Chunli Kong1,2, Zhongwei Zhao1,2, Weiyue Chen1,2, Xiuling Lv1,2, Gaofeng Shu1,2, Miaoqing Ye1,2, Jingjing Song1,2, Xihui Ying1,2, Qiaoyou Weng1,2, Wei Weng1,2, Shiji Fang1,2, Minjiang Chen1,2, Jianfei Tu3,4, Jiansong Ji5,6. 1. Key Laboratory of Imaging Diagnosis and Minimally Invasive Intervention Research, Lishui Hospital of Zhejiang University/the Fifth Affiliated Hospital of Wenzhou Medical University, Lishui, 323000, China. 2. Department of Radiology, Affiliated Lishui Hospital of Zhejiang University/the Fifth Affiliated Hospital of Wenzhou Medical University/The Central Hospital of Zhejiang Lishui, Lishui, 323000, China. 3. Key Laboratory of Imaging Diagnosis and Minimally Invasive Intervention Research, Lishui Hospital of Zhejiang University/the Fifth Affiliated Hospital of Wenzhou Medical University, Lishui, 323000, China. jianfei1133@163.com. 4. Department of Radiology, Affiliated Lishui Hospital of Zhejiang University/the Fifth Affiliated Hospital of Wenzhou Medical University/The Central Hospital of Zhejiang Lishui, Lishui, 323000, China. jianfei1133@163.com. 5. Key Laboratory of Imaging Diagnosis and Minimally Invasive Intervention Research, Lishui Hospital of Zhejiang University/the Fifth Affiliated Hospital of Wenzhou Medical University, Lishui, 323000, China. jijiansong@zju.edu.cn. 6. Department of Radiology, Affiliated Lishui Hospital of Zhejiang University/the Fifth Affiliated Hospital of Wenzhou Medical University/The Central Hospital of Zhejiang Lishui, Lishui, 323000, China. jijiansong@zju.edu.cn.
Abstract
OBJECTIVES: To develop and validate a pre-transcatheter arterial chemoembolization (TACE) MRI-based radiomics model for predicting tumor response in intermediate-advanced hepatocellular carcinoma (HCC) patients. MATERIALS: Ninety-nine intermediate-advanced HCC patients (69 for training, 30 for validation) treated with TACE were enrolled. MRI examinations were performed before TACE, and the efficacy was evaluated according to the mRECIST criterion 3 months after TACE. A total of 396 radiomics features were extracted from T2-weighted pre-TACE images, and least absolute shrinkage and selection operator (LASSO) regression was applied to feature selection and model construction. The performance of the model was evaluated by receiver operating characteristic (ROC) curves, calibration curves, and decision curves. RESULTS: The AFP value, Child-Pugh score, and BCLC stage showed a significant difference between the TACE response (TR) and non-TACE response (nTR) patients. Six radiomics features were selected by LASSO and the radiomics score (Rad-score) was calculated as the sum of each feature multiplied by the non-zero coefficient from LASSO. The AUCs of the ROC curve based on Rad-score were 0.812 and 0.866 in the training and validation cohorts, respectively. To improve the diagnostic efficiency, the Rad-score was further integrated with the above clinical indicators to form a novel predictive nomogram. Results suggested that the AUC increased to 0.861 and 0.884 in the training and validation cohorts, respectively. Decision curve analysis showed that the radiomics nomogram was clinically useful. CONCLUSION: The radiomics and clinical indicator-based predictive nomogram can well predict TR in intermediate-advanced HCC and can further be applied for auxiliary diagnosis of clinical prognosis. KEY POINTS: • The therapeutic outcome of TACE varies greatly even for patients with the same clinicopathologic features. • Radiomics showed excellent performance in predicting the TACE response. • Decision curves demonstrated that the novel predictive model based on the radiomics signature and clinical indicators has great clinical utility.
OBJECTIVES: To develop and validate a pre-transcatheter arterial chemoembolization (TACE) MRI-based radiomics model for predicting tumor response in intermediate-advanced hepatocellular carcinoma (HCC) patients. MATERIALS: Ninety-nine intermediate-advanced HCC patients (69 for training, 30 for validation) treated with TACE were enrolled. MRI examinations were performed before TACE, and the efficacy was evaluated according to the mRECIST criterion 3 months after TACE. A total of 396 radiomics features were extracted from T2-weighted pre-TACE images, and least absolute shrinkage and selection operator (LASSO) regression was applied to feature selection and model construction. The performance of the model was evaluated by receiver operating characteristic (ROC) curves, calibration curves, and decision curves. RESULTS: The AFP value, Child-Pugh score, and BCLC stage showed a significant difference between the TACE response (TR) and non-TACE response (nTR) patients. Six radiomics features were selected by LASSO and the radiomics score (Rad-score) was calculated as the sum of each feature multiplied by the non-zero coefficient from LASSO. The AUCs of the ROC curve based on Rad-score were 0.812 and 0.866 in the training and validation cohorts, respectively. To improve the diagnostic efficiency, the Rad-score was further integrated with the above clinical indicators to form a novel predictive nomogram. Results suggested that the AUC increased to 0.861 and 0.884 in the training and validation cohorts, respectively. Decision curve analysis showed that the radiomics nomogram was clinically useful. CONCLUSION: The radiomics and clinical indicator-based predictive nomogram can well predict TR in intermediate-advanced HCC and can further be applied for auxiliary diagnosis of clinical prognosis. KEY POINTS: • The therapeutic outcome of TACE varies greatly even for patients with the same clinicopathologic features. • Radiomics showed excellent performance in predicting the TACE response. • Decision curves demonstrated that the novel predictive model based on the radiomics signature and clinical indicators has great clinical utility.
Authors: Lindsey A Torre; Freddie Bray; Rebecca L Siegel; Jacques Ferlay; Joannie Lortet-Tieulent; Ahmedin Jemal Journal: CA Cancer J Clin Date: 2015-02-04 Impact factor: 508.702
Authors: Fahrettin Kucukay; Serife Badem; Adnan Karan; Mustafa Ozdemir; Riza S Okten; Nilgun I Ozbulbul; Murat B Kucukay; Ipek Unlu; Erdal B Bostanci; Meral Akdogan Journal: J Vasc Interv Radiol Date: 2015-08-28 Impact factor: 3.464