Zafer Iscan

Classification of electroencephalogram signals with combined time and frequency features

Epilepsy is a neurological disorder that causes people to have seizures and the main application field of electroencephalography. In this study, combined time and frequency features approach for the classification of healthy and epileptic electroencephalogram (EEG) signals is proposed. Features in the time domain are extracted using the cross correlation (CC) method. Features related to the frequency domain are extracted by calculating the power spectral density (PSD). In the study, these individual time and frequency features are considered to carry complementary information about the nature of the EEG itself. By using divergence analysis, distributions of the feature vectors in the feature space are quantitatively measured. As a result, using the combination rather than individual feature vectors is suggested for classification. In order to show the efficiency of this approach, first of all, the classification performances of the time and frequency based feature vectors in terms of overall accuracy are analyzed individually. Afterwards, the feature vectors obtained by the combination of the individual feature vectors are used in classification. The results achieved by different classifier structures are given. Obtained performances in the study are comparatively evaluated by the help of the other studies for the same dataset in advance. Results show that the combination of the features derived from cross correlation and PSD is very promising in discriminating between epileptic and healthy EEG segments.

Tumor detection by using Zernike moments on segmented magnetic resonance brain images

In this study, a novel method is proposed for the detection of tumor in magnetic resonance (MR) brain images. The performance of the novel method is investigated on one phantom and 20 original MR brain images with tumor and 50 normal (healthy) MR brain images. Before the segmentation process, 2D continuous wavelet transform (CWT) is applied to reveal the characteristics of tissues in MR head images. Then, each MR image is segmented into seven classes (six head tissues and the background) by using the incremental supervised neural network (ISNN) and the wavelet-bands. After the segmentation process, the head is extracted from the background by simply discarding the background pixels. Symmetry axis of the head in the MR image is determined by using moment properties. Asymmetry is analyzed by using the Zernike moments of each of six tissues segmented in the head: two vectors are individually formed for the left and right hand sides of the symmetry axis on the sagittal plane by using the Zernike moments of the segmented tissues in the head. Presence of asymmetry and the tumors are inquired by considering the distance between these two vectors. The performance of the proposed method is further investigated by moving the location of the tumor and by modifying its size in the phantom image. It is observed that tumor detection is successfully realized for the tumorous 20 MR brain images.

Medical image segmentation with transform and moment based features and incremental supervised neural network

In this study, a novel incremental supervised neural network (ISNN) is proposed for the segmentation of medical images. Performance of the ISNN is investigated for tissue segmentation in medical images obtained from various imaging modalities. Two feature extraction methods based on transform and moments are comparatively investigated to segment the tissues in medical images. Two-dimensional (2D) continuous wavelet transform (CWT) and the moments of the gray-level histogram (MGH) are computed in order to form the feature vectors of ultrasound (US) bladder and phantom images, X-ray computerized tomography (CT) and magnetic resonance (MR) head images. In the 2D-CWT method, feature vectors are formed by the intensity of one pixel of each wavelet-plane of different energy bands. The MGH represents the tissues within the sub-windows by using the spatial variation of image intensities. In this study, the ISNN and Grow and Learn (GAL) network are employed for the segmentation task. It is observed that the ISNN has significantly eliminated the disadvantages of the GAL network in the segmentation of the medical images.

Segmentation of medical images by using wavelet transform and incremental self-organizing map

This paper presents a novel method that uses incremental self-organizing map (ISOM) network and wavelet transform together for the segmentation of magnetic resonance (MR), computer tomography (CT) and ultrasound (US) images. In order to show the validity of the proposed scheme, ISOM has been compared with Kohonens SOM. Two-dimensional continuous wavelet transform (2D-CWT) is used to form the feature vectors of medical images. According to the selected two feature extraction methods, features are formed by the intensity of the pixel of interest or mean value of intensities at one neighborhood of the pixel at each sub-band. The first feature extraction method is used for MR and CT head images. The second method is used for US prostate image.

MLSP Competition, 2010: Description of second place method

In this paper, the classification method which generated the second highest AUC (the area under the ROC curve) in the MLSP 2010 Competition is presented. After application of some pre-processing steps to the dataset, by using statistical information, proper weights are found which maximize the separability between the P300 and the non-P300 responses. The classification method is simple and very suitable for online brain-computer interface (BCI) applications due to its fast algorithm.

Retrospective correction of near field effect of X-ray source in radiographic images by using genetic algorithms

X-ray bone images are used in the areas such as bone age assessment, bone mass assessment and examination of bone fractures. Medical image analysis is a very challenging problem due to large variability in topologies, medical structure complexities and poor image modalities such as noise, low contrast, several kinds of artifacts and restrictive scanning methods. Computer aided analysis leads to operator independent, subjective and fast results. In this study, near field effect of X-ray source is eliminated from hand radiographic images. Firstly, near field effect of X-ray source is modeled, then the parameters of the model are estimated by using genetic algorithms. Near field effect is corrected for all image pixels retrospectively. Two different categories of images are analyzed to show the performance of the developed algorithm. These are original X-ray hand images and phantom hand images. Phantom hand images are used to analyze the effect of noise. Two performance criteria are proposed to test the developed algorithm: Hand segmentation performance and variance value of the pixels in the background. It is observed that the variance value of the pixels in the background decreases, and hand segmentation performance increases after retrospective correction process is applied.

Classification of EEG in a steady state visual evoked potential based brain computer interface experiment

In this paper, electroencephalogram (EEG) signals of 20 subjects are classified in a steady state visual evoked potential (SSVEP) based brain computer interface (BCI) system by using 4 different stimulation frequencies in a program created by Visual C#. After applying proper pre-processing methods, power spectral density (PSD) based features are extracted around first and second harmonics of the stimulation frequencies. Average classification performance obtained from 20 subjects in 4-class classification is 83.62% with Nearest Mean Classifier (NMC). Results for 5-class classification, EEG segment size and gender differences are also analyzed in a detailed manner. The classification method is simple and very suitable for real-time experiments.

Improved T-Weight method in classification of slow cortical potentials

In this paper, T-Weight Method is improved by integration of a threshold determination step into the original algorithm. The new method is called Improved T-Weight (ITW) Method and the performance of the ITW Method is evaluated on classification of slow cortical potentials (SCPs) for a brain-computer interface (BCI) task. Two different datasets from BCI Competition 2003 are used for classification. It is showed that ITW Method outperforms all the other submissions in the Competition in terms of classification error. Proposed method has a great potential to become a widely used classifier.

Survey evaluation by character recognition

In the study, an automated system was proposed for the evaluation of survey sheets filled by different students. In this method, the regions related to the answers on the survey sheets digitized by a scanner are determined. For this purpose, after finding the right edge of the survey, upper-right corner of the survey is marked by a developed edge tracking algorithm. Afterwards, rows of the survey are found and the cells which contain the answers between the rows are segmented. After the pre-processing step that includes filling and thinning operations, the answers in these parts are categorized using histogram-based features and area ratio. Obtained performances using limited survey sheets indicate that the survey evaluation by character recognition can be an appropriate option.

Discrimination between different art types: Marbled paper, watercolor and tile images

In this study, discrimination between different art categories was presented. To be able to classify different art images, features capable of including the characteristic properties of art types were extracted. Extracted features are based on RGB histogram characteristics, coarseness and edge ratio in the images. Obtained features were used in different classifier structures and an instance based learning algorithm (K-Nearest Neighbor) was preferred to be used in the classification step due to its high and robust classification performance. Obtained results show that the extracted features are highly capable of representing the characteristics of the arts.