Imaging-Based Individualized Response Prediction Of Carbon Ion Radiotherapy For Prostate Cancer Patients

Shuang Wu; Yining Jiao; Yafang Zhang; Xuhua Ren; Ping Li; Qi Yu; Qing Zhang; Qian Wang; Shen Fu

doi:10.2147/CMAR.S214020

Imaging-Based Individualized Response Prediction Of Carbon Ion Radiotherapy For Prostate Cancer Patients

Cancer Manag Res. 2019 Oct 24:11:9121-9131. doi: 10.2147/CMAR.S214020. eCollection 2019.

Authors

Shuang Wu^#^{1

2}, Yining Jiao^#³, Yafang Zhang^{1

2}, Xuhua Ren³, Ping Li^{2

4}, Qi Yu^{1

2}, Qing Zhang^{2

4}, Qian Wang³, Shen Fu^{1

2

5

6}

Affiliations

¹ Department of Radiation Oncology, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital, Shanghai, People's Republic of China.
² Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy, Shanghai, People's Republic of China.
³ Institute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, People's Republic of China.
⁴ Department of Radiation Oncology, Shanghai Proton and Heavy Ion Center, Shanghai, People's Republic of China.
⁵ Key Laboratory of Nuclear Physics and Ion-beam Application MOE, Fudan University, Shanghai, People's Republic of China.
⁶ Department of Radiation Oncology, Shanghai Concord Cancer Hospital, Shanghai, People's Republic of China.

^# Contributed equally.

Abstract

Purpose: To explore the value of the pre-treatment MRI radiomic features in individualized prediction of the therapeutic response of carbon ion radiotherapy (CIRT) for prostate cancer patients.

Patients and methods: Twenty-three patients with localized prostate cancer treated by CIRT were enrolled for analysis. Prostate tumors were manually delineated on T2-weighted (T2w) images and apparent diffusion coefficient (ADC) maps acquired before CIRT. Abundant radiomic features were extracted from the delineations, which were randomly deformed to account for delineation uncertainty. The robust features were selected and then compared between patient groups of different CIRT responses. Support vector machine (SVM) was subsequently applied to demonstrate the role of the radiomic features to predict individualized CIRT response in the way of artificial intelligence.

Results: Radiomic features from ADC had significantly higher intra-correlation coefficient (ICC) (0.71±0.28) than T2w features (0.60±0.31) (p<0.01), indicating higher robustness of ADC features against delineation uncertainty. More features were excellently robust in ADC (58.2% of all the radiomic feature candidates, compared to 41.3% in T2w). By combining the excellently robust radiomic features of T2w and ADC, SVM achieved high performance to predict individualized therapeutic response of CIRT, ie, area-under-curve (AUC) = 0.88.

Conclusion: Radiomic features extracted from T2w and ADC images displayed great robustness to quantify the tumor characteristics of prostate cancer and high accuracy to predict the individualized therapeutic response of CIRT. After further validation, the selected radiomic features may become potential imaging biomarkers in the management of prostate cancer through CIRT.

Keywords: MRI; carbon ion radiotherapy; prostate cancer; radiomics.