ESTRO 37 Abstract book

S1154

ESTRO 37

models may not be generalisable. Test-retest imaging is the recommended method for assessing feature robustness, but is tumour phenotype-specific. A test- retest experiment would thus be required for each radiomics study, incurring additional costs in terms of patient preparation, imaging and additional imaging dose. Therefore we asses feature robustness using single images as a surrogate and compare these with test-retest results. Material and Methods Two patient cohorts with test-retest CT imaging were used: a public NSCLC cohort of 31 patients [1] and an HNSCC cohort of 19 patients. For the NSCLC cohort, two separate images were acquired within 15 minutes of each other using the same scanner and protocol. Images in the HNSCC cohort were acquired within 4 days of each other with different scanners and protocols. The gross tumour volume (GTV) was contoured and 5571 features were extracted from the GTV of each image. Image perturbation was used to assess robustness from single images. Images were perturbed by adding image noise, performing sub-voxel translation, rotation, and contour randomisation, where contour boundaries are altered based on overlap of supervoxels with the GTV. Feature robustness between test-retest images and between perturbations of a single image was measured using the intraclass correlation coefficient (ICC). Features with ICC ≥ 0.85 were considered to be robust. [1] Zhao, B., et al. "Evaluating variability in tumor measurements from same-day repeat CT scans of patients with non–small cell lung cancer." Radiology 252.1 (2009): 263-272. Results We identified 3831 and 1123 robust features for test- retest imaging for the NSCLC and HNSCC cohorts, respectively, see Figure 1. Features in the HNSCC cohort were generally less reproducible compared to the NSCLC cohort. The largest overlap between non-robust features identified by test-retest imaging and single image perturbation existed for rotation with randomised contours with 96% and 86% for NSCLC and HNSCC cohorts, respectively .

provides a suitable alternative to test-retest imaging that is easily available in clinical routine. EP-2096 Sodium-MRI at ultra-high magnetic fields for early response assessment in brain tumors S. Regnery 1,2 , N. Behl 3 , D. Paech 4 , H.P. Schlemmer 4 , M.E. Ladd 3 , A. Nagel 3,5 , S. Rieken 1,2 , J. Debus 1,2 , S. Adeberg 1,2 1 University Hospital Heidelberg, Department of Radiation Oncology, Heidelberg, Germany 2 German Cancer Research Center DKFZ, Clinical Cooperation Unit Radiation Oncology, Heidelberg, Germany 3 German Cancer Research Center DKFZ, Division of Medical Physics in Radiology, Heidelberg, Germany 4 German Cancer Research Center DKFZ, Division of Radiology, Heidelberg, Germany 5 University Hospital Erlangen, Institute of Radiology, Erlangen, Germany Purpose or Objective Radiotherapy is a cornerstone in the treatment of glioblastoma and skull-base-meningioma. At present, the response assessment is mainly based on contrast- enhanced T1- and T2-weighted MRI images acquired at 3 Tesla with its well-known limitations. The increasing utilization of ultra-high magnetic fields with enhanced signal-to-noise-ratio bears great potential to enhance biological imaging. In this context, sodium-MRI is an emerging approach for tumor characterization and response evaluation. Here we present the first results of a prospective longitudinal study employing sodium-MRI on a 7-Tesla-scanner during radiotherapy of brain tumors. Material and Methods Three glioblastoma and four meningioma patients under- went imaging on a 7T-MRI-scanner (Siemens Healthineers, Erlangen, Germany) in addition to the standard 3T-MRI- protocol before, during and after definitive treatment. High-resolution T2-TSE and T2-FLAIR-imaging was performed using a 24-channel single resonant head coil. Sodium-MR-images were acquired with a double-resonant (1H/23Na) quadrature birdcage coil using a house made density-adapted 3D radial projection pulse sequence and an iterative 3D-DLCS reconstruction algorithm. 7T- and clinical 3T-MRI-images from different time points were co-registered manually using MITK. ROIs were delineated on clinical standard imaging by an experienced radiation oncologist: regions with T1-weighted Gadolinium- contrast-enhancement (gdce) representing tumorous tissue, regions of T2-FLAIR-hyperintensity representing edema and normal-appearing-white-matter (nawm). Furthermore, response evaluation was done according to RANO-criteria. Results In all glioblastoma patients, clear changes in sodium mean signal can be observed in regions of tumorous tissue and edema (Fig. 1).

Conclusion An essential step in radiomic analyses is the selection of features that are insensitive to different imaging protocols and equipment, and inter-observer variability. We demonstrated that perturbing single images by rotations combined with random contour alteration

Furthermore, there is a tendency towards decreasing sodium values in tumorous tissue and edema in therapy responders, whereas the opposite is true for the non- responder. This tendency already becomes obvious in the