A new image steganography method with optimum pixel similarity for data hiding in medical images.

Steganography is one of the approaches used in data hiding. Image steganography, is a type of steganography that the image is used as a covering object. Data hiding capacity and image quality of the cover object are important factors in image steganography. Because the deterioration of image quality can be noticed by the human vision system, it attracts the attention of attackers. Therefore, the purpose of this study is increasing the amount of data to be hidden and stego image is to ensure high image quality. In the study, a new optimization-based method has been proposed by making use of the similarities of the pixels. In order to test the performance of the proposed method has been used visual quality analysis metrics such as MSE, RMSE, PSNR, SSIM and UQI. As a cover object; different sizes medical images have been used that obtained from the open access Dicom library database. Doctor comments in different capacities have been hidden to the medical images. Experimental results show that the average PSNR value is 66.5374, 59.4420 and 56.3936, respectively, when 1000 characters, 5000 characters and 10,000 characters data is hidden in 512 × 512 images. In addition, the average PSNR value is 60.4308, 53.3529 and 47.4113, respectively, when 1000 characters, 5000 characters and 10,000 characters data is hidden in 256 × 256 images. 10,000 characters of data have not been hidden in 256 × 256 images without using data compression techniques with classical similarity based LSB method. In the proposed method, 10,000 characters of data have been hidden in 256 × 256 size images without using data compression techniques.

A novel ECG signal classification method using DEA-ELM.

Electrocardiogram (ECG) signals represent the electrical mobility of the human heart. In recent years, computer-aided systems have helped to cardiologists in the detection, classification and diagnosis of ECG. The aim of this paper is to optimize the number hidden neurons of the traditional Extreme Learning Machine (ELM) using Differential Evolution Algorithm (DEA) and contribute to the classification of ECG signals with a higher accuracy rate. In this paper, publicly ECG records in Physionet was utilized. Pan-Tompkins technique (PTT) and Discrete Wavelet Transform (DWT) approaches were implemented to obtain characteristic properties which are PR period, QT period, ST period and QRS wave of ECG signals. Then, ELM was executed to the ECG samples. Lastly, DEA on software ELM was developed for the assign of the number of hidden neurons, which were used in the ELM algorithm. The performance criterions were used in order to compare the performance of the classification exerted. Concordantly, it was realized that the highest classification achievement values were reached to Accuracy 97.5% and values 93 of number of hidden neurons, with the practice improved with the DEA compared to conventional ELM.

White blood cells detection and classification based on regional convolutional neural networks.

White blood cells (WBC) are important parts of our immune system and they protect our body against infections by eliminating viruses, bacteria, parasites and fungi. There are five types of WBC. These are called Lymphocytes, Monocytes, Eosinophils, Basophils and Neutrophils. The number of WBC types and the total number of WBCs provide important information about our health status. Diseases such as leukemia, AIDS, autoimmune diseases, immune deficiencies, blood diseases can be diagnosed based on the number of WBCs. In this study, a computer-aided automated system that can easily identify and locate WBC types in blood images has been proposed. Current blood test devices usually detect WBCs with traditional image processing methods such as preprocessing, segmentation, feature extraction, feature selection and classification. Deep learning methodology is superior to traditional image processing methods in literature. In addition, traditional methods require the appearance of the whole object to be able to recognize objects. Contrary to traditional methods, convolutional neural networks (CNN), a deep learning architecture, can extract features from a part of an object and perform object recognition. In this case, a CNN-based system shows a higher performance in recognizing partially visible cells for reasons such as overlap or only partial visibility of the image. Therefore, it has been the motivation of this study to increase the performance of existing blood test devices with deep learning method. Blood cells have been identified and classified by Regional Based Convolutional Neural Networks. Designed architectures have been trained and tested by combining BCCD data set and LISC data set. Regional Convolutional Neural Networks (R - CNN) has been used as a methodology. In this way, different cell types within the same image have been classified simultaneously with a detector. While training CNN which is the basis of R - CNN architecture; AlexNet, VGG16, GoogLeNet, ResNet50 architectures have been tested with full learning and transfer learning. At the end of the study, the system has showed 100% success in determining WBC cells. ResNet50, one of the CNN architectures, has showed the best performance with transfer learning. Cell types of Lymphocyte were determined with 99.52% accuracy rate, Monocyte with 98.40% accuracy rate, Basophil with 98.48% accuracy rate, Eosinophil with 96.16% accuracy rate and Neutrophil with 95.04% accuracy rate.

