Valvular Heart Disease (VHD) is a known late complication of radiotherapy for childhood cancer (CC), and identifying high-risk survivors correctly remains a challenge. This paper focuses on the distribution of the radiation dose absorbed by heart tissues. We propose that a dosiomics signature could provide insight into the spatial characteristics of the heart dose associated with a VHD, beyond the already-established risk induced by high doses. We analyzed data from the 7670 survivors of the French Childhood Cancer Survivors’ Study (FCCSS), 3902 of whom were treated with radiotherapy. In all, 63 (1.6%) survivors that had been treated with radiotherapy experienced a VHD, and 57 of them had heterogeneous heart doses. From the heart–dose distribution of each survivor, we extracted 93 first-order and spatial dosiomics features. We trained random forest algorithms adapted for imbalanced classification and evaluated their predictive performance compared to the performance of standard mean heart dose (MHD)-based models. Sensitivity analyses were also conducted for sub-populations of survivors with spatially heterogeneous heart doses. Our results suggest that MHD and dosiomics-based models performed equally well globally in our cohort and that, when considering the sub-population having received a spatially heterogeneous dose distribution, the predictive capability of the models is significantly improved by the use of the dosiomics features. If these findings are further validated, the dosiomics signature may be incorporated into machine learning algorithms for radiation-induced VHD risk assessment and, in turn, into the personalized refinement of follow-up guidelines.

Background: Valvular Heart Disorder (VHD) is a known complication of childhood cancer after radiotherapy treatment. However, the dose-volume-effect relationships have not been fully explored. Methods: We obtained individual heart Dose Volume Histograms (DVH) for each French Childhood Cancer Survivors Study (FCCSS) patient who had received radiotherapy. We calculated the Mean Dose to the Heart (MHD), as well as the heart DVH parameters (Vd, which represent the percentage of heart volume receiving at least d Gy) calculated for 0.1 (V0.1), 5 (V5), 20 (V20) and 40 Gy (V40). We also analyzed V0.1, V5, and V20 in survivors with a maximum dose to the heart of less than 5 (V0.1 |_V5=0%), 20 (V5 |_V20=0%) and 40Gy (V20 |_V40=0%), respectively. We investigated their role in the occurrence of VHD using the Cox proportional hazard models adjusting for cancer diagnosis age and chemotherapy exposure. Results: Eighty-one patients developed a severe VHD (grade ≥3). Radiotherapy was significantly associated with increased VHD risk (Hazard ratio (HR) = 1.97 95% confidence intervals (95% CI): 1.16 - 3.36) and was much higher when MHD was over 15 Gy (HR = 7.63, 95% CI: 4.39 - 13.29). Strong doses to small heart-volume (V40 <10%) as well as weak doses to a large heart-volume (V5 | V20=0% <90%) were associated with VHD risk (HR = 5.53, 95% CI: 2.59-11.81 and HR = 3.93, 95% CI: 1.15-13.48, respectively). Conclusions: Our results provide new insight into the VHD-risk that may impact current treatments as well as long-term follow-up of childhood cancer survivors.