The need for encryption techniques capable of ensuring the security of medical images is increasing due to the frequent exchange of these images among healthcare professionals and institutions. Ensuring the security of Digital Imaging and Communications in Medicine (DICOM) images is highly critical, as this standard is widely adopted for exchanging medical imaging data. The proposed medical image encryption method enables secure and robust encryption of grayscale or color images of any size and depth. The encryption algorithm is based on a newly created chaotic map. The classical Chirp signal has been modified to exhibit chaotic behavior, and this modification is referred to as the hyperbolic Chirp signal based chaotic map (HCBCM). The bifurcation and phase diagrams of the HCBCM function are presented, alongside comparative analyses of Lyapunov exponent and entropy plots against other recently developed chaotic maps. Performance evaluations demonstrate that HCBCM possesses strong cryptographic characteristics. Additionally, a novel algorithm utilizing O-shaped scanning, combined with permutation and diffusion, has been introduced for encrypting DICOM images. Testing with DICOM images of various modalities, sizes, and depths validates the algorithm's effectiveness, with security analysis confirming its reliability for medical image encryption.

The most predictive sensors, sensor positions, and features for detecting falls early in elderly people were investigated using feature dataset from three-axis accelerometers placed on the head, pelvis, right and left shank, and pressure-sensing insoles. A feature database containing records of 100 older people (76 non-fallers and 24 fallers) was used. The three different feature selection algorithm was used, and most predictive feature vector obtained. An SVM classification model was developed for each feature vector. As a result, the best classification accuracy was observed for features determined by the feature selection algorithm using the chi-square test. In the classification using ten features of the acceleration signal recorded from the head, 80.17% (+/- 8.33) accuracy, 43.99% (+/- 21.93) sensitivity, and 91.59% (+/- 9.57) specificity were obtained. These results demonstrate that a sufficiently accurate model can be developed using a sensor and activity when the correct feature selection and classification algorithm is determined.

This paper presents a novel image encryption algorithm based on a newly proposed two-dimensional hyperchaotic map derived from the chirp signal. Performance evaluations of the proposed map include bifurcation analysis, phase portrait visualization, sensitivity to initial conditions, Lyapunov exponent calculations, entropy measurements, and NIST tests. These evaluations confirm the map's strong randomness and broad chaotic behavior. The proposed encryption algorithm utilizes the high sensitivity to initial conditions and wide chaotic range of the hyperchaotic map to enhance security. The algorithm achieves a high degree of confusion and diffusion through bit-level manipulation, chaotic permutation, and randomized row-column diffusion processes. As a result, it can effectively encrypt images of any size, whether color or grayscale. Comprehensive security evaluations, such as key analysis, histogram analysis, Shannon entropy analysis, correlation analysis, differential analysis, and robustness analysis, confirm the algorithm's resilience against a wide range of cryptographic attacks. Thus, the proposed algorithm offers a promising solution for secure image transmission.

Hippocampal field potentials are widely used in research on neurodegenerative diseases, epilepsy, neuropharmacology, and particularly long- and short-term synaptic plasticity. To conduct these studies, it is necessary to identify specific components within hippocampal field potential signals. However, manually marking the relevant signal points for analysis is a time-consuming, error-prone, and subjective process. Currently, there is no specialized software dedicated to automating this task. In this study, three different recurrent neural network-based deep learning architectures were examined for the automatic segmentation of hippocampal field potential signals in two separate experimental studies. In the first experimental study, 10,836 epochs of field potential signals recorded from 54 rats were used, and in the second experimental study, field potential signals with noise added to the above data at different rates were used. The best model achieved an average f-score of 98.1% on noise-free data and 97.15% on data with noise, highlighting its robustness in real-world scenarios. Furthermore, we assessed system stability using the repeated holdout method, which randomly split the data into training and testing sets 100 times, and each time trained a new version of the system. As a result, the proposed system was proven to be reliable and generalizable by showing similar average scores and low variability across all 100 iterations of the test.

