Ming Fan1, Peng Zhang1, Yue Wang2, Weijun Peng3, Shiwei Wang4, Xin Gao5, Maosheng Xu6, Lihua Li7. 1. Institute of Biomedical Engineering and Instrumentation, Hangzhou Dianzi University, Hangzhou, China. 2. Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Arlington, VA, 22203, USA. 3. Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China. 4. Department of Radiology, First Affiliated Hospital of Zhejiang Chinese Medical University, Zhejiang, Hangzhou, China. 5. Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Saudi Arabia. 6. Department of Radiology, First Affiliated Hospital of Zhejiang Chinese Medical University, Zhejiang, Hangzhou, China. 1243454330@qq.com. 7. Institute of Biomedical Engineering and Instrumentation, Hangzhou Dianzi University, Hangzhou, China. lilh@hdu.edu.cn.
Abstract
OBJECTIVES: This study aimed to predict the molecular subtypes of breast cancer via intratumoural and peritumoural radiomic analysis with subregion identification based on the decomposition of contrast-enhanced magnetic resonance imaging (DCE-MRI). METHODS: The study included 211 women with histopathologically confirmed breast cancer. We utilised a completely unsupervised convex analysis of mixtures (CAM) method by unmixing dynamic imaging series from heterogeneous tissues. Each tumour and the surrounding parenchyma were thus decomposed into multiple subregions, representing different vascular characterisations, from which radiomic features were extracted. A random forest model was trained and tested using a leave-one-out cross-validation (LOOCV) method to predict breast cancer subtypes. The predictive models from tumoural and peritumoural subregions were fused for classification. RESULTS: Tumour and peritumour DCE-MR images were decomposed into three compartments, representing plasma input, fast-flow kinetics, and slow-flow kinetics. The tumour subregion related to fast-flow kinetics showed the best performance among the subregions for differentiating between patients with four molecular subtypes (area under the receiver operating characteristic curve (AUC) = 0.832), exhibiting an AUC value significantly (p < 0.0001) higher than that obtained with the entire tumour (AUC = 0.719). When the tumour- and parenchyma-based predictive models were fused, the performance, measured as the AUC, increased to 0.897; this value was significantly higher than that obtained with other tumour partition methods. CONCLUSIONS: Radiomic analysis of intratumoural and peritumoural heterogeneity based on the decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features and serve as a valuable clinical marker to enhance the prediction of breast cancer subtypes. KEY POINTS: • Decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features. • Fusion of intratumoural- and peritumoural-based predictive models improves the prediction of breast cancer subtypes.
OBJECTIVES: This study aimed to predict the molecular subtypes of breast cancer via intratumoural and peritumoural radiomic analysis with subregion identification based on the decomposition of contrast-enhanced magnetic resonance imaging (DCE-MRI). METHODS: The study included 211 women with histopathologically confirmed breast cancer. We utilised a completely unsupervised convex analysis of mixtures (CAM) method by unmixing dynamic imaging series from heterogeneous tissues. Each tumour and the surrounding parenchyma were thus decomposed into multiple subregions, representing different vascular characterisations, from which radiomic features were extracted. A random forest model was trained and tested using a leave-one-out cross-validation (LOOCV) method to predict breast cancer subtypes. The predictive models from tumoural and peritumoural subregions were fused for classification. RESULTS:Tumour and peritumour DCE-MR images were decomposed into three compartments, representing plasma input, fast-flow kinetics, and slow-flow kinetics. The tumour subregion related to fast-flow kinetics showed the best performance among the subregions for differentiating between patients with four molecular subtypes (area under the receiver operating characteristic curve (AUC) = 0.832), exhibiting an AUC value significantly (p < 0.0001) higher than that obtained with the entire tumour (AUC = 0.719). When the tumour- and parenchyma-based predictive models were fused, the performance, measured as the AUC, increased to 0.897; this value was significantly higher than that obtained with other tumour partition methods. CONCLUSIONS: Radiomic analysis of intratumoural and peritumoural heterogeneity based on the decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features and serve as a valuable clinical marker to enhance the prediction of breast cancer subtypes. KEY POINTS: • Decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features. • Fusion of intratumoural- and peritumoural-based predictive models improves the prediction of breast cancer subtypes.
Entities:
Keywords:
Breast neoplasms; Diagnostic imaging; Magnetic resonance imaging
Authors: M Elizabeth H Hammond; Daniel F Hayes; Antonio C Wolff; Pamela B Mangu; Sarah Temin Journal: J Oncol Pract Date: 2010-06-23 Impact factor: 3.840
Authors: Li Chen; Tsung-Han Chan; Peter L Choyke; Elizabeth M C Hillman; Chong-Yung Chi; Zaver M Bhujwalla; Ge Wang; Sean S Wang; Zsolt Szabo; Yue Wang Journal: Bioinformatics Date: 2011-07-23 Impact factor: 6.937
Authors: Li Chen; Peter L Choyke; Tsung-Han Chan; Chong-Yung Chi; Ge Wang; Yue Wang Journal: IEEE Trans Med Imaging Date: 2011-06-23 Impact factor: 10.048
Authors: Ke Nie; Jeon-Hor Chen; Siwa Chan; Man-Kwun I Chau; Hon J Yu; Shadfar Bahri; Tiffany Tseng; Orhan Nalcioglu; Min-Ying Su Journal: Med Phys Date: 2008-12 Impact factor: 4.071
Authors: Mingquan Lin; Jacob F Wynne; Boran Zhou; Tonghe Wang; Yang Lei; Walter J Curran; Tian Liu; Xiaofeng Yang Journal: J Appl Clin Med Phys Date: 2021-06-24 Impact factor: 2.102