Search

Salivary gland tumors constitute 2%-6% of all head and neck tumors and are most common in the parotid gland. Magnetic resonance (MR) imaging is the most sensitive imaging modality for diagnosis. Tumor type, localization, and relationship with surrounding structures are important factors for treatment. Therefore, parotid gland tumor segmentation is important. Specialists widely use manual segmentation in diagnosis and treatment. However, considering the development of artificial intelligence-based models today, it is seen that artificial intelligence-based automatic segmentation models can be used instead of manual segmentation, which is a time-consuming technique. Therefore, we segmented parotid gland tumor (PGT) using deep learning-based architectures in the paper. The dataset used in the study includes 102 T1-w, 102 contrast-enhanced T1-w (T1C-w), and 102 T2-w MR images. After cropping the raw and manually segmented images by experts, we obtained the masks of these images. After standardizing the image sizes, we split these images into approximately 80% training set and 20% test set. Hereabouts, we trained six models for these images using ResNet18 and Xception-based DeepLab v3+. We prepared a user-friendly Graphical User Interface application that includes each of these models. From the results, the accuracy and weighted Intersection over Union values of the ResNet18-based DeepLab v3+ architecture trained for T1C-w, which is the most successful model in the study, are equal to 0.96153 and 0.92601, respectively. Regarding the results and the literature, it can be seen that the proposed system is competitive in terms of both using MR images and training the models independently for T1-w, T1C-w, and T2-w. Expressing that PGT is usually segmented manually in the literature, we predict that our study can contribute significantly to the literature. In this study, we prepared and presented a software application that can be easily used by users for automatic PGT segmentation. In addition to predicting the reduction of costs and workload through the study, we developed models with meaningful performance metrics according to the literature. [ABSTRACT FROM AUTHOR]

• Two powerful datasets were created for the selection of the wart treatment method. • In the dataset pre-analysis, it was evaluated that it is very difficult to determine a treatment method without classification techniques. • As a result of the tests on the datasets, it was determined that the Ensemble Classification method was the most appropriate. • It has been observed that the estimations of the Ensemble model fully comply with the real data. • The performance values of the Ensemble method are higher than the literature models. Warts caused by Human Papilloma Virus (HPV) do not disappear spontaneously with the body's natural immunity. This is due to many features of HPV, such as its weak immune effect, not entering the bloodstream and causing an immune response, and permanent infection of skin cells. HPV requires urgent treatment due to these characteristics and the fact that warts are most common on the hands and feet and are painful and disturbing. Choosing the most appropriate Cryotherapy or Immunotherapy treatment methods according to the patient's physiological characteristics is important in order to carry out the treatment process quickly. This study focuses on helping experts choose the most appropriate treatment for the most common plantar and common warts. For the selection of treatment method machine learning have been used. Bagged Tree and Subspace K-Nearest Neighbors (KNN) Ensemble classification algorithms were developed and tested on two data sets. These data sets were used to develop classification algorithms with pre- and post-treatment information of 180 patients receiving cryotherapy and immunotherapy treatments. The Subspace KNN Ensemble algorithm correctly predicted the treatment results of 88 of 90 patients receiving cryotherapy treatment, reaching 97.80% accuracy, and the Bagged Tree Ensemble algorithm correctly predicted 78 out of 90 patients receiving immunotherapy, reaching 86.7% accuracy. It has been shown that algorithms can help experts in terms of both high accuracy values ​​and fast decision making. The algorithms proposed have not been used before, and it has also been seen that they have superior performances than similar studies. [ABSTRACT FROM AUTHOR]

The formation and duration of partnerships are analyzed.

