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.

Evaluation of Radiosensitization and Cytokine Modulation by Differentially PEGylated Gold Nanoparticles in Glioblastoma Cells.

Glioblastoma (GBM) is known as the most aggressive type of malignant brain tumour, with an extremely poor prognosis of approximately 12 months following standard-of-care treatment with surgical resection, radiotherapy (RT), and temozolomide treatment. Novel RT-drug combinations are urgently needed to improve patient outcomes. Gold nanoparticles (GNPs) have demonstrated significant preclinical potential as radiosensitizers due to their unique physicochemical properties and their ability to pass the blood-brain barrier. The modification of GNP surface coatings with poly(ethylene) glycol (PEG) confers several therapeutic advantages including immune avoidance and improved cellular localisation. This study aimed to characterise both the radiosensitizing and immunomodulatory properties of differentially PEGylated GNPs in GBM cells in vitro. Two GBM cell lines were used, U-87 MG and U-251 MG. The radiobiological response was evaluated by clonogenic assay, immunofluorescent staining of 53BP1 foci, and flow cytometry. Changes in the cytokine expression levels were quantified by cytokine arrays. PEGylation improved the radiobiological efficacy, with double-strand break induction being identified as an underlying mechanism. PEGylated GNPs also caused the greatest boost in RT immunogenicity, with radiosensitization correlating with a greater upregulation of inflammatory cytokines. These findings demonstrate the radiosensitizing and immunostimulatory potential of ID11 and ID12 as candidates for RT-drug combination in future GBM preclinical investigations.