Bu Didi, Duan Shaobo, Ren Shanshan, Ma Yujing, Liu Yuanyuan, Li Yahong, Cai Xiguo, Zhang Lianzhong
Department of Ultrasound, Zhengzhou University People's Hospital, Henan Provincial People's Hospital, Zhengzhou University, Zhengzhou, China.
Department of Health Management, Henan Provincial People's Hospital, Zhengzhou, China.
Front Med (Lausanne). 2025 Apr 28;12:1565618. doi: 10.3389/fmed.2025.1565618. eCollection 2025.
To explore the utility of machine learning-based ultrasound radiomics for predicting gene mutation in hepatocellular carcinoma (HCC).
154 HCC patients with 182 lesions from 2019 to 2024 were reviewed retrospectively. All lesions were randomly split into the training set ( = 129) and the test set ( = 53), and ultrasound radiomics features were extracted and selected. Extreme gradient boosting tree (XGBoost), decision tree (DT), random forest (RF), support vector machine (SVM), and logistic regression (LR) were used to construct the ultrasound radiomics models, the clinical models, and the combined models. The predictive performance of various models was evaluated by the area under the curve (AUC), accuracy, calibration curve, and decision curve analysis (DCA).
Among the 182 lesions, 102 were confirmed as mutant and 80 were confirmed as wild-type . The ultrasound radiomics model obtained an AUC of 0.778 and an accuracy of 0.774 in the test set. The clinical model achieved an AUC of 0.761 and an accuracy of 0.710 in the test set. Notably, integrating clinical features with ultrasound radiomics further enhanced predictive performance. The XGBoost-based combined model exhibited the highest predictive performance among all models, achieving an AUC of 0.846 and an accuracy of 0.823 in the test set. The decision curve analysis and calibration curve revealed that the XGBoost-based combined model provided the highest clinical benefit and exhibited strong predictive consistency.
Machine learning-based ultrasound radiomics signatures accurately predict gene mutations in HCC. The XGBoost-based combined model, which combined ultrasound radiomics features with clinical features, showed the best performance and represented a promising noninvasive approach for screening -mutated HCC.
探讨基于机器学习的超声放射组学在预测肝细胞癌（HCC）基因突变中的应用价值。
回顾性分析2019年至2024年154例患有182个病灶的HCC患者。将所有病灶随机分为训练集（n = 129）和测试集（n = 53），并提取和选择超声放射组学特征。使用极端梯度提升树（XGBoost）、决策树（DT）、随机森林（RF）、支持向量机（SVM）和逻辑回归（LR）构建超声放射组学模型、临床模型和联合模型。通过曲线下面积（AUC）、准确性、校准曲线和决策曲线分析（DCA）评估各种模型的预测性能。
在182个病灶中，102个被确认为突变型，80个被确认为野生型。超声放射组学模型在测试集中的AUC为0.778，准确性为0.774。临床模型在测试集中的AUC为0.761，准确性为0.710。值得注意的是，将临床特征与超声放射组学相结合进一步提高了预测性能。基于XGBoost的联合模型在所有模型中表现出最高的预测性能，在测试集中的AUC为0.846，准确性为0.823。决策曲线分析和校准曲线显示，基于XGBoost的联合模型提供了最高的临床效益，并表现出很强的预测一致性。
基于机器学习的超声放射组学特征能够准确预测HCC中的基因突变。基于XGBoost的联合模型将超声放射组学特征与临床特征相结合，表现出最佳性能，代表了一种有前景的非侵入性方法用于筛查突变型HCC。
