Yang Zhou1, Guofeng Zhou2,3, Jiulou Zhang1, Chen Xu4, Feipeng Zhu5, Pengju Xu6,7. 1. Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, No 300, Guangzhou Road, Nanjing, 210029, Jiangsu Province, China. 2. Department of Radiology, Zhongshan Hospital, Fudan University, No.180 Fenglin Road, Xuhui District, Shanghai, 200032, China. 3. Shanghai Institute of Medical Imaging, No.180 Fenglin Road, Xuhui District, Shanghai, 200032, China. 4. Department of Pathology, Zhongshan Hospital, Fudan University, Shanghai, 200032, China. 5. Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, No 300, Guangzhou Road, Nanjing, 210029, Jiangsu Province, China. zhufeipeng2008@163.com. 6. Department of Radiology, Zhongshan Hospital, Fudan University, No.180 Fenglin Road, Xuhui District, Shanghai, 200032, China. xpjbfc@163.com. 7. Shanghai Institute of Medical Imaging, No.180 Fenglin Road, Xuhui District, Shanghai, 200032, China. xpjbfc@163.com.
Abstract
OBJECTIVE: To establish a radiomics nomogram based on dynamic contrast-enhanced (DCE) MR images to preoperatively differentiate combined hepatocellular-cholangiocarcinoma (cHCC-CC) from mass-forming intrahepatic cholangiocarcinoma (IMCC). METHODS: A total of 151 training cohort patients (45 cHCC-CC and 106 IMCC) and 65 validation cohort patients (19 cHCC-CC and 46 IMCC) were enrolled. Findings of clinical characteristics and MR features were analyzed. Radiomics features were extracted from the DCE-MR images. A radiomics signature was built based on radiomics features by the least absolute shrinkage and selection operator algorithm. Univariate and multivariate analyses were used to identify the significant clinicoradiological variables and construct a clinical model. The radiomics signature and significant clinicoradiological variables were then incorporated into the radiomics nomogram by multivariate logistic regression analysis. Performance of the radiomics nomogram, radiomics signature, and clinical model was assessed by receiver operating characteristic and area under the curve (AUC) was compared. RESULTS: Eleven radiomics features were selected to develop the radiomics signature. The radiomics nomogram integrating the alpha fetoprotein, background liver disease (cirrhosis or chronic hepatitis), and radiomics signature showed favorable calibration and discrimination performance with an AUC value of 0.945 in training cohort and 0.897 in validation cohort. The AUCs for the radiomics signature and clinical model were 0.848 and 0.856 in training cohort and 0.792 and 0.809 in validation cohort, respectively. The radiomics nomogram outperformed both the radiomics signature and clinical model alone (p < 0.05). CONCLUSION: The radiomics nomogram based on DCE-MRI may provide an effective and noninvasive tool to differentiate cHCC-CC from IMCC, which could help guide treatment strategies. KEY POINTS: • The radiomics signature based on dynamic contrast-enhanced magnetic resonance imaging is useful to preoperatively differentiate cHCC-CC from IMCC. • The radiomics nomogram showed the best performance in both training and validation cohorts for differentiating cHCC-CC from IMCC.
OBJECTIVE: To establish a radiomics nomogram based on dynamic contrast-enhanced (DCE) MR images to preoperatively differentiate combined hepatocellular-cholangiocarcinoma (cHCC-CC) from mass-forming intrahepatic cholangiocarcinoma (IMCC). METHODS: A total of 151 training cohort patients (45 cHCC-CC and 106 IMCC) and 65 validation cohort patients (19 cHCC-CC and 46 IMCC) were enrolled. Findings of clinical characteristics and MR features were analyzed. Radiomics features were extracted from the DCE-MR images. A radiomics signature was built based on radiomics features by the least absolute shrinkage and selection operator algorithm. Univariate and multivariate analyses were used to identify the significant clinicoradiological variables and construct a clinical model. The radiomics signature and significant clinicoradiological variables were then incorporated into the radiomics nomogram by multivariate logistic regression analysis. Performance of the radiomics nomogram, radiomics signature, and clinical model was assessed by receiver operating characteristic and area under the curve (AUC) was compared. RESULTS: Eleven radiomics features were selected to develop the radiomics signature. The radiomics nomogram integrating the alpha fetoprotein, background liver disease (cirrhosis or chronic hepatitis), and radiomics signature showed favorable calibration and discrimination performance with an AUC value of 0.945 in training cohort and 0.897 in validation cohort. The AUCs for the radiomics signature and clinical model were 0.848 and 0.856 in training cohort and 0.792 and 0.809 in validation cohort, respectively. The radiomics nomogram outperformed both the radiomics signature and clinical model alone (p < 0.05). CONCLUSION: The radiomics nomogram based on DCE-MRI may provide an effective and noninvasive tool to differentiate cHCC-CC from IMCC, which could help guide treatment strategies. KEY POINTS: • The radiomics signature based on dynamic contrast-enhanced magnetic resonance imaging is useful to preoperatively differentiate cHCC-CC from IMCC. • The radiomics nomogram showed the best performance in both training and validation cohorts for differentiating cHCC-CC from IMCC.