Abstract Book

S1157

ESTRO 37

clinical data (PSA initial , Gleason score) were calculated. After splitting the data into the two patient groups, a comparison was performed to investigate the influence of ADT. Results Median tumor volume was 1cm 3 . Table 1 lists the most relevant correlations of clinical parameters, textural features and MRI-parameters. , PSA nadir

predicting treatment response for prostate cancer patients undergoing radiotherapy as well as ADT. EP-2105 Radiomics in response prediction to Cyberknife radiosurgery for acoustic neuroma:a pilot study I. Bossi Zanetti 1 , N.C. D'Amico 2 , E. Grossi 3 , G. Valbusa 3 , G. D'Anna 2 , D. Fazzini 2 , F. Rigiroli 4 , A. Bergantin 1 , I. Redaelli 1 , A. Maldera 1 , I. Castiglioni 5 , G. Scotti 2 , S. Papa 2 , G. Beltramo 1 1 Centro Diagnostico Italiano, Cyberknife, Milano, Italy 2 Centro Diagnostico Italiano, Imaging, Milano, Italy 3 Bracco Imaging S.p.A, Imaging, Milano, Italy 4 Università degli Studi di Milano, Postgraduation school of Radiodiagnostics, Milano, Italy 5 CNR, Istituto di Bioimmagini e Fisiologia Molecolare, Milano, Italy Purpose or Objective The objective of this study is to analyse MR images acquired before Cyberknife radiosurgery in order to predict the volumetric evolution of the tumour after the treatment. Material and Methods T1 weighted MR images of 38 patients presenting an acoustic neuroma treated with Cyberknife® at Centro Diagnostico Italiano, were acquired and analysed. These selected patients had a follow-up of at least one year (mean 4.6 years, range: 1-10 years) in order to know the tumour evolution after the treatment: 20 patients (52.6%) responded with a Volumetric Reduction (VR), 14 patients (36.8%) responded with stable volumetric evolution and 4 patients (10.5%) had a volume increase. These last two subgroups were considered as a unique set defined as patients without Volumetric Reduction (wVR). The analysed images were acquired on 1.5T machines with contrast enhanced T1-weighted sequences in the axial plane. These images were acquired before the treatment with a standardized protocol necessary as guided image for the Cyberknife® treatment. Semi- automatic tumour segmentation was carried out on MR images using the 3DSlicer image analysis software. The used editor modules is the level tracing effect, where the operator is required to define the segmented region interactively by moving the mouse over the region of interest letting the software automatically adjusting an outline where the pixels all have the same intensity value as the current selected pixel. After the tumour segmentation, the images were pre-processed, resampling label and intensity images to voxels of 1x1x1 mm. MR images features were calculated using a dedicated software developed upon the ITK framework. Shape-based, intensity-based and texture-based features were extracted. An evolutionary algorithm (a TWIST system based on KNN algorithm) was used to subdivide the dataset into training and validation test and to select features yielding the maximal amount of information. After this pre-processing, different machine learning systems(MLS) were applied to develop a predictive model based on a training-testing crossover procedure. The best neural network was a 3-layers feed forward back propagation algorithm with 8 input variables containing the maximal amount of information. Results Two training/testing groups were created (group 1: training-21; testing-17, group 2: training-17; testing-21). The neural network was used twice inverting the training/testing set. In the first analysis the sensitivity was 100%, while the specificity was 77.78%. These two results gave a global accuracy of 88.89%. In the second analysis the sensitivity was 61.54% and the specificity 100%, with a global accuracy of 80.77%. The mean value of the global accuracy was 84.83%.

Gleason score, PSA initial showed non-significant weak positive correlations with each other. Correlations of textural features with tumor volume were observed. However, this might be caused by a size dependency of the features in question. T2w parameters did not correlate with T2w TF, while for ADC max strong negative correlations were found with ADC Contrast, DifferenceVariance and DifferenceEntropy . The DCE- derived parameters showed significant correlations with TF as well. Table 2 summarizes parameters of interest for the split patient groups. and PSA nadir

ADC parameters showed the expected higher values in patients receiving ADT. However, the difference did not reach statistical significance. The results for four Haralick TF showed significant differences between the two patient groups. Conclusion The findings of this pilot analysis indicate that the TF T2w SumAverage , Autocorrelation and ClusterShade as well as the ADC DifferenceEntropy are influenced by ADT. These preliminary results motivate further investigation of this behavior and analysis of the remaining datasets. Furthermore, they indicate a possible relevance of the residual TF in characterizing tumors and