There is no effective fall risk screening tool for the elderly that can be integrated into clinical practice. Developing a system that can be easily used in primary care services is a current need. Current studies focus on the use of multiple sensors or activities to achieve higher accuracy. However, multiple sensors and activities reduce the availability of these systems. This study aims to develop a system to perform fall prediction for the elderly by using signals recorded from a single sensor during a short-term activity. A total of 168 features in the time and frequency domains were created using acceleration signals obtained from 71 elderly people. The features were weighted based on the ReliefF algorithm, and the artificial neural networks model was developed using the most important features. The best classification result was obtained using the 17 most important features of those weighted for K = 20 nearest neighbors. The highest accuracy was 82.2

This paper proposes a new medical image encryption algorithm that can effectively encrypt medical images of various sizes and modalities. The encryption algorithm is mainly based on a newly developed one-dimensional chaotic map, derived by combining and then transforming the traditional sine and Chebyshev maps. Dynamical analyses show that the proposed map outperforms various 1D maps in terms of chaotic behavior and randomness. The designed medical image encryption algorithm utilizes permutation-diffusion operations, with chaotic parameters derived from the proposed highly chaotic 1D map to perform these operations. The algorithm was tested on various medical images with different sizes and modalities to evaluate its performance. The results from the simulations of security analysis demonstrate its effectiveness in encrypting medical images.

Chaotic maps have wide application areas due to their unpredictable behavior and sensitivity to initial conditions and control parameters. This paper presents a new chaotic map derived from polynomial chirp functions. The performance of the generated map is evaluated using bifurcation diagrams, phase portraits, Lyapunov exponents and sample entropy. To demonstrate the effectiveness of the map, random numbers are generated with a simple PRNG algorithm and analyzed with histogram, Shannon entropy, and NIST test. As a result of the evaluation, it is seen that both the proposed map has a wide chaotic range and a uniform distribution in the phase space and the numbers generated by the new map-based PRNG have perfect randomness.

Few studies have investigated differences in functional connectivity (FC) between patients with subcortical ischemic vascular disease (SIVD) and Alzheimer's disease (AD), especially in relation to apathy. Therefore, the aim of this study was to compare apathy-related FC changes among patients with SIVD, AD, and cognitively normal subjects. The SIVD group had the highest level of apathy as measured using the Apathy Evaluation Scale-clinician version (AES). Dementia staging, volume of white matter hyperintensities (WMH), and the Beck Depression Inventory were the most significant clinical predictors for apathy. Group-wise comparisons revealed that the SIVD patients had the worst level of "Initiation" by factor analysis of the AES. FCs from four resting state networks (RSNs) were compared, and the connectograms at the level of intra- and inter-RSNs revealed dissociable FC changes, shared FC in the dorsal attention network, and distinct FC in the salient network across SIVD and AD. Neuronal correlates for "Initiation" deficits that underlie apathy were explored through a regional-specific approach, which showed that the right inferior frontal gyrus, left middle frontal gyrus, and left anterior insula were the critical hubs. These findings broaden the disconnection theory by considering the effect of FC interactions across multiple RSNs on apathy formation.

Yaslanmayla birlikte vucutta meydana gelen anatomik ve fizyolojik degisimlerin bir sonucu olarak yasli bireylerde dusme bir saglik problemi olarak karsimiza cikmaktadir. Dunya saglik orgutune gore dusme yaslilarda gorulen en onemli saglik problemidir. Dusmenin yaslinin fiziksel olarak yaralanmasi ve dusme korkusunun getirdigi psikolojik etkinin yaninda hastaya, aileye ve topluma ekonomik olarak etkileri vardir. Dunyada ve ulkemizde saglik alaninda meydana gelen gelismelerle beraber bireylerin yasam suresinin hizla artmasiyla bu etki daha da belirgin hale gelecektir. Ancak yaslilarda dusmenin onlenmesi ile bu olumsuz etkiler azaltilabilir. Yaslilarda dusmenin etkilerini azaltmak icin etkili yontem dusmenin onceden tahmin edilmesi ve gerekli onlemlerin alinmasidir. Dusmenin onceden tahmin edilebilmesi icin yaslilarda rutