目的:探讨肝脏磁共振动态增强的影像组学特征在评估肝硬化患者肝脏储备功能中的价值。方法:收集2018年1月-2022年9月在我院就诊符合纳入标准的肝硬化患者共474例,按照Child-Pugh分级标准分成222例Child-Pugh A级患者和252例Child-Pugh B+C级患者,并分别按照7∶3的比例随机分成训练组和验证组。采用3D Slicer软件勾画感兴趣区并提取门脉期图像的影像组学特征,2名医师勾画结果的一致性检验使用组内相关系数进行,采用最小绝对收缩和选择算法对数据进行降维以及特征筛选处理,利用受试者工作特征(ROC)曲线定量评估其诊断效能。结果:利用3D Slicer软件提取的1 223个纹理特征参数进行降维筛选,最终得到18个影像组学特征参数。根据以上特征构建影像组学模型,该影像组学模型在预测肝脏储备功能的诊断效能方面,其在训练组及验证组中的ROC曲线下面积分别为0.80和0.61。结论:利用肝脏磁共振动态增强的影像组学特征可以准确评估肝硬化患者肝脏储备功能,该模型可作为肝脏储备功能较为准确可靠的辅助检测工具,为临床医生评估肝硬化患者的肝脏储备功能提供一种更为准确立体的新手段。
Objective: To explore the value of radiomics features of liver dynamic contrast enhanced magnetic resonance imaging in evaluating liver reserve function in patients with liver cirrhosis. Methods: A total of 474 patients with cirrhosis who met the inclusion criteria were collected from our hospital from January 2018 to September 2022. According to the Child-Pugh classification standard, they were divided into Child-Pugh A (222 patients) and Child-Pugh B+C (252 patients). Meanwhile, according to the ratio of 7∶3, they were randomly divided into training group and validation group. The 3D Slicer software was used to delineate the region of interest and extract the radiomics features of the portal phase images. The consistency test of the delineation results of the two physicians was performed using the intra-group correlation coefficient. The minimum absolute shrinkage and selection algorithm was used to reduce the dimension of the data and screen the features. The receiver operating characteristic (ROC) curve was used to quantitatively evaluate its diagnostic efficacy. Results: The 1 223 texture feature parameters extracted by 3D Slicer software were used for dimensionality reduction and screening, and finally 18 radiomics feature parameters were obtained. Based on the above characteristics, a radiomics model was constructed, and the area under the ROC curve of the radiomics model in predicting the diagnostic efficacy of liver reserve function in the training group and the validation group was 0.80 and 0.61, respectively. Conclusion: The radiomics features of dynamic contrast enhanced magnetic resonance imaging can accurately evaluate the liver reserve function of patients with cirrhosis. The model can be used as a more accurate and reliable auxiliary detection tool for liver reserve function, which provides a more accurate and three-dimensional new method for clinicians to evaluate the liver reserve function of patients with cirrhosis.
[1] Li M, Wang ZQ, Zhang L, et al. Burden of cirrhosis and other chronic liver diseases caused by specific etiologies in china, 1990-2016:findings from the global burden of disease study 2016[J]. Biomed Environ Sci, 2020, 33(1): 1-10.
[2] Li C, Liu H, Wang J, et al. Multiparametric MRI combined with liver volume for quantitative evaluation of liver function in patients with cirrhosis[J]. Diagn Interv Radiol, 2022, 28(6): 547-554.
[3] Ginès P, Krag A, Abraldes JG, et al. Liver cirrhosis[J]. Lancet, 2021, 398(10308): 1359-1376.
[4] Zhou W, Hu HJ, Shen B, et al. Application values of gadolinium-ethoxybenzyl diethylenetriaminepentaacetic acid enhanced magnetic resonance imaging-based radiomics in the quantitative assessment of liver reserve function of patients withliver cirrhosis[J].Zhongguo Yi Xue Ke Xue Yuan Xue Bao, 2020, 42(4): 459-467.
[5] 张喆, 李民, 赵丽琴, 等.基于CT影像组学特征评估肝硬化患者肝脏储备功能[J]. CT理论与应用研究, 2022, 31(1): 55-62.
[6] Abraldes JG, Caraceni P, Ghabril M, et al. Update in the Treatment of the Complications of Cirrhosis[J]. Clin Gastroenterol Hepatol, 2023, 21(8): 2100-2109.
[7] 中华医学会肝病学分会. 肝硬化诊治指南[J]. 现代医药卫生, 2020, 36(2): 320, 1-18.
[8] Gwak GY. Renewed 2015 clinical practice guidelines for management of hepatitis c by Korean association for the study of the liver;what has been changed?Treatment of patients with decompensated cirrhosis[J].Korean J Gastroenterol, 2016, 67(3): 137-141.
[9] Tang G, Liu J, Liu P, et al. Evaluation of liver function in patients with liver cirrhosis and chronic liver dis-ease using functional liver imaging scores at different acquisition time points[J]. Front Genet, 2022, 13: 1071025
[10] Huang Z, Zhang G, Liu J, et al. LRFNet: a deep learning model for the assessment of liver reserve function based on Child-Pugh score and CT image[J]. Comput Methods Programs Biomed, 2022, 223: 106993.
[11] 刘宏, 刘光耀, 周俊林. 肝硬化食管静脉曲张及出血风险影像学研究进展[J]. 磁共振成像, 2021,12(9): 109-112.
[12] Wei Y, Gong J, He X, et al. An MRI-Based Radiomic model for individualized prediction of hepatocellular carcinoma in patients with hepatitis b virus-related cirrhosis[J]. Front Oncol, 2022, 12: 800787.
[13] 周玮, 胡红杰, 沈博, 等. 基于钆塞酸二钠增强磁共振成像影像组学定量评估肝硬化患者肝脏储备功能的应用价值[J]. 中国医学科学院学报, 2020, 42(4): 459-467.
[14] Park HJ, Park B, Lee SS. Radiomics and Deep Learning: Hepatic Applications[J]. Korean J Radiol, 2020, 21(4): 387-401.
[15] Cao JM, Yang JQ, Ming ZQ, et al. A radiomics model of liver CT to predict risk of hepatic encephalopathy secondary to hepatitis B related cirrhosis[J]. Eur J Radiol, 2020, 130: 109201.
[16] Wu J, Xie F, Ji H, et al. A clinical-radiomic model for predicting indocyanine green retention rate at 15 min in patients with hepatocellular carcinoma[J]. Front Surg, 2022, 9: 857838.
[17] 陈敏山. 中国肿瘤整合诊治指南-肝癌(2022精简版)[J]. 中国肿瘤临床, 2022, 49(17): 865-873.
[18] 李宏为, 陈皓. 当代门静脉高压症治疗方法合理选择[J]. 中国实用外科杂志, 2014, 34(1): 24-27.
[19] Nitsch J, Sack J, Halle MW, et al. MRI-based radiomic feature analysis of end-stage liver disease for severity stratification[J]. Int J Comput Assist Radiol Surg, 2021,16(3): 457-466.
[20] 张智星, 黄忠江, 何生, 等. 基于增强CT影像组学评估肝硬化患者肝储备功能的应用[J]. 放射学实践, 2022, 37(6): 676-682.