A Novel Method for Classifying Liver and Brain Tumors Using Convolutional Neural Networks, Discrete Wavelet Transform and Long Short-Term Memory Networks.

Rapid classification of tumors that are detected in the medical images is of great importance in the early diagnosis of the disease. In this paper, a new liver and brain tumor classification method is proposed by using the power of convolutional neural network (CNN) in feature extraction, the power of discrete wavelet transform (DWT) in signal processing, and the power of long short-term memory (LSTM) in signal classification. A CNN-DWT-LSTM method is proposed to classify the computed tomography (CT) images of livers with tumors and to classify the magnetic resonance (MR) images of brains with tumors. The proposed method classifies liver tumors images as benign or malignant and then classifies brain tumor images as meningioma, glioma, and pituitary. In the hybrid CNN-DWT-LSTM method, the feature vector of the images is obtained from pre-trained AlexNet CNN architecture. The feature vector is reduced but strengthened by applying the single-level one-dimensional discrete wavelet transform (1-D DWT), and it is classified by training with an LSTM network. Under the scope of the study, images of 56 benign and 56 malignant liver tumors that were obtained from Firat University Research Hospital were used and a publicly available brain tumor dataset were used. The experimental results show that the proposed method had higher performance than classifiers, such as K-nearest neighbors (KNN) and support vector machine (SVM). By using the CNN-DWT-LSTM hybrid method, an accuracy rate of 99.1% was achieved in the liver tumor classification and accuracy rate of 98.6% was achieved in the brain tumor classification. We used two different datasets to demonstrate the performance of the proposed method. Performance measurements show that the proposed method has a satisfactory accuracy rate at the liver tumor and brain tumor classifying.

Automatic RNA virus classification using the Entropy-ANFIS method.

Innovations in the fields of medicine and medical image processing are becoming increasingly important. Historically, RNA viruses produced in cell cultures have been identified using electron microscopy, in which virus identification is performed by eye. Such an approach is time consuming and depends on manual controls. Moreover, detailed knowledge about RNA viruses is required. This study introduces the Entropy-Adaptive Network Based Fuzzy Inference System (Entropy-ANFIS method), which can be used to automatically detect RNA virus images. This system consists of four stages: pre-processing, feature extraction, classification and testing the Entropy-ANFIS method with respect to the correct classification ratio. In the pre-processing stage, a center-edge changing method is used, in which the Euclidian distances are calculated from the center pixels to the edges of the imaged object. In this way, the distance vector is obtained. This calculation is repeated for each RNA virus image. In feature extraction, stage norm entropy, logarithmic energy and threshold entropy values are calculated to form the feature vector. The obtained feature vector is independent of the rotation and scale of the RNA virus image. In the classification stage, the feature vector is given as input to the ANFIS classifier, ANN classifier and FCM cluster. Finally, the test stage is performed to evaluate the correct classification ratio of the Entropy-ANFIS algorithm for the RNA virus images. The correct classification ratio has been determined as 95.12% using the proposed Entropy-ANFIS method.

A new expert system for diagnosis of lung cancer: GDA-LS_SVM.

In nowadays, there are many various diseases, whose diagnosis is very hardly. Lung cancer is one of this type diseases. It begins in the lungs and spreads to other organs of human body. In this paper, an expert diagnostic system based on General Discriminant Analysis (GDA) and Least Square Support Vector Machine (LS-SVM) Classifier for diagnosis of lung cancer. This expert diagnosis system is called as GDA-LS-SVM in rest of this paper. The GDA-LS-SVM expert diagnosis system has two stages. These are 1. Feature extraction and feature reduction stage and 2. Classification stage. In feature extraction and feature reduction stage, lung cancer dataset is obtained and dimension of this lung cancer dataset, which has 57 features, is reduced to eight features using Generalized Discriminant Analysis (GDA) method. Then, in classification stage, these reduced features are given to Least Squares Support Vector Machine (LS-SVM) classifier. The lung cancer dataset used in this study was taken from the UCI machine learning database. The classification accuracy of this GDA-LS-SVM expert system was obtained about 96.875% from results of these experimental studies.

A new Watermarking System based on Discrete Cosine Transform (DCT) in color biometric images.

This paper recommend a biometric color images hiding approach An Watermarking System based on Discrete Cosine Transform (DCT), which is used to protect the security and integrity of transmitted biometric color images. Watermarking is a very important hiding information (audio, video, color image, gray image) technique. It is commonly used on digital objects together with the developing technology in the last few years. One of the common methods used for hiding information on image files is DCT method which used in the frequency domain. In this study, DCT methods in order to embed watermark data into face images, without corrupting their features.