AUTHOR=Nie Ke , Hu Peng , Zheng Jianjun , Zhang Yang , Yang Pengfei , Jabbour Salma K. , Yue Ning , Dong Xue , Xu Shufeng , Shen Bo , Niu Tianye , Hu Xiaotong , Cai Xiujun , Sun Jihong 

TITLE=Incremental Value of Radiomics in 5-Year Overall Survival Prediction for Stage II–III Rectal Cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.779030

DOI=10.3389/fonc.2022.779030

ISSN=2234-943X

ABSTRACT=Although rectal cancer comprising up one third of colorectal cancer cases and several prognosis nomograms having been established for colon cancer, statistical tools for predicting long-term survival in rectal cancer are lacking. In addition, previous prognostic studies did not include imaging findings, despite MRI is an indispensable tool for rectal cancer diagnosis and treatment assessment. Therefore, we include multi-parametric MRI information from both radiologist’s readings and quantitative radiomics signatures, to construct a prognostic model that allows 5-year overall survival (OS) prediction for advance staged rectal cancer patients. The model with combined imaging and non-imaging information outperforms than that of TNM staging or clinical-histopathological prognostic factors. Findings are confirmed in the validation set. It is noteworthy that the identified radiomics signature consisted of three from dynamic MRI, four from anatomical MRI and one from functional DWI. This study provides data that underlines the importance of multi-parametric MRI, to our knowledge, as the first attempt to address the issue of long-term survival estimation in rectal cancer. The radiomics signature adds incremental value to the conventional prognostic factors in predicting 5-year OS for stage II-III rectal cancer. The presented nomogram also provides a practical example of individualized prognosis estimation and may potentially impact treatment strategies.