Summary Objective The aim of this study was to determine nodules using newly developed software with a computer-assisted visual process technique for the calculation of size. The effects of the ratios of nodule base and width were evaluated with voice acoustic analysis. Methods A total of 72 patients with pediatric vocal nodule were evaluated. Nodules were marked with the ImageJ News program on photographs obtained from the video recordings in the videostroboscopic examination and classified according to the Shah et al scale. Segmentation was applied automatically. The ratios were taken as base of nodule/width and base of nodule/vocal cord. In the voice acoustic analysis, basic frequencies (mean F0), jitter (local %), shimmer (local %), and harmonicity (mean harmonics-to-noise [mean HNR]) were evaluated. Results A statistically significant negative correlation was determined between the mean F0 value and the nodule base/width ratio (P = 0.042, r = −0.240). A negative statistically significant relationship was determined between jitter (%) and vocal nodule base/width (P = 0.009, r = −0.305). A statistically significant positive correlation was determined between mean HNR and vocal nodule base/width (P = 0.034, r = 0.324). In discriminant analysis, correct classification of the Shah et al scale degrees of the classifying variables was 73.6%. Conclusion Through collaboration with the biomedical engineering department, the results of this study determined new ratios in patients with pediatric vocal nodule. In voice acoustic analysis, the mean F0 was more affected by the width of the nodule, mean HNR was affected by the length of the base of the nodule, and jitter (%) was affected by the width of the nodule. [ABSTRACT FROM AUTHOR]

Renal cell cancer is the most common type of kidney cancer and usually occurs at an advanced ages. The rapid spread of renal cell cancer and the inability to detect the disease early often results in a fatality. Therefore, it is important to identify the renal abnormalities before the disease reaches the advanced phase. This paper proposes a decision support system that detects renal cell cancer using abdominal images of healthy and renal cell cancer tissues. Renal cell cancer detection involves two main stages as segmentation and cancer detection. In the first step, the kidney areas have been obtained by segmentation based on clustering analysis. In the second step, classification has been made by computer-assisted detection system to identify renal cell cancer. Feature vectors that support the originality of the study at this stage have been created. Subsequently, classification has been made using these feature vectors with the Support Vector Machines (SVMs). For detecting the renal abnormality, 130 different images obtained from the image archiving system of the Radiodiagnostic Department of Fırat University Medical Faculty were used. Thirty of these images have been used to train the K-means classifier. Performance evaluations have been made for both segmentation and classification. In order to measure segmentation success, the Dice coefficient was obtained as 89.3%. Sensitivity, Specificity, Accuracy, Positive Predictive Value (PPV) and Negative Predictive Value (NPV) coefficients, which have been used to determine the classification performance, were obtained as 84%, 92%, 88%, 91.3% and 85.19% respectively. [ABSTRACT FROM AUTHOR]

• Extraction of image features for some classifiers. Selection of the five most successful classifiers for Phase-1 and Phase-2. Designing a system using majority voting and creating a theoretical framework. Designing the graphical user interface application. The COVID-19 pandemic has been affecting the world since December 2019, and nowadays, the number of infected is increasing rapidly. Chest X-ray images are clinical adjuncts that can be used in the diagnosis of COVID-19 disease. Because of the rapid spread of COVID-19 disease worldwide and the limited number of expert radiologists, the proposed method uses the automatic diagnosis method rather than a manual diagnosis method. In the paper, COVID-19 Positive/Negative (2275 Positive, 4626 Negative) and Normal/Pneumonia (2313 Normal, 2313 Pneumonia) are diagnosed using chest X-ray images. Herein, 80 % and 20 % of the images are used in the training and validation set, respectively. In the proposed method, six different classifiers are trained using chest X-ray images, and the five most successful classifiers are used in both phases. In Phase-1 and Phase-2, image features are extracted using the Bag of Features method for Cosine K-Nearest Neighbor (KNN), Linear Discriminant, Logistic Regression, Bagged Trees Ensemble, Medium Gaussian Support Vector Machine (SVM), excluding SqueezeNet Deep Learning (K = 2000 and K = 1500 for Phase-1 and Phase-2, respectively). In both phases, the five most successful classifiers are determined, and images classify with the help of the Majority Voting (Mathematical Evaluation) method. The application of the proposed method is designed for users to diagnose COVID-19 Positive, Normal, and Pneumonia. The results show that accuracy values obtained by Majority Voting (Mathematical Evaluation) method for Phase-1 and Phase-2 are equal to 99.86 % and 99.28 %, respectively. Thus, it indicates that the accuracy of the whole system is 99.63 %. When we analyze the classification performance metrics for Phase-1 and Phase-2, Specificity (%), Precision (%), Recall (%), F 1 Score (%), Area Under Curve (AUC), and Matthews Correlation Coefficient (MCC) are equal to 99.98–99.83–99.07–99.51–0.9974–0.9855 and 99.73–99.69–98.63–99.23–0.9928–0.9518, respectively. Moreover, if the classification performance metrics of the whole system are examined, it is seen that Specificity (%), Precision (%), Recall (%), F 1 Score (%), AUC, and MCC are 99.88, 99.78, 98.90, 99.40, 0.9956, and 0.9720 , respectively. When the studies in the literature are examined, the results show that the proposed model is better than its counterparts. Because the best performance metrics for the dataset used were obtained in this study. In addition, since the biphasic majority voting technique is used in the study, it is seen that the proposed model is more reliable. On the other hand, although there are tens of thousands of studies on this subject, the usability of these models is debatable since most of them do not have graphical user interface applications. Already, in artificial intelligence technologies, besides the performance of the developed models, their usability is also important. Because the developed models can generally be used by people who are less knowledgeable about artificial intelligence. [ABSTRACT FROM AUTHOR]

