Haimei Chen1, Xiao Zhang2, Xiaohong Wang3, Xianyue Quan4, Yu Deng5, Ming Lu6, Qingzhu Wei7, Qiang Ye1, Quan Zhou1, Zhiming Xiang8, Changhong Liang9, Wei Yang10, Yinghua Zhao11. 1. Department of Radiology, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics. Guangdong Province), 183 Zhongshan Da Dao Xi, Guangzhou, 510630, Guangdong, China. 2. Zhuhai Precision Medical Center, Zhuhai People's Hospital (Zhuhai Hospital Affiliated with Jinan University), Zhuhai, 519000, Guangdong, China. 3. Department of Radiology, The Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, 510630, Guangdong, China. 4. Department of Radiology, Zhujiang Hospital of Southern Medical University, Guangzhou, 510282, Guangdong, China. 5. Department of Radiology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, 510120, Guangdong, China. 6. Department of Oncology, The Third Affiliated Hospital of Southern Medical University, Guangzhou, 510630, Guangdong, China. 7. Department of Pathology, The Third Affiliated Hospital of Southern Medical University, Guangzhou, 510630, Guangdong, China. 8. Department of Radiology, Panyu Central Hospital of Guangzhou, Guangzhou, 511400, Guangdong, China. 9. Department of Radiology, Guangdong General Hospital, Guangdong Academy of Medical Sciences, Guangzhou, 510080, Guangdong, China. 10. Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Baiyun District, Guangzhou, 510515, Guangdong, China. weiyanggm@gmail.com. 11. Department of Radiology, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics. Guangdong Province), 183 Zhongshan Da Dao Xi, Guangzhou, 510630, Guangdong, China. zyh7258957@163.com.
Abstract
OBJECTIVE: To develop and validate a radiomics signature based on magnetic resonance imaging (MRI) from multicenter datasets for preoperative prediction of pathologic response to neoadjuvant chemotherapy (NAC) in patients with osteosarcoma. METHODS: We retrospectively enrolled 102 patients with histologically confirmed osteosarcoma who received chemotherapy before treatment from 4 hospitals (68 in the primary cohort and 34 in the external validation cohort). Quantitative imaging features were extracted from contrast-enhanced fat-suppressed T1-weighted images (CE FS T1WI). Four classification methods, i.e., the least absolute shrinkage and selection operator logistic regression (LASSO-LR), support vector machine (SVM), Gaussian process (GP), and Naive Bayes (NB) algorithm, were compared for feature selection and radiomics signature construction. The predictive performance of the radiomics signatures was assessed with the area under receiver operating characteristics curve (AUC), calibration curve, and decision curve analysis (DCA). RESULTS: Thirteen radiomics features selected based on the LASSO-LR classifier were adopted to construct the radiomics signature, which was significantly associated with the pathologic response. The prediction model achieved the best performance between good and poor responders with an AUC of 0.882 (95% CI, 0.837-0.918) in the primary cohort. Calibration curves showed good agreement. Similarly, findings were validated in the external validation cohort with good performance (AUC, 0.842 [95% CI, 0.793-0.883]) and good calibration. DCA analysis confirmed the clinical utility of the selected radiomics signature. CONCLUSION: The constructed CE FS T1WI-radiomics signature with excellent performance could provide a potential tool to predict pathologic response to NAC in patients with osteosarcoma. KEY POINTS: • The radiomics signature based on multicenter contrast-enhanced MRI was useful to predict response to NAC. • The prediction model obtained with the LASSO-LR classifier achieved the best performance. • The baseline clinical characteristics were not associated with response to NAC.
OBJECTIVE: To develop and validate a radiomics signature based on magnetic resonance imaging (MRI) from multicenter datasets for preoperative prediction of pathologic response to neoadjuvant chemotherapy (NAC) in patients with osteosarcoma. METHODS: We retrospectively enrolled 102 patients with histologically confirmed osteosarcoma who received chemotherapy before treatment from 4 hospitals (68 in the primary cohort and 34 in the external validation cohort). Quantitative imaging features were extracted from contrast-enhanced fat-suppressed T1-weighted images (CE FS T1WI). Four classification methods, i.e., the least absolute shrinkage and selection operator logistic regression (LASSO-LR), support vector machine (SVM), Gaussian process (GP), and Naive Bayes (NB) algorithm, were compared for feature selection and radiomics signature construction. The predictive performance of the radiomics signatures was assessed with the area under receiver operating characteristics curve (AUC), calibration curve, and decision curve analysis (DCA). RESULTS: Thirteen radiomics features selected based on the LASSO-LR classifier were adopted to construct the radiomics signature, which was significantly associated with the pathologic response. The prediction model achieved the best performance between good and poor responders with an AUC of 0.882 (95% CI, 0.837-0.918) in the primary cohort. Calibration curves showed good agreement. Similarly, findings were validated in the external validation cohort with good performance (AUC, 0.842 [95% CI, 0.793-0.883]) and good calibration. DCA analysis confirmed the clinical utility of the selected radiomics signature. CONCLUSION: The constructed CE FS T1WI-radiomics signature with excellent performance could provide a potential tool to predict pathologic response to NAC in patients with osteosarcoma. KEY POINTS: • The radiomics signature based on multicenter contrast-enhanced MRI was useful to predict response to NAC. • The prediction model obtained with the LASSO-LR classifier achieved the best performance. • The baseline clinical characteristics were not associated with response to NAC.
Entities:
Keywords:
Logistic models; Magnetic resonance imaging; Neoadjuvant therapy; Osteosarcoma
Authors: Paul A Meyers; Cindy L Schwartz; Mark Krailo; Eugenie S Kleinerman; Donna Betcher; Mark L Bernstein; Ernest Conrad; William Ferguson; Mark Gebhardt; Allen M Goorin; Michael B Harris; John Healey; Andrew Huvos; Michael Link; Joseph Montebello; Helen Nadel; Michael Nieder; Judith Sato; Gene Siegal; Michael Weiner; Robert Wells; Lester Wold; Richard Womer; Holcombe Grier Journal: J Clin Oncol Date: 2005-03-20 Impact factor: 44.544
Authors: G Bacci; S Ferrari; F Bertoni; P Ruggieri; P Picci; A Longhi; R Casadei; N Fabbri; C Forni; M Versari; M Campanacci Journal: J Clin Oncol Date: 2000-12-15 Impact factor: 44.544
Authors: Allen M Goorin; Douglas J Schwartzentruber; Meenakshi Devidas; Mark C Gebhardt; Alberto G Ayala; Michael B Harris; Lee J Helman; Holcombe E Grier; Michael P Link Journal: J Clin Oncol Date: 2003-04-15 Impact factor: 44.544
Authors: Lawrence M White; Angela Atinga; Ali M Naraghi; Katherine Lajkosz; Jay S Wunder; Peter Ferguson; Kim Tsoi; Anthony Griffin; Masoom Haider Journal: Skeletal Radiol Date: 2022-07-01 Impact factor: 2.199
Authors: Yang Li; Ping Yin; Yang Liu; Chuanxi Hao; Lei Chen; Chao Sun; Sicong Wang; Nan Hong Journal: Biomed Res Int Date: 2022-09-05 Impact factor: 3.246