Rukiye Karakis

Interpretation of MR images using self-organizing maps and knowledge-based expert systems

A new image segmentation system is presented to automatically segment and label brain magnetic resonance (MR) images to show normal and abnormal brain tissues using self-organizing maps (SOM) and knowledge-based expert systems. Elements of a feature vector are formed by image intensities, first-order features, texture features extracted from gray-level co-occurrence matrix and multiscale features. This feature vector is used as an input to the SOM. SOM is used to over segment images and a knowledge-based expert system is used to join and label the segments. Spatial distributions of segments extracted from the SOM are also considered as well as gray level properties. Segments are labeled as background, skull, white matter, gray matter, cerebrospinal fluid (CSF) and suspicious regions.

MR Images Restoration With the Use of Fuzzy Filter Having Adaptive Membership Parameters

A new fuzzy adaptive median filter is presented for the noise reduction of magnetic resonance images corrupted with heavy impulse (salt and pepper) noise. In this paper, we have proposed a Fuzzy Adaptive Median Filter with Adaptive Membership Parameters (FAMFAMP) for removing highly corrupted salt and pepper noise, with preserving image edges and details. The FAMFAMP filter is an improved version of Adaptive Median Filter (AMF) and is presented in the aim of noise reduction of images corrupted with additive impulse noise. The proposed filter can preserve image details better than AMF while suppressing additive salt and pepper or impulse type noise. In this paper, we placed our preference on bell-shaped membership function with adaptive parameters instead of triangular membership function without variable coefficients in order to observe better results.

A novel fuzzy logic-based image steganography method to ensure medical data security

This study aims to secure medical data by combining them into one file format using steganographic methods. The electroencephalogram (EEG) is selected as hidden data, and magnetic resonance (MR) images are also used as the cover image. In addition to the EEG, the message is composed of the doctor׳s comments and patient information in the file header of images. Two new image steganography methods that are based on fuzzy-logic and similarity are proposed to select the non-sequential least significant bits (LSB) of image pixels. The similarity values of the gray levels in the pixels are used to hide the message. The message is secured to prevent attacks by using lossless compression and symmetric encryption algorithms. The performance of stego image quality is measured by mean square of error (MSE), peak signal-to-noise ratio (PSNR), structural similarity measure (SSIM), universal quality index (UQI), and correlation coefficient (R). According to the obtained result, the proposed method ensures the confidentiality of the patient information, and increases data repository and transmission capacity of both MR images and EEG signals.

A wiki application for artificial neural network course in engineering education

Using a wiki is one of the most popular and simple way to collaborate in education. A survey conducted in electronics and computer education students in Gazi University, Faculty of Technical Education shows that wikis containing lecture materials are the most preferred source for the course following the instructors handouts. In this paper, the combination of lecture notes, presentations and interactive animations on a wiki for artificial neural network course is presented. The opportunities and enhancement of wikis for collaborative engineering education are discussed.

Classification the axillary lymph node status of breast cancer patients with the analysis of pattern recognition

Today one of the prevalent cancer types we come across in women is breast cancer. The determining whether cancer spread axillary lymph nodes or not is very important in staging and determining treatment of breast cancer disease. In this study, clinic and pathologic data of 270 breast cancer patients applied to Ankara Numune Educational and Research Hospital, Ankara Oncology Educational and Research Hospital were used and classified with pattern recognition analysis methods such as multi layer perceptron(MLP), support vector machines(SVM), linear discriminant analysis(LDA), k-nearest neighbour classifier(k-NN). The MLP classifier was obtained the correlation coefficient and the accuracy value of testing dataset as 0.872 and 94.4% respectively.

A new method of fuzzy logic-based steganography for the security of medical images

Dicom (Digital Imaging and Communications in Medicine) files stores the personal data of patients in file headers. The personal data of patients can be obtained illegally while archiving and transmitting Dicom files. Therefore, the personal rights of patients can also be invaded. It can be also changed the treatment of disease. This study proposes a new fuzzy logic-based steganography method for the security of medical images. It provides to select randomly the least significant bits (LSB) of image pixels. The message which combined of personal data and comment of doctor, are compressed and encrypted to prevent the attacks.

Feature selection in pulmonary function test data with machine learning methods

Pulmonary function test has vital importance in diagnosis and treatment of lung diseases. With this test, several parameters are measured such as forced vital capacity (FVC) and forced expiratory volume in the first second (FEV1) of patients. These parameters indicate different types of lung disorders. Main constraint in diagnosis is to selection of important parameters among test results. In this study, five results of pulmonary function test (PFT) are evaluated with machine learning methods and feature selections with test results are achieved. Feature selections are performed with using Naive bayes, support vector machine (SVM), linear discriminant analysis (LDA) and k-nearest neighbor classifier (k-NN) methods. The test results of 436 patients are obtained from Atatürk Chest Diseases and Thoracic Surgery Training and Research Hospital in Ankara/Turkey. SVM method has a highest performance values with 89,6% accuracy, 87,4 % specificity, 71,6% sensitivity respectively. Thus, it is found with feature selection that importance order of test results are FVC, FEV1, FEV1/FVC, PEF ve FEF25/75 respectively. In this study, obtained performance values are higher than most of studies in the literature.

An application of fuzzy logic-based image steganography

Today, data security in digital environment (such as text, image and video files) is revealed by development technology. Steganography and Cryptology are very important to save and hide data. Cryptology saves the message contents and Steganography hides the message presence. In this study, an application of fuzzy logic (FL)-based image Steganography was performed. First, the hidden messages were encrypted by XOR (eXclusive Or) algorithm. Second, FL algorithm was used to select the least significant bits (LSB) of the image pixels. Then, the LSBs of selected image pixels were replaced with the bits of the hidden messages. The method of LSB was improved as robustly and safely against steg-analysis by the FL-based LSB algorithm.

Corrigendum: Corrigendum to A genetic algorithm model based on artificial neural network for prediction of the axillary lymph node status in breast cancer [Eng. Appl. Artif. Intell. 26 (2013), 945-950]

Corrigendum to ‘‘A genetic algorithm model based on artificial neural network for prediction of the axillary lymph node status in breast cancer’’ [Eng. Appl. Artif. Intell. 26 (2013), 945–950] R. Karakıs, M. Tez , Y.A. Kılıc, B. Kuru , _I. Güler a a Department of Computer and Electronics Technology, Faculty of Technology, Gazi University, 06500 Teknikokullar, Ankara, Turkey b Department of Surgery, Ankara Numune Educational and Research Hospital, Ankara, Turkey c Department of Surgery, Hacettepe University Faculty of Medicine, Ankara, Turkey d Department of Surgery, Ondokuz Mayis University, Samsun, Turkey