基于IVIM-DWI功能图像的影像组学模型术前预测肝细胞癌的分化程度

庄羽翔; 李晓凤; 周代全; 旷连勤; 严敏

doi:10.16016/j.2097-0927.202403098

您当前的位置：

首页 >

文章列表页 >

基于IVIM-DWI功能图像的影像组学模型术前预测肝细胞癌的分化程度

临床医学 | 更新时间：2026-01-09

- 基于IVIM-DWI功能图像的影像组学模型术前预测肝细胞癌的分化程度
- IVIM-DWI-based radiomic model for preoperative prediction of hepatocellular carcinoma differentiation
- 陆军军医大学学报 2024年46卷第20期页码：2322-2329
- 作者机构：
  
  401120 重庆，重庆医科大学附属第三医院放射科
- 作者简介：
  
  [严敏，E-mail：yanmin@cqmu.edu.cn YAN Min, E-mail: yanmin@cqmu.edu.cn
- 基金信息：
  
  重庆市教育委员会科学技术研究项目(KJQN202300452);重庆市临床重点专科建设项目(SLCZDZK202202);利益冲突全体作者声明不存在利益冲突
- DOI：10.16016/j.2097-0927.202403098
  中图分类号： R445.2;R730.21;R735.7
- 收稿：2024-03-25，
  
  修回：2024-06-02，
  
  纸质出版：2024-10-30
- 稿件说明：
移动端阅览
庄羽翔, 李晓凤, 周代全, 等. 基于IVIM-DWI功能图像的影像组学模型术前预测肝细胞癌的分化程度[J]. 陆军军医大学学报, 2024,46(20):2322-2329.

Yuxiang ZHUANG, Xiaofeng LI, Daiquan ZHOU, et al. IVIM-DWI-based radiomic model for preoperative prediction of hepatocellular carcinoma differentiation[J]. Journal of Army Medical University, 2024, 46(20): 2322-2329.
庄羽翔, 李晓凤, 周代全, 等. 基于IVIM-DWI功能图像的影像组学模型术前预测肝细胞癌的分化程度[J]. 陆军军医大学学报, 2024,46(20):2322-2329. DOI： 10.16016/j.2097-0927.202403098.

Yuxiang ZHUANG, Xiaofeng LI, Daiquan ZHOU, et al. IVIM-DWI-based radiomic model for preoperative prediction of hepatocellular carcinoma differentiation[J]. Journal of Army Medical University, 2024, 46(20): 2322-2329. DOI： 10.16016/j.2097-0927.202403098.

摘要

目的

基于体素内不相干运动扩散加权成像(intravoxel incoherent motion diffusion-weighted imaging

IVIM-DWI)功能图像构建影像组学相关模型，探讨其术前预测肝细胞癌(hepatocellular carcinoma

HCC)分化程度的价值。

方法

纳入2018年6月至2024年1月于重庆医科大学附属第三医院接受手术治疗的187例HCC患者的临床及影像学资料，根据术后病理结果分为低分化组(

=58)和非低分化组(

=129)，以8 ∶2的比例随机分为训练组149例和验证组38例。采用单因素分析评估与HCC分化程度相关的临床资料并构建临床模型；应用Pyradiomics软件提取IVIM-DWI功能图像的组学特征，采用最小绝对收缩和选择算子逻辑回归算法筛选出与HCC分化程度高度相关的影像组学特征，分别运用支持向量机(support vector machine

SVM)、逻辑回归(logistic regression

LR)、随机森林(random forest

RF)算法构建不同的影像组学模型；采用SVM算法构建影像组学-临床联合模型。采用10折交叉验证进行模型内部验证；运用受试者工作特征曲线(receiver operating characteristic curve

ROC)、曲线下面积(area under the curve

AUC)、校准曲线、决策曲线分析(decision curve analysis

DCA)评价临床模型、影像组学模型、影像组学-临床联合模型的诊断价值和临床收益。

结果

共提取4 060个影像组学特征，经过特征筛选及降维后，最终纳入24个特征进行模型构建。结果显示，影像组学模型、影像组学-临床联合模型的预测性能优于临床模型。运用SVM算法构建的影像组学模型、影像组学-临床联合模型间进行比较，在训练集中影像组学模型AUC=0.954(0.908~1.000)，影像组学-临床联合模型AUC=0.943(0.905~0.982)，二者间差异无统计学意义；在验证集中影像组学模型AUC=0.807(0.640~0.975)，影像组学-临床联合模型AUC=0.876(0.743~1.000)，二者间差异具有统计学意义(

＜0.05)。校准曲线显示影像组学模型和影像组学-临床联合模型具有良好的拟合优度。DCA曲线显示影像组学模型和影像组学-临床联合模型的净收益较高，阈概率范围较大，影像组学-临床联合模型的临床净收益最大(

＜0.05)。

结论

基于IVIM-DWI功能图像构建的影像组学模型和影像组学-临床联合模型能够在术前较准确地预测HCC分化程度。

Abstract

Objective

To construct a radiomic model based on intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) for preoperative prediction of hepatocellular carcinoma (HCC) differentiation and validate its clinical value.

