Dose-dependent changes in cardiac function, strain and remodelling in a preclinical model of heart base irradiation.

BACKGROUND AND PURPOSE: Radiation induced cardiotoxicity (RICT) is as an important sequela of radiotherapy to the thorax for patients. In this study, we aim to investigate the dose and fractionation response of RICT. We propose global longitudinal strain (GLS) as an early indicator of RICT and investigate myocardial deformation following irradiation. METHODS: RICT was investigated in female C57BL/6J mice in which the base of the heart was irradiated under image-guidance using a small animal radiation research platform (SARRP). Mice were randomly assigned to a treatment group: single-fraction dose of 16 Gy or 20 Gy, 3 consecutive fractions of 8.66 Gy, or sham irradiation; biological effective doses (BED) used were 101.3 Gy, 153.3 Gy and 101.3 Gy respectively. Longitudinal transthoracic echocardiography (TTE) was performed from baseline up to 50 weeks post-irradiation to detect structural and functional effects. RESULTS: Irradiation of the heart base leads to BED-dependent changes in systolic and diastolic function 50 weeks post-irradiation. GLS showed significant decreases in a BED-dependent manner for all irradiated animals, as early as 10 weeks after irradiation. Early changes in GLS indicate late changes in cardiac function. BED-independent increases were observed in the left ventricle (LV) mass and volume and myocardial fibrosis. CONCLUSIONS: Functional features of RICT displayed a BED dependence in this study. GLS showed an early change at 10 weeks post-irradiation. Cardiac remodelling was observed as increases in mass and volume of the LV, further supporting our hypothesis that dose to the base of the heart drives the global heart toxicity.

Characterisation of quantitative imaging biomarkers for inflammatory and fibrotic radiation-induced lung injuries using preclinical radiomics.

BACKGROUND AND PURPOSE: Radiomics is a rapidly evolving area of research that uses medical images to develop prognostic and predictive imaging biomarkers. In this study, we aimed to identify radiomics features correlated with longitudinal biomarkers in preclinical models of acute inflammatory and late fibrotic phenotypes following irradiation. MATERIALS AND METHODS: Female C3H/HeN and C57BL6 mice were irradiated with 20 Gy targeting the upper lobe of the right lung under cone-beam computed tomography (CBCT) image-guidance. Blood samples and lung tissue were collected at baseline, weeks 1, 10 & 30 to assess changes in serum cytokines and histological biomarkers. The right lung was segmented on longitudinal CBCT scans using ITK-SNAP. Unfiltered and filtered (wavelet) radiomics features (n = 842) were extracted using PyRadiomics. Longitudinal changes were assessed by delta analysis and principal component analysis (PCA) was used to remove redundancy and identify clustering. Prediction of acute (week 1) and late responses (weeks 20 & 30) was performed through deep learning using the Random Forest Classifier (RFC) model. RESULTS: Radiomics features were identified that correlated with inflammatory and fibrotic phenotypes. Predictive features for fibrosis were detected from PCA at 10 weeks yet overt tissue density was not detectable until 30 weeks. RFC prediction models trained on 5 features were created for inflammation (AUC 0.88), early-detection of fibrosis (AUC 0.79) and established fibrosis (AUC 0.96). CONCLUSIONS: This study demonstrates the application of deep learning radiomics to establish predictive models of acute and late lung injury. This approach supports the wider application of radiomics as a non-invasive tool for detection of radiation-induced lung complications.