 0.960. (3) The results showed that the radiomics features based on routine lumbar MRI can distinguish osteoporosis from normal bone mass, and the clinical-radiomics diagnosis model based on clinical and radiomics features can improve the diagnostic efficiency, which is valuable for diagnosis of osteoporosis.

Key words: bone, imaging histology, lumbar spine, magnetic resonance, osteoporosis, bone mineral density, model

中图分类号: