Li Lingling, Liang Xiaoxin, Yu Yiwen, Mao Rushuang, Han Jing, Peng Chuan, Zhou Jianhua
Department of Ultrasound, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, Guangdong, China.
Indian J Radiol Imaging. 2024 Jan 17;34(3):405-415. doi: 10.1055/s-0043-1777993. eCollection 2024 Jul.
Accurate differentiation within the LI-RADS category M (LR-M) between hepatocellular carcinoma (HCC) and non-HCC malignancies (mainly intrahepatic cholangiocarcinoma [CCA] and combined hepatocellular and cholangiocarcinoma [cHCC-CCA]) is an area of active investigation. We aimed to use radiomics-based machine learning classification strategy for differentiating HCC from CCA and cHCC-CCA on contrast-enhanced ultrasound (CEUS) images in high-risk patients with LR-M nodules. A total of 159 high-risk patients with LR-M nodules (69 HCC and 90 CCA/cHCC-CCA) who underwent CEUS within 1 month before pathologic confirmation from January 2006 to December 2019 were retrospectively included (111 patients for training set and 48 for test set). The training set was used to build models, while the test set was used to compare models. For each observation, six CEUS images captured at predetermined time points (T1, peak enhancement after contrast injection; T2, 30 seconds; T3, 45 seconds; T4, 60 seconds; T5, 1-2 minutes; and T6, 2-3 minutes) were collected for tumor segmentation and selection of radiomics features, which included seven types of features: first-order statistics, shape (2D), gray-level co-occurrence matrix, gray-level size zone matrix, gray-level run length matrix, neighboring gray tone difference matrix, and gray-level dependence matrix. Clinical data and key radiomics features were employed to develop the clinical model, radiomics signature (RS), and combined RS-clinical (RS-C) model. The RS and RS-C model were built using the machine learning framework. The diagnostic performance of these three models was calculated and compared. Alpha-fetoprotein (AFP), CA19-9, enhancement pattern, and time of washout were included as independent factors for clinical model (all < 0.05). Both the RS and RS-C model performed better than the clinical model in the test set (area under the curve [AUC] of 0.698 [0.571-0.812] for clinical model, 0.903 [0.830-0.970] for RS, and 0.912 [0.838-0.977] for the RS-C model; both < 0.05). Radiomics-based machine learning classifiers may be competent for differentiating HCC from CCA and cHCC-CCA in high-risk patients with LR-M nodules.
在肝脏影像报告和数据系统（LI-RADS）的M类（LR-M）中，准确区分肝细胞癌（HCC）与非HCC恶性肿瘤（主要是肝内胆管癌[CCA]以及肝细胞癌合并胆管癌[cHCC-CCA]）是一个正在积极研究的领域。我们旨在采用基于放射组学的机器学习分类策略，在具有LR-M结节的高危患者的对比增强超声（CEUS）图像上区分HCC与CCA和cHCC-CCA。
回顾性纳入了2006年1月至2019年12月期间在病理确诊前1个月内接受CEUS检查的159例具有LR-M结节的高危患者（69例HCC和90例CCA/cHCC-CCA）（111例患者作为训练集，48例作为测试集）。训练集用于构建模型，而测试集用于比较模型。对于每次观察，收集在预定时间点（T1，注射造影剂后的峰值增强；T2，30秒；T3，45秒；T4，60秒；T5，1 - 2分钟；T6，2 - 3分钟）采集的6张CEUS图像，用于肿瘤分割和放射组学特征选择，这些特征包括七种类型：一阶统计量、形状（二维）、灰度共生矩阵、灰度大小区域矩阵、灰度行程长度矩阵、相邻灰度色调差异矩阵和灰度依赖矩阵。临床数据和关键放射组学特征被用于开发临床模型、放射组学特征（RS）以及联合RS-临床（RS-C）模型。RS和RS-C模型使用机器学习框架构建。计算并比较这三种模型的诊断性能。
甲胎蛋白（AFP）、CA19-9、增强模式和洗脱时间被纳入临床模型的独立因素（均<0.05）。在测试集中，RS和RS-C模型的表现均优于临床模型（临床模型的曲线下面积[AUC]为0.698[0.571 - 0.812]，RS为0.903[0.830 - 0.970]，RS-C模型为0.912[0.838 - 0.977]；均<0.05）。
基于放射组学的机器学习分类器可能有能力在具有LR-M结节的高危患者中区分HCC与CCA和cHCC-CCA。
