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

• Published in: Radiotherapy and oncology Vol. 192; p. 110106
• Main Authors: Brown, Kathryn H., Ghita-Pettigrew, Mihaela, Kerr, Brianna N., Mohamed-Smith, Letitia, Walls, Gerard M., McGarry, Conor K., Butterworth, Karl T.
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.03.2024
• Subjects: Animals; Biomarkers; Female; Fibrosis; Imaging biomarkers; Lung - diagnostic imaging; Lung - pathology; Lung Injury - diagnostic imaging; Lung Injury - etiology; Lung Injury - pathology; Lung Neoplasms - pathology; Mice; Mice, Inbred C3H; Mice, Inbred C57BL; Preclinical models; Prediction models; Pulmonary fibrosis; Radiation Injuries - pathology; Radiation pneumonitis; Radiomics; Retrospective Studies; Tomography, X-Ray Computed - methods; Pulmonary fibrosis; Prediction models; Imaging biomarkers; Preclinical models; Radiomics; Radiation pneumonitis
• ISSN: 0167-8140; 1879-0887; 1879-0887
• DOI: 10.1016/j.radonc.2024.110106

•Cone beam computed tomography (CBCT) radiomics can differentiate preclinical models of inflammatory and fibrotic radiation-induced lung injury.•Radiomics features were correlated with inflammatory and fibrotic phenotypes based on cytokine expression and histology.•Deep learning radiomics was used to establish predictive models of acute and late radiation-induced lung injury.•Preclinical CBCT radiomics is a non-invasive tool that can be used to develop prediction models for clinically relevant radiotherapy toxicities. 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. 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. 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). 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.