[Display omitted] • 1432 images in the dataset used in the study were labeled as Periodontal bone loss and Non-periodontal bone loss. • Image features were extracted using AlexNet and SqueezeNet, also images are directly classified using the EfficientNetB5. • AlexNet and SqueezeNet based image features are classified using the five different classifiers. • To save time and reduce the workload of experts, the user-friendly GUI application was designed. As artificial intelligence in medical imaging is used to diagnose many diseases, it can also be employed to diagnose whether a person has periodontal bone loss or not. Accurate and early diagnosis performs a vital task in the treatment of the patient's dental disorder. Therefore, such medical images are known to be an important clinical adjunct. In this manuscript, whether the patient has periodontal bone loss or non-periodontal bone loss is diagnosed employing hybrid artificial intelligence-based systems. Herein, after tagging a total of 1432 images by an expert, we extract 1000 deep image features for each image using AlexNet and SqueezeNet deep learning architectures. On the other hand, we classify these images directly without extracting the image features using the EfficientNetB5 deep learning architecture. First, we categorize AlexNet-based deep image features using the Coarse Tree, Weighted K-Nearest Neighbor (KNN), Gaussian Naïve Bayes, RUSBoosted Trees Ensemble, and Linear Support Vector Machine (SVM) classifiers. Afterward, we classify SqueezeNet-based deep image features using Medium Tree, Gaussian Naïve Bayes, Boosted Trees Ensemble, Coarse KNN, and Medium Gaussian SVM classifiers. With the help of the ten classifiers employed in this study, we also design a user-friendly Graphical User Interface (GUI) application. Thanks to this application, we aim to reduce the workload of experts, save time and help to diagnose dental disorders early. The results show that the best classifiers for AlexNet-based, SqueezeNet-based, and Direct-Convolutional Neural Network (CNN) are Linear SVM, Medium Gaussian SVM, and EfficientNetB5, respectively. Among these classifiers, the best classifier is Linear SVM, and its accuracy, error, sensitivity, specificity, precision, and F 1 score values are 81.49%, 18.51%, 84.57%, 79.14%, 75.68%, and 79.88%, respectively. [ABSTRACT FROM AUTHOR]

Highlights: [•] RBAC and SSRG methods have been used for thyroid nodule detection. [•] Preprocessed MR images are segmented and cross sectional nodule areas are obtained. [•] Accuracies are given by ZSI and corr. by comparing them with manually obtained areas. [•] RBAC and SSRG method yielded average ZSI values of 0.938 and 0.906 respectively. [•] RBAC and SSRG method yielded ave. cross-corr. val. of 0.91 and 0.91 respectively. [ABSTRACT FROM AUTHOR]

