Zheng Guo1,2, Nanying Zhong3, Xueming Xu4, Yu Zhang4, Xiaoning Luo4, Huabin Zhu3, Xiufang Zhang3, Di Wu5, Yingwei Qiu6,7, Fuping Tu4. 1. Department of Oncology, Ganzhou Key Laboratory of Gastrointestinal Carcinomas, First Affiliated Hospital of Gannan Medical University, Gannan Medical University, Ganzhou, Jiangxi, People's Republic of China. 2. Department of Hematology and Oncology, International Cancer Center, Shenzhen Key Laboratory of Precision Medicine for Hematological Malignancies, Shenzhen University General Hospital, Shenzhen University Clinical Medical Academy, Shenzhen University Health Science Center, Shenzhen, Guangdong, People's Republic of China. 3. First School of Clinical Medicine, Gannan Medical University, Ganzhou, Jiangxi, People's Republic of China. 4. Department of Oncology, First Affiliated Hospital of Gannan Medical University, Gannan Medical University, Ganzhou, Jiangxi, People's Republic of China. 5. Department of Imaging, First Affiliated Hospital of Gannan Medical University, Gannan Medical University, Ganzhou, Jiangxi, People's Republic of China. 6. Department of Radiology, The Third Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical University, Guangzhou, Guangdong, People's Republic of China. 7. Department of Radiology, Huazhong University of Science and Technology Union Shenzhen Hospital, Shenzhen, Guangdong, People's Republic of China.
Abstract
OBJECTIVE: To construct a predictive model of short-term response and overall survival for transcatheter arterial chemoembolization (TACE) treatment in hepatocellular carcinoma (HCC) patients based on non-contrast computed tomography (NC-CT) radiomics and clinical features. METHODS: Ninety-four HCC patients who underwent CT scanning 1 week before the first TACE treatment were retrospectively recruited and divided randomly into a training group (n = 47) and a validation group (n = 47). NC-CT radiomics data were extracted using MaZda software, and the compound model was calculated from radiomics and clinical features by logistic regression. The performance of the different models was compared by examining the area under the receiver operating characteristic curve (AUC). The prediction of prognosis was evaluated using survival analysis. RESULTS: Thirty NC-CT radiomic features were extracted and analyzed. The compound model was formed using four NC-CT run-length matrix (RLM) features and general image features, which included the maximum diameter (cm) of the tumor and the number of tumors (n). The AUCs of the model for TACE response were 0.840 and 0.815, whereas the AUCs of the six-and-twelve grade were 0.754 and 0.750 in the training and validation groups, respectively. HCC patients were divided into two groups using the cutoff value of the model: a group in which the TACE-response led to good survival and a group in which TACE-nonresponse caused poor prognosis. CONCLUSION: Radiomic features from NC-CT predicted TACE-response. The compound model generated by NC-CT radiomics and clinical features is effective and directly predicts TACE-response and overall survival. The model may be used repeatedly and is easy to operate.
OBJECTIVE: To construct a predictive model of short-term response and overall survival for transcatheter arterial chemoembolization (TACE) treatment in hepatocellular carcinoma (HCC) patients based on non-contrast computed tomography (NC-CT) radiomics and clinical features. METHODS: Ninety-four HCC patients who underwent CT scanning 1 week before the first TACE treatment were retrospectively recruited and divided randomly into a training group (n = 47) and a validation group (n = 47). NC-CT radiomics data were extracted using MaZda software, and the compound model was calculated from radiomics and clinical features by logistic regression. The performance of the different models was compared by examining the area under the receiver operating characteristic curve (AUC). The prediction of prognosis was evaluated using survival analysis. RESULTS: Thirty NC-CT radiomic features were extracted and analyzed. The compound model was formed using four NC-CT run-length matrix (RLM) features and general image features, which included the maximum diameter (cm) of the tumor and the number of tumors (n). The AUCs of the model for TACE response were 0.840 and 0.815, whereas the AUCs of the six-and-twelve grade were 0.754 and 0.750 in the training and validation groups, respectively. HCC patients were divided into two groups using the cutoff value of the model: a group in which the TACE-response led to good survival and a group in which TACE-nonresponse caused poor prognosis. CONCLUSION: Radiomic features from NC-CT predicted TACE-response. The compound model generated by NC-CT radiomics and clinical features is effective and directly predicts TACE-response and overall survival. The model may be used repeatedly and is easy to operate.
Authors: L X Xu; M H He; Z H Dai; J Yu; J G Wang; X C Li; B B Jiang; Z F Ke; T H Su; Z W Peng; Y Guo; Z B Chen; S L Chen; S Peng; M Kuang Journal: Ann Oncol Date: 2019-06-01 Impact factor: 32.976
Authors: L-T Chen; E Martinelli; A-L Cheng; G Pentheroudakis; S Qin; G S Bhattacharyya; M Ikeda; H-Y Lim; G F Ho; S P Choo; Z Ren; H Malhotra; M Ueno; B-Y Ryoo; T C Kiang; D Tai; A Vogel; A Cervantes; S-N Lu; C-J Yen; Y-H Huang; S-C Chen; C Hsu; Y-C Shen; J Tabernero; Y Yen; C-H Hsu; T Yoshino; J-Y Douillard Journal: Ann Oncol Date: 2019-12-20 Impact factor: 32.976
Authors: L Kadalayil; R Benini; L Pallan; J O'Beirne; L Marelli; D Yu; A Hackshaw; R Fox; P Johnson; A K Burroughs; D H Palmer; T Meyer Journal: Ann Oncol Date: 2013-07-14 Impact factor: 32.976
Authors: Guohong Han; Sarah Berhane; Hidenori Toyoda; Dominik Bettinger; Omar Elshaarawy; Anthony W H Chan; Martha Kirstein; Cristina Mosconi; Florian Hucke; Daniel Palmer; David J Pinato; Rohini Sharma; Diego Ottaviani; Jeong W Jang; Tim A Labeur; Otto M van Delden; Mario Pirisi; Nick Stern; Bruno Sangro; Tim Meyer; Waleed Fateen; Marta García-Fiñana; Asmaa Gomaa; Imam Waked; Eman Rewisha; Guru P Aithal; Simon Travis; Masatoshi Kudo; Alessandro Cucchetti; Markus Peck-Radosavljevic; R B Takkenberg; Stephen L Chan; Arndt Vogel; Philip J Johnson Journal: Hepatology Date: 2020-05-27 Impact factor: 17.425