Preliminary study on the evaluation of early recurrence of hepatocellular carcinoma by magnetic resonance imaging three-dimensional texture features combined with clinical parameters using a radiomics model

WANG Min; SONG Bin

doi:10.19732/j.cnki.1008-617X.2018.04.005

您当前的位置：

首页 >

文章列表页 >

Preliminary study on the evaluation of early recurrence of hepatocellular carcinoma by magnetic resonance imaging three-dimensional texture features combined with clinical parameters using a radiomics model

更新时间：2025-12-15

- Preliminary study on the evaluation of early recurrence of hepatocellular carcinoma by magnetic resonance imaging three-dimensional texture features combined with clinical parameters using a radiomics model
- Vol. 27, Issue 4, Pages: 265-273(2018)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19732/j.cnki.1008-617X.2018.04.005
  CLC：
- Published Online：17 September 2018，
  
  Published：17 September 2018
- 稿件说明：
移动端阅览
王敏,宋彬. 磁共振成像三维纹理特征结合临床参数放射组学模型评估肝细胞癌术后早期复发的初步研究[J]. 肿瘤影像学, 2018, 27(4): 265-273 https://doi.

org/10.19732/j.cnki.1008-617X.2018.04.005
王敏,宋彬. 磁共振成像三维纹理特征结合临床参数放射组学模型评估肝细胞癌术后早期复发的初步研究[J]. 肿瘤影像学, 2018, 27(4): 265-273 https://doi. DOI： 10.19732/j.cnki.1008-617X.2018.04.005.

org/10.19732/j.cnki.1008-617X.2018.04.005 DOI：

摘要

目的：

初步探索磁共振成像（magnetic resonance imaging，MRI）三维纹理（three-dimensional texture，3D-texture）特征结合临床参数构建预测模型，术前评估肝细胞癌（hepatocellular carcinoma，HCC）患者术后早期复发的可行性。

方法：

回顾性纳入98例术后早期复发HCC患者，记录实验室检查结果、MRI影像征象、3D-texture，经数据去冗余、Lasso回归行主要特征提取，使用监督学习算法进行建模，并将模型用于预测83例前瞻性患者术后早期复发。

结果：

动脉期（arterial phase，AP）和门静脉期（portal venous phase，PVP）分别提取出6和2个纹理特征进行建模，AP-3D-texture模型在训练集、验证集及测试集中的预测效能如下：预测准确性（accuracy，ACC）分别为0.735、0.735和0.651；受试者工作特征（receiver operating characteristic，ROC）曲线的曲线下面积（area under curve，AUC）分别为0.759、0.769和0.669。PVP-3D-texture模型在3个数据集中预测效能如下：训练集中ACC为0.721，AUC为0.591；验证集中ACC为0.367，AUC为0.498；测试集中ACC为0.402，AUC为0.560。AP-3D-texture结合临床参数后在3个数据集中的预测效能如下：训练集中ACC为0.838，AUC为0.876；验证集中ACC为0.833，AUC为0.864；测试集中ACC为0.663，AUC为0.656。

结论：

AP-3D-texture可以作为预测HCC术后早期复发的标记，与临床参数结合后预测效能进一步提高，但是在测试集中效能偏低，可能与训练集样本量偏少有关。

Abstract

Objective:

This study aimed to preliminarily explore the feasibility of using mag

netic resonance imaging (MRI) three-dimensional texture (3D-texture) features combined with clinical parameters to build predictive models to assess early recurrence of hepatocellular carcinoma (HCC) patients before surgery.

Methods:

A retrospective study of 98 patients with early recurrence of HCC was performed

and laboratory examinations

MRI images

and 3D-texture were recorded. Data redundancy and Lasso regression were used to extract the main features

using a supervised learning algorithm. Modeling was performed and the model was further used to predict early postoperative recurrence in 83 prospective patients.

Results:

The arterial phase (AP) and the portal venous phase (PVP) extracted 6 and 2 texture features respectively for modeling. The prediction performance of the AP-3D-texture model in the training set

validation set and test set was as follows: The accuracy (ACC) of the prediction was 0.735

0.735 and 0.651; Area under the receiver operating characteristic (ROC) curve (AUC) was 0.759

0.769 and 0.669. The PVP-3Dtexture model prediction performance in three data sets was as follows: Training set ACC was 0.721

AUC was 0.591; Validation set ACC was 0.367

AUC was 0.498; Test set ACC was 0.402

AUC was 0.560. The predictive efficacy of AP-3D-texture in combination with clinical parameters in the three data sets was as follows: Training set ACC was 0.838

AUC was 0.876; Validation set ACC was 0.833

AUC was 0.864; Test set ACC was 0.663

AUC was 0.656.

Conclusion:

AP-3D-texture can be used as a predictor of early recurrence of HCC. Combined with clinical parameters

predictive power is further improved

but the efficacy in the test set is low

which is related to the small sample size of the training set.

关键词

Keywords

references

Views

1517

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Nomogram prediction model of contrast-enhanced ultrasound combined with clinical and pathological features to evaluate the risk of early recurrence after surgical resection of hepatocellular carcinoma

Research progress on preoperative MRI markers combined with surgical margins in predicting early recurrence of HCC

Study on optimizing the prediction model for microvascular invasion in hepatocellular carcinoma by integrating peripheral blood immune cells and FS-T2WI radiomics

Application of magnetic resonance elastography in the identification of benign and malignant liver lesions and prognostic prediction of malignant tumors

Contrast-enhanced ultrasound for the diagnosis of intrahepatic cholangiocarcinoma: debates, focus areas and emerging perspectives

Related Author

Ya YUAN

Kunpeng CAO

Chaoli XU

Xinyue WANG

Hua SHU

Xinhua YE

Lu LI

YU Dexin

Related Institution

Department of Ultrasound, The First Affiliated Hospital with Nanjing Medical University

Department of Radiology, Qilu Hospital of Shandong University

Department of Radiology, Zibo No 1 Hospital

Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University

Department of Radiology, Suzhou BOE Hospital

AI问答

⁰