Yang Nan, Ma Zhuangxuan, Zhang Ling, Ji Wenbin, Xi Qian, Li Ming, Jin Liang
Department of Radiology, Huadong Hospital, Fudan University, Shanghai, China.
Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China.
Abdom Radiol (NY). 2025 May;50(5):2126-2139. doi: 10.1007/s00261-024-04685-y. Epub 2024 Nov 22.
BACKGROUND & AIMS: Enhanced computed tomography (CT) is the primary method for focal liver lesion diagnosis. We aimed to use automated machine learning (AutoML) algorithms to differentiate between benign and malignant focal liver lesions on the basis of radiomics from unenhanced CT images.
We enrolled 260 patients from 2 medical centers who underwent CT examinations between January 2017 and March 2023. This included 60 cases of hepatic malignancies, 93 cases of hepatic hemangiomas, 48 cases of hepatic abscesses, and 84 cases of hepatic cysts. The Pyradiomics method was used to extract radiomics features from unenhanced CT images. By using the mljar-supervised (MLJAR) AutoML framework, clinical, radiomics, and fusion models combining clinical and radiomics features were established.
In the training and validation sets, the area under the curve (AUC) values for the clinical, radiomics, and fusion models exceeded 0.900. In the external testing set, the respective AUC values for the clinical, radiomics, and fusion models were as follows: 0.88, 1.00, and 1.00 for hepatic cysts; 0.81, 0.90, and 0.97 for hepatic hemangiomas; 0.89, 0.98, and 0.92 for hepatic abscesses; and 0.23, 0.80, and 0.93 for hepatic malignancies. The diagnostic accuracy rates for hepatic cysts, hemangiomas, malignancies, and abscesses by radiologists in the external testing cohort were 0.96, 0.60, 0.79, and 0.66, respectively.
The fusion model based on noninvasive radiomics and clinical features of unenhanced CT images has high clinical value for distinguishing focal hepatic lesions.
增强计算机断层扫描（CT）是局灶性肝病变诊断的主要方法。我们旨在使用自动机器学习（AutoML）算法，基于平扫CT图像的影像组学特征区分良性和恶性局灶性肝病变。
我们纳入了来自2个医疗中心的260例患者，这些患者在2017年1月至2023年3月期间接受了CT检查。其中包括60例肝脏恶性肿瘤、93例肝血管瘤、48例肝脓肿和84例肝囊肿。使用Pyradiomics方法从平扫CT图像中提取影像组学特征。通过使用mljar - 监督（MLJAR）AutoML框架，建立了临床、影像组学以及结合临床和影像组学特征的融合模型。
在训练集和验证集中，临床、影像组学和融合模型的曲线下面积（AUC）值均超过0.900。在外部测试集中，临床、影像组学和融合模型对于肝囊肿的AUC值分别为：0.88、1.00和1.00；对于肝血管瘤的AUC值分别为：0.81、0.90和0.97；对于肝脓肿的AUC值分别为：0.89、0.98和0.92；对于肝脏恶性肿瘤的AUC值分别为：0.23、0.80和0.93。外部测试队列中放射科医生对肝囊肿、血管瘤、恶性肿瘤和脓肿的诊断准确率分别为0.96、0.60、0.79和0.66。
基于平扫CT图像的无创影像组学和临床特征的融合模型在鉴别局灶性肝病变方面具有较高的临床价值。