Abstract: The electromyography (EMG) signal is a bioelectrical signal variation, generated in muscles during voluntary or involuntary muscle activities. The muscle activities such as contraction or relaxation are always controlled by the nervous system. The EMG signal is a complicated biomedical signal due to anatomical/physiological properties of the muscles and its noisy environment. In this paper, a classification technique is proposed to classify signals required for a prosperous arm prosthesis control by using surface EMG signals. This work uses recorded EMG signals generated by biceps and triceps muscles for four different movements. Each signal has one single pattern and it is essential to separate and classify these patterns properly. Discriminant analysis and support vector machine (SVM) classifier have been used to classify four different arm movement signals. Prior to classification, proper feature vectors are derived from the signal. The feature vectors are generated by using mean absolute value (MAV). These feature vectors are provided as inputs to the identification/classification system. Discriminant analysis using five different approaches, classification accuracy rates achieved from very good (98%) to poor (96%) by using 10-fold cross validation. SVM classifier gives a very good average accuracy rate (99%) for four movements with the classification error rate 1%. Correct classification rates of the applied techniques are very high which can be used to classify EMG signals for prosperous arm prosthesis control studies. [Copyright &y& Elsevier]

Abstract: The scope of this paper is to develop the nonlinear meta-models for seakeeping behaviour, considering the fishing vessels. These models are intended to be inserted either in a multiattribute design selection process or in a comprehensive multiobjective optimization procedure. For this purpose, seakeeping data of fishing vessels in regular head waves are used to develop meta-models of transfer functions of heave, pitch and vertical acceleration by nonlinear analysis. A home-made software considers two databases; the first is composed by the ship dimensions and coefficients of fishing vessels, and the second is their ship motion data obtained by employing a strip-theory calculation. The meta-models are proposed to predict the vertical motion characteristics for given ranges of speed and wave length during the concept design stage. The independent variables are hull size (Δ), main dimensions (L, B, T), and some hydrostatic parameters (CWP , CVP , LCB, LCF, etc.). The results estimated by the software show good correspondences with the ones achieved by direct computations. The study provides additional insight on the influence of hull form parameters on seakeeping performance of small vessels having form properties and parametric range corresponding to the investigated vessels. [Copyright &y& Elsevier]

Abstract: Harmonics are the major power quality problems in industrial and commercial power systems. Several methods for detection of power system harmonics have been investigated by engineers due to increasing harmonic pollution. Since the non-integer multiple harmonics (inter and sub-harmonics) become wide spread, the importance of harmonic detection has increased for sensitive filtration. This paper suggests parametric spectral estimation methods for the detection of harmonics, inter-harmonics and sub-harmonics. Yule Walker, Burg, Covariance and Modified Covariance methods are applied to generate cases. Not only integer multiple harmonics but also non-integer multiple harmonics are successfully determined in the computer simulations. Further, performances of proposed methods are compared with each other in terms of frequency resolution. [Copyright &y& Elsevier]

Abstract: In this study, power quality (PQ) signals are analyzed by using Welch (non-parametric) and autoregressive (parametric) spectral estimation methods. The parameters of the autoregressive (AR) model were estimated by using the Yule–Walker method. PQ spectra were then used to compare the applied spectral estimation methods in terms of their frequency resolution and the effects in determination of spectral components. The variations in the shape of the obtained power spectra were examined in order to detect power system transients. Performance of the proposed methods was evaluated by means of power spectral densities (PSDs). Graphical results comparing the performance of the AR method with that of the Welch technique are given. The results demonstrate superior performance of the AR method over the Welch method. [Copyright &y& Elsevier]

Abstract: The main idea of this paper is to identify functional relations between seakeeping characteristics and hull form parameters of Mediterranean fishing vessels. Multiple regression analysis is used for quantitative assessment through a computer software that is based on the SQL Server Database. The seakeeping attributes under investigation are the transfer functions of heave and pitch motions and of absolute vertical acceleration at stern, while the ship parameters influencing motion dynamics have been classified into two groups: displacement (Δ) and main dimensions (L, B, T), coefficients that define the details of the hull form (C WP, C VP, LCB, LCF, etc.). Four multiple regression models having different parameter combinations are here investigated and discussed, giving way to the so-called ‘Simple Model’, ‘Intermediate Model’, ‘Enhanced 1 Model’ and ‘Enhanced 2 Model’. The obtained results are more than satisfactory for seakeeping predictions during the conceptual design stage. [Copyright &y& Elsevier]