Methods

Clinical and imaging data of 187 HCC patients who received surgical treatment in the Third Affiliated Hospital of Chongqing Medical University from June 2018 to January 2024 were collected and retrospectively analyzed. According to the postoperative pathological results

they were divided into low-differentiation group (

=58) and non-low-differentiation group (

=129)

and randomly divided into the training group (

=149) and the validation group (

=38) with the ratio of 8 ∶2. Univariate analysis was used to assess the clinical indicators related to HCC differentiation

and then a clinical model was constructed. Pyramidimics software was used to extract the radiomic features of IVIM-DWI functional images

and minimum absolute contraction and selection operator logistic regression algorithm were employed to screen those highly correlated indicators with HCC differentiation. Support vector machine (SVM)

logistic regression (LR) and random forest (RF) algorithms were utilized to construct different image omics models. SVM algorithm was applied to construct the combined imaging omics and clinical model. The internal verification of the model was carried out by using ten-fold cross-validation. Receiver operating characteristic (ROC) curve

area under the curve (AUC)

calibration curve

and decision curve analysis (DCA) were used to evaluate the diagnostic value and clinical benefits of clinical model

radiomic model

and their combination.

Results

A total of 4 060 radiological features were extracted

and after feature screening and dimensionality reduction

24 features were finally included to construct the model. Among all models

the pre

dictive performance of the radiomic model and the radiomic-clinical combined model was better than that of the clinical model. In the comparison between the radiomic model constructed by SVM algorithm and the radiomics-clinical combined model

the AUC value was 0.954 (0.908~1.000) for the former model

and was 0.943 (0.905~0.982) for the latter model in the training set

and there was no significant difference between them. In the validation set

the AUC value was 0.807 (0.640~0.975) and 0.876 (0.743~1.000)

respectively

with statistical difference between the 2 models (

0.05). Calibration curve analysis showed that the radiomic model and the radiomics-clinical combined model had good goodness of fit. DCA indicated that the net benefit was higher and the threshold probability range was larger in both the radiomic model and the radiomics-clinical combined model

and the net benefit of the combined model was larger.

Conclusion

Both the radiomic model and the combined radiomics-clinical model constructed on the basis of IVIM-DWI functional images can better predict the severity of HCC differentiation before surgery.

关键词

Keywords

references

CAO W, CHEN H D, YU Y W, et al . Changing profiles of cancer burden worldwide and in China: a secondary analysis of the global cancer statistics 2020[J ] . Chin Med J, 2021, 134(7): 783-791. DOI: 10.1097/CM9.0000000000001474.

YANG J D, HEIMBACH J K. New advances in the diagnosis and management of hepatocellular carcinoma[J]. Br Med J, 2020, 371: m3544. DOI: 10.1136/bmj.m3544.

PELLAT A, BARAT M, CORIAT R, et al . Artificial intelligence: a review of current applications in hepatocellular carcinoma imaging[J ] . Diagn Interv Imaging, 2023, 104(1): 24-36. DOI: 10.1016/j.diii.2022.10.001.

HU X J, LI C F, WANG Q, et al . Development and external validation of a radiomics model derived from preoperative gadoxetic acid-enhanced MRI for predicting histopathologic grade of hepatocellular carcinoma[J ] . Diagnostics, 2023, 13(3): 413. DOI: 10.3390/diagnostics13030413.

MAO B, ZHANG L Z, NING P G, et al . Preoperative prediction for pathological grade of hepatocellular carcinoma via machine learning-based radiomics[J ] . Eur Radiol, 2020, 30(12): 6924-6932. DOI: 10.1007/s00330-020-07056-5.

WU M H, TAN H N, GAO F, et al . Predicting the grade of hepatocellular carcinoma based on non-contrast-enhanced MRI radiomics signature[J ] . Eur Radiol, 2019, 29(6): 2802-2811. DOI: 10.1007/s00330-018-5787-2.

张天奇, 王芊婷, 李明洋, 等. 基于IVIM多参数MRI影像组学术前预测直肠癌T分期[J]. 放射学实践, 2022, 37(9): 1085-1091. DOI: 10.13609/j.cnki.1000-0313.2022.09.006.

ZHANG T Q, WANG Q T, LI M Y, et al . Preoperative prediction of T-stage of rectal cancer based on IVIM multiparameter MRI radiomics[J ] . Radiol Pract, 2022, 37(9): 1085-1091. DOI: 10.13609/j.cnki.1000-0313.2022.09.006.

戴干棉, 武文渊, 傅丽莉, 等. 基于IVIM-DWI定量参数的影像组学预测鼻咽癌短期疗效[J]. 磁共振成像, 2023, 14(9): 56-62, 69. DOI: 10.12015/issn.1674-8034.2023.09.010.

DAI G M, WU W Y, FU L L, et al . Radiomics analysis based on IVIM-DWI quantitative parameters to predict the short-term therapeutic effect of nasopharyngeal carcinoma[J ] . Chin J Magn Reson Imag, 2023, 14(9): 56-62, 69. DOI: 10.12015/issn.1674-8034.2023.09.010.

