Utilization of Radiomics to Predict Radiation Associated Cardiovascular Morbidity in Lung SBRT

Abstract

<h3>Purpose/Objective(s)</h3> SBRT for early lung cancers is now considered standard of care for some patients, but there is increasing evidence linking long-term cardiac toxicity with cardiovascular dose. While the dose constraints for aortic radiation exposure are still unclear, there is accumulating data that higher aortic doses can be associated with mortality. Our study explores the link between central thoracic radiation and early radiomic changes, determining if these radiomic changes are associated with relevant cardiovascular toxicity. This information will allow us to identify the most relevant dosing information for a variety of central thoracic organs in predicting cardiovascular toxicity from SBRT to lung. <h3>Materials/Methods</h3> We analyzed 27 patients who received SBRT to lung tumors with curative intent. Pretreatment and post treatment contrast enhanced diagnostic CT scans were accessed. The following structures were manually contoured by a medical student and reviewed by an MD: aorta, vena cava, pulmonary artery, heart, L atrium, R atrium, L ventricle, R Ventricle, and septum. For this analysis, the aorta was divided in to 10 equal sections along the inferior/superior direction. 1) 168 radiomic features were extracted for each section of the aorta wall for all 27 patients. (Mean value /standard deviation >10) between patients was used as a criterion to determine the useful and stable features. 2) dose dependent aortic wall volumes for 26 pre and post (up to 4.5 years post) treatment contrast enhanced CT scans were evaluated for the radiomic feature changes with dose. <h3>Results</h3> 1) Only 13 radiomic features were deemed stable according to our radiomic feature analysis between patients across all 10 sections of the aortic wall. These include 4 Gray-Level Co-occurrence Matrix (GLCM) features, 1 Gray Level Dependence Matrix (GLDM) feature, 5 Gray-Level Run-Length Matrix (GLRLM) features, and 3 Gray Level Size Zone Matrix (GLSZM) feature. 2) Early results indicate that no statistically significant radiomic changes of these 13 parameters were observed post SBRT to lung up to 4.5 years even with a dose of 55 Gy to the aorta. These observations were confirmed by the patient's clinical status. <h3>Conclusion</h3> Preliminary analysis suggests that radiomic features for contrast enhanced CTs could be used to evaluate the absence of radiation damage to cardiovascular structures.