Abstract: The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. In this study, multiple signal classification (MUSIC), autoregressive (AR) and periodogram methods were used to get power spectra in patients with absence seizure. The EEG power spectra were used as an input to a classifier. We introduce two fundamentally different approaches for designing classification models (classifiers); the traditional statistical method based on logistic regression (LR) and the emerging computationally powerful techniques based on artificial neural networks (ANNs). LR as well as multilayer perceptron neural network (MLPNN) based classifiers were developed and compared in relation to their accuracy in classification of EEG signals. The comparisons between the developed classifiers were primarily based on analysis of the receiver operating characteristic (ROC) curves as well as a number of scalar performance measures pertaining to the classification. The MLPNN based classifier outperformed the LR based counterpart. Within the same group, the MLPNN-based classifier was more accurate than the LR-based classifier. [Copyright &y& Elsevier]

Abstract: Since EEG is one of the most important sources of information in therapy of epilepsy, several researchers tried to address the issue of decision support for such a data. In this paper, we introduce two fundamentally different approaches for designing classification models (classifiers); the traditional statistical method based on logistic regression and the emerging computationally powerful techniques based on artificial neural networks (ANNs). Logistic regression as well as feedforward error backpropagation artificial neural networks (FEBANN) and wavelet neural networks (WNN) based classifiers were developed and compared in relation to their accuracy in classification of EEG signals. In these methods we used FFT and autoregressive (AR) model by using maximum likelihood estimation (MLE) of EEG signals as an input to classification system with two discrete outputs: epileptic seizure or nonepileptic seizure. By identifying features in the signal we want to provide an automatic system that will support a physician in the diagnosing process. By applying AR with MLE in connection with WNN, we obtained novel and reliable classifier architecture. The network is constructed by the error backpropagation neural network using Morlet mother wavelet basic function as node activation function. The comparisons between the developed classifiers were primarily based on analysis of the receiver operating characteristic (ROC) curves as well as a number of scalar performance measures pertaining to the classification. The WNN-based classifier outperformed the FEBANN and logistic regression based counterpart. Within the same group, the WNN-based classifier was more accurate than the FEBANN-based classifier, and the logistic regression-based classifier. [Copyright &y& Elsevier]

Microaneurysms are lesions in the shape of small circular dilations which result from thinning in peripheral retinal blood vessels due to diabetes and increasing intra-retinal blood pressure. Because it is considered as the most important clinical finding in the diagnosis of diabetic retinopathy, accurate detection of these lesions bear utmost importance in the early diagnosis of diabetic retinopathy. The present study aims to accurately, effectively and automatically detect microaneurysms which are difficult to detect in color fundus images in early stage. To this aim, ant colony algorithm, which is an important optimization method, was used instead of conventional image processing techniques. First, retinal vascular structure was extracted from color fundus images in Messidor and DiaretDB1 data sets. Afterwards, the segmentation of microaneurysms was effectively carried out using ant colony algorithm. The same procedure was also applied to five different image processing and clustering algorithms (watershed, random walker, k-means, maximum entropy and region growing) in order to compare the performance of the proposed method with other methods. Microaneurysm images manually detected by a specialist eye doctor were used to measure the performances of above-mentioned methods. The similarities among microaneurysms which were automatically and manually segmented were tested using Dice and Jaccard similarity index values. Dice index values obtained from the study vary between 0.52 and 0.98 in maximum entropy, 0.55 and 0.88 in watershed, 0.75 and 0.86 in region growing, 0.55 and 0.78 in k-means, and 0.66 and 0.83 in random walker, and 0.81 and 0.9 in ant colony. Similar performance values were also obtained in Jaccard index. The results show that different performances were observed in the conventional segmentation of microaneurysms depending on the image quality. On the other hand, the ant colony based method proposed in this paper displays a more stabilized and higher performance irrespective of image contrast. Therefore, it is evident that the proposed method successfully detects microaneurysms even in low quality images, thus helping specialists diagnose them in an easier way. [ABSTRACT FROM AUTHOR]