ZHANG Y, ZHANG K Y, JIA H D, et al . IVIM-DWI and MRI-based radiomics in cervical cancer: Prediction of concurrent chemoradiotherapy sensitivity in combination with clinical prognostic factors[J ] . Magn Reson Imaging, 2022, 91: 37-44. DOI: 10.1016/j.mri.2022.05.005.

NAGTEGAAL I D, ODZE R D, KLIMSTRA D, et al . The 2019 WHO classification of tumours of the digestive system[J ] . Histopathology, 2020, 76(2): 182-188. DOI: 10.1111/his.13975.

WEI J W, JIANG H Y, ZHOU Y, et al . Radiomics: a radiological evidenc e-based artificial intelligence technique to facilitate personalized precision medicine in hepatocellular carcinoma[J ] . Dig Liver Dis, 2023, 55(7): 833-847. DOI: 10.1016/j.dld.2022.12.015.

ZHU S C, LIU Y H, WEI Y, et al . Intravoxel incoherent motion diffusion-weighted magnetic resonance imaging for predicting histological grade of hepatocellular carcinoma: Comparison with conventional diffusion-weighted imaging[J ] . World J Gastroenterol, 2018, 24(8): 929-940. DOI: 10.3748/wjg.v24.i8.929.

SHAN Q G, KUANG S C, ZHANG Y, et al . A comparative study of monoexponential versus biexponential models of diffusion-weighted imaging in differentiating histologic grades of hepatitis B virus-related hepatocellular carcinoma[J ] . Abdom Radiol, 2020, 45(1): 90-100. DOI: 10.1007/s00261-019-02253-3.

SOKMEN B K, SABET S, OZ A, et al . Value of intravoxel incoherent motion for hepatocellular carcinoma grading[J ] . Transplant Proc, 2019, 51(6): 1861-1866. DOI: 10.1016/j.transproceed.2019.02.027.

ZHOU Y, ZHENG J, YANG C, et al . Application of intravoxel incoherent motion diffusion-weighted imaging in hepatocellular carcinoma[J ] . World J Gastroenterol, 2022, 28(27): 3334-3345. DOI: 10.3748/wjg.v28.i27.3334.

SHI G F, HAN X, WANG Q, et al . Evaluation of multiple prognostic factors of hepatocellular carcinoma with intra-voxel incoherent motions imaging by extracting the histogram metrics[J ] . Cancer Manag Res, 2020, 12: 6019-6031. DOI: 10.2147/CMAR.S262973.

张喆, 刘爱连, 赵莹, 等. 基于体素内不相干运动成像的三维容积ROI直方图分析在术前评估肝细胞癌病理分化程度中的价值研究[J]. 磁共振成像, 2020, 11(9): 758-764, 770. DOI: 10.12015/issn.1674-8034.2020.09.008.

ZHANG Z, LIU A L, ZHAO Y, et al . The value of three-dimensional volumetric ROI histogram analysis based on intravoxel incoherent motion imaging in preoperative assessment of pathological differentiation degree of hepatocellular carcinoma[J ] . Chin J Magn Reson Imag, 2020, 11(9): 758-764, 770. DOI: 10.12015/issn.1674-8034.2020.09.008.

潘杰, 毛景松, 姚天虹, 等. 影像组学在肝癌中应用的研究进展[J]. 中国CT和MRI杂志, 2023, 21(4): 174-177. DOI: 10.3969/j.issn.1672-5131.2023.04.061.

PAN J, MAO J S, YAO T H, et al . The research progress in the application of radiomics in liver cancer[J ] . Chin J CT MRI, 2023, 21(4): 174-177. DOI: 10.3969/j.issn.1672-5131.2023.04.061.

NAKAGAWA M, NAKAURA T, NAMIMOTO T, et al . Machine learning to differentiate T2-weighted hyperintense uterine leiomyomas from uterine sarcomas by utilizing multiparametric magnetic resonance quantitative imaging features[J ] . Acad Radiol, 2019, 26(10): 1390-1399. DOI: 10.1016/j.acra.2018.11.014.

ZHANG J J, WANG G H, REN J L, et al . Multiparametric MRI-based radiomics nomogram for preoperative prediction of lymphovascular invasion and clinical outcomes in patients with breast invasive ductal carcinoma[J ] . Eur Radiol, 2022, 32(6): 4079-4089. DOI: 10.1007/s00330-021-08504-6.

浏览量

101

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于磁共振DSC-PWI构建的肿瘤血管生境对胶质母细胞瘤和单发脑转移瘤鉴别诊断效能的研究

融合深度学习、临床与影像组学特征的综合模型提升非小细胞肺癌EGFR突变预测效能

SLC38A1通过促进谷氨酰胺摄取激活PI3K/AKT信号通路驱动肝细胞癌恶性进展

T1rho磁共振技术定量评估腰痛患者椎间盘早期退行性改变

肝细胞癌临床诊治新进展：综合治疗策略的演变