ESTRO 36 Abstract Book

S907 ESTRO 36 2017 _______________________________________________________________________________________________

The optimal window for assessing the responsiveness to treatment based on αeff calculations derived from repeated FDG PET scans in NSCLC patients appears to be the second week of the treatment but validation on a larger cohort of patients is warranted. [1] Toma-Dasu I, Uhrdin J, Lazzeroni M, Carvalho S, van Elmpt W, Lambin P, Dasu A. Evaluating tumor response of non-small cell lung cancer patients with 18F- fludeoxyglucose positron emission tomography: potential for treatment individualization. Int J Radiat Oncol Biol Phys. 2015 1;91(2):376-84. EP-1685 CT-Radiomics outperforms FMISO-PET/CT for the prediction of local control in head-and-neck cancer J.A. Socarras Fernandez 1 , D. Mönnich 1 , F. Lippert 1 , D. Welz 2 , C. Pfannenberg 3 , C. La Fougere 4 , G. Reischl 5 , D. Zips 2 , D. Thorwarth 1 1 University Hospital Tübingen, Radiation Oncology - Section for Biomedical Physics, Tübingen, Germany 2 University Hospital Tübingen, Radiation Oncology, Tübingen, Germany 3 University Hospital Tübingen, Diagnostic and Interventional Radiology, Tübingen, Germany 4 University Hospital Tübingen, Radiology - Section of Nuclear Medicine, Tübingen, Germany 5 University Hospital Tübingen, Radiology - Section of Radiopharmacy, Tübingen, Germany Purpose or Objective FMISO-PET has proven to capture probabilities of hypoxia in tumors, which may predict risks of local recurrence across patients. On the other hand, Radiomics hypothesizes that heterogeneity of tumors can be extracted from medical images. In this study, we investigate the performance of CT-radiomics features and FMISO PET/CT for prediction of local recurrence in head and neck cancer (HNC) patients. Material and Methods A cohort of 22 HNC patients who underwent FMISO PET/CT before primary Radiotherapy (RT) treatment was used. Planning CT scans as well as FMISO PET/CT were acquired prior to RT, FMISO PET data was analysed using maximum tumour-to-muscle ratios (TMR max ) 4h post injection. 92 Robust radiomics features including intensity-based as well as texture features were extracted from the planning CT images in the gross tumour volume (GTV). Six highly significant radiomics features were selected from a simple filter method based on cumulative distribution function (CDF) in a univariate fashion in addition to a logistic regression classification model (LoG) to build a predictive model. Area under the curve of the receiver operating characteristic curve (AUC-ROC) was computed for TMR max and the model including the six selected radiomics Features. Finally, a combined model using FMISO TMR max and two radiomics features (one from texture and one from intesity) were constructed. Results Each of the selected six radiomics features (1 texture and 5 first order statistics), which were normalized to be comparable, showed higher predictive power compared to FMISO TMR max at the moment of predicting outcomes univariately. AUC-ROC curves demonstrated that a model created out of only six dominant CT-radiomics features can discriminate groups better with respect to local control in HNC using the logistic regression models (AUC = 0.904) than FMISO TMR max (AUC = 0.800). Nevertheless, a combination of FMISO-PET TMR max values and only two CT- radiomics features (Small Zone Emphasis texture and Minimum Grey Level first-order statistics) can reach an AUC of 0.886 in our classification model.

Conclusion CT radiomics proved to have better prognostic power with respect to local control in HNC than FMISO-PET TMR max . Nonetheless, a combination of TMR max and the two most significant features of CT radiomics reaches high prognostic power with fewer features to assess. Consequently, analysing tumour heterogeneity using CT radiomics features may have the power to determine substitute measures of tumour hypoxia and might therefore be used as a basis for personalized RT adaptations in the future. EP-1686 Diffusion weighted imaging for treatment response prediction in advanced rectal cancer H.D. Nissen 1 1 Nissen Henrik D., Department of Oncology - Section for Radiotherapy, Vejle, Denmark Purpose or Objective The standard treatment of locally advanced distal rectal cancer is chemoradiotherapy (CRT) followed by surgery. Based on pathologic examination of the surgery specimen, a significant number of patients are found to be without remaining tumor at the time of surgery. This has led to an increasing interest in whether, for a select group of patients, surgery can be replaced by a wait-and-see strategy. Several recent studies [1, 2] have shown that this is possible without compromising survival and with significantly reduced comorbidities. A significant challenge in this strategy is selecting the patients who are candidates for this strategy. We wish to examine whether diffusion weighted MRI (DWI) can be used as an early biomarker for tumor response to CRT. Material and Methods Here we present data from 25 patients treated for distal T3 or T4 rectal tumors. Patients were treated with long course CRT, including a brachytherapy boost to the tumor, followed by surgery. Patients were DWI scanned before start of CRT and again after 2 weeks of CRT. The DWI sequence included 11 b-values from 0 to 1100. Regions of interest (ROI) were drawn using an algorithm to locate