Abstract Ship motions and their adverse effects have always been studied with the aim of reducing motions and accelerations using whatsoever plausible ways during both the ship design process and operating lifetime. In the present work, a simulation study is carried out by taking into consideration the passengers in several locations of the selected motor yacht in an intermediate sea state with Hs = 1 m. Irregular head wave scenario at Fn = 0.25 is investigated and a controller design is implemented to ensure that the calculated RMS vertical acceleration values are decreased to tolerated levels in terms of motion sickness index. First, wave loads are obtained in the time domain by using strip theory, linear superposition technique, and the most common realization technique. Then, using a linear two-degree-of-freedom mathematical model, in which pitch and heave motions are considered together with the direct solution of convolution integrals, the uncontrolled motions and accelerations are obtained. Then, the linear matrix inequalities based on robust static output feedback controller are designed to mitigate the vertical acceleration of the ship. Finally, the results obtained with the robust static output feedback control design are presented in numerical simulation studies to demonstrate the effectiveness of the proposed control approach. Highlights • Cummins' equation is used for the mathematical model in irregular waves. • Direct solution of the convolution integral is used for fluid memory effects. • It is aimed to mitigate vertical ship motions by designing a robust controller. • The results obtained with the static output feedback controller are presented. [ABSTRACT FROM AUTHOR]

Structured light (SL) methods are widely used in 3D measurement systems because of their speed and contactless operation. These methods provide high resolution 3D modeling. Phase shifting is one of the SL algorithms that give high resolution with less number of pattern requirements. Since reflected patterns and obtained results are commonly distorted due to the lenses in cameras and projector systems, system calibration must be fulfilled before starting 3D modeling with SL system. Uncalibrated SL system may model the object much greater/smaller than the real dimension of it. In this study, a three step calibration system is proposed for an SL system that uses a three phase shifting algorithm with automatic thresholding. These calibration steps include camera calibration, projector calibration and depth calibration. Experimental studies showed that proposed calibrated system reduces the camera and projector lens errors. Depth calibration is applied as a last calibration step provided a 3D modeling of the object with accurate dimension. Dimensions of the objects and their 3D models are compared to have accuracy of the proposed 3D modeling system. After system calibration, obtained results showed that proposed 3D modeling system gives high accuracy with acceptable depth measurements. [ABSTRACT FROM AUTHOR]

Abstract: Electroencephalography is an important clinical tool for the evaluation and treatment of neurophysiologic disorders related to epilepsy. Careful analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders. The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. In this study, we have proposed subspace-based methods to analyze and characterize epileptiform discharges in the form of 3-Hz spike and wave complex in patients with absence seizure. The variations in the shape of the EEG power spectra were examined in order to obtain medical information. These power spectra were then used to compare the applied methods in terms of their frequency resolution and the effects in determination of epileptic seizure. Global performance of the proposed methods was evaluated by means of the visual inspection of power spectral densities (PSDs). Graphical results comparing the performance of the proposed methods with that of the autoregressive techniques were given. The results demonstrate consistently superior performance of the proposed methods over the autoregressive ones. [Copyright &y& Elsevier]

In this study, wave excitation and radiation terms in 2DOF equations of vertical ship motion are obtained by using a URANS solver based on the finite volume method. The DTMB 5512 hull form is chosen for the calculations at the Froude number of 0.41. Numerical simulations are performed for 7 different regular wave conditions. First, in the regular wave, the excitation heave force and pitch moment with the related phase angle are computed while the ship is fixed to heave and pitch motions. Then, the body is forced to oscillate in the heave and pitch directions with a certain frequency and the radiation coefficients are obtained. After finding the excitation and radiated terms, the 2DOF vertical ship motion equations are solved in the frequency domain, and motion transfer functions are plotted. The results are compared with those obtained through strip theory, fully nonlinear URANS approach and experiments. The new URANS based approach presented in this paper offers a more accurate prediction of vertical ship motions compared to strip theory outputs because it takes the viscous effects and free surface nonlinearities into account. The new URANS based approach can be considered as a better alternative to the fully nonlinear URANS approach. [ABSTRACT FROM AUTHOR]