1. Georgiadis P. 1, Cavouras D. 2, Kalatzis I. 2, Daskalakis A. 1, Kagadis G. 1, Sifaki K. 3, Malamas M. 3, Nikiforidis G. 1, Solomou A. 4 1 Medical Image Processing and Analysis (MIPA) Group, Laboratory of Medical Physics, School of Medicine, University of Patras, Rio, GR-26503 Greece e-mail: pgeorgiadis@med.upatras.gr, web page: http://mipa.med.upatras.gr 2 Medical Signal and Image Processing Lab, Department of Medical Instrumentation Technology, Technological Education Institution of Athens, Ag. Spyridonos Street, Aigaleo, GR-12210, Athens, Greece e-mail: cavouras@teiath.gr, web page: http://medisp.bme.teiath.gr 3 251 General Hellenic Airforce Hospital, MRI Unit, Katehaki, Athens, Greece 4 Department of Radiology, School of Medicine, University of Patras, Rio, GR-26503 Greece Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features MedicExpo 2008, March 27-30, Athens

2. BRAIN TUMOURS Approximately 39,550 people were newly diagnosed with primary benign and primary malignant brain tumours in 2002. The incidence rate of primary brain tumours, whether benign or malignant, is 14 per 100,000, while median age at diagnosis is 57 years (CBTRUS 2002). INTRODUCTION Secondary or metastatic brain tumours, originate in tissues outside the central nervous system and are a common complication of systemic cancer. Brain metastases occur in 20% to 40% of all cancer patients. More than 100,000 individuals per year will develop brain metastases (CBTRUS 2002). MedicExpo 2008, March 27-30, Athens

3. CURRENT TECHNIQUES Today, one of the most promising techniques for generating useful information for brain tissue characterization is Magnetic Resonance Imaging (MRI). In order to extract the diagnostic information of different parameters reflected in MRI, image analysis techniques have been employed. INTRODUCTION Brain tumour characterization is a process that requires a complicated assessment of the various MR image features and is typically performed by experienced radiologists. An expert radiologist performs this task with a significant degree of precision and accuracy, despite the inherently subjective nature of many of the decisions associated with this process. Nevertheless, in the effort to deliver more effective treatment, clinicians are continuously seeking for greater accuracy in the pathological characterization of brain tissues from imaging investigations. MedicExpo 2008, March 27-30, Athens

4. AIM The aim of the present study was to design, implement, and evaluate a pattern recognition system, which, by analyzing routinely taken T1 post- contrast MR images, would improve brain tumor classification accuracy. Employing a two-level hierarchical decision tree, distinction between metastatic and primary brain tumors and between gliomas and meningiomas were performed at the 1 st and 2 nd level of the decision tree respectively. INTRODUCTION MedicExpo 2008, March 27-30, Athens

5. CLINICAL MATERIAL, FEATURE EXTRACTION AND REDUCTION A total number of 67 T1-weighted gadolinium-enhanced MR images were obtained from the Hellenic Airforce Hospital with verified intracranial tumours, using a SIEMENS-Sonata 1.5 Tesla MR Unit (21 metastasis, 19 meningiomas and 27 gliomas). MATERIALS AND METHODS Utilizing these images, the radiologist specified Regions of Interest (ROIs) that included tumour regions. From each ROI, a series of 36 features were extracted; 4 features from the ROI’s histogram, 22 from the co-occurrence matrices, and 10 from the run-length matrices. To reduce feature dimensionality, the non-parametric Wilcoxon test was employed. Only features of high discriminatory ability (p<0.001), were selected to feed the classification scheme. MedicExpo 2008, March 27-30, Athens

6. CLASSIFICATION SYSTEM - EVALUATION Best features combination was determined employing the robust but time consuming exhaustive search method (up to 3 features). MATERIALS AND METHODS Classifier performance was evaluated employing the leave-one-out method. MedicExpo 2008, March 27-30, Athens Least Squares Features Transformation – Probabilistic Neural Network (LSFT-PNN) Classifier (Third degree (cubic) LSFT-PNN at 1st level, second degree (quadratic) LSFT-PNN at 2nd level)

7. CLASSIFICATION RESULTS () CLASSIFICATION RESULTS ( Metastatic VS Primary brain tumors ) RESULTS AND DISCUSSION Primary Brain Tumors Secondary Brain Tumors Accurac y (%) Primary Brain Tumors 43393.48 Secondary Brain Tumors 12095.24 94.03 Cubic LSFT-PNN PNN Primary Brain Tumors Secondary Brain Tumors Accurac y (%) Primary Brain Tumors 40686.96 Secondary Brain Tumors 12095.24 89.55 MedicExpo 2008, March 27-30, Athens

8. CLASSIFICATION RESULTS () CLASSIFICATION RESULTS ( Gliomas VS Meningiomas ) RESULTS AND DISCUSSION Quadratic LSFT-PNN PNNGliomas Meningio mas Accurac y (%)Gliomas270100 Meningiomas019100 100Gliomas Meningio mas Accurac y (%)Gliomas26196.30 Meningiomas019100 97.83 MedicExpo 2008, March 27-30, Athens

9. DISCUSSION #1 RESULTS AND DISCUSSION The LSFT-PNN classification algorithm increased the overall accuracy in correctly characterizing primary and metastatic brain tumours. This is important, since the precision of such a decision may be crucial in patient management, e.g. metastatic tumours require specific treatment protocols, such as radiation therapy and chemotherapy, while primary tumours may also require surgical intervention. The reason behind this accuracy increment may be attributed to the increased class separability that the LSFT procedure provides, especially when non-linear terms are introduced in the classifier’s discriminant function. MedicExpo 2008, March 27-30, Athens

10. DISCUSSION #2 RESULTS AND DISCUSSION The best features combination described the shape of the histogram peak (kurtosis) and expressed the degree of the in-homogeneity (sum and difference entropy) in the grey-tones of the ROIs. These textural characteristics are related to textural parameters that physicians employ in diagnosis and they are proportional to the textural imprint of brain tumours in MRI. MedicExpo 2008, March 27-30, Athens

11. CONCLUSION CONCLUSION The aim of the present study was to design, implement, and evaluate a software pattern recognition system to improve classification accuracy between primary and metastatic brain tumours on MRI. The system improved classification accuracy compared to other studies. Thus the system could be of assistance to physicians as a reliable second opinion tool when analysing brain tumour MR images. MedicExpo 2008, March 27-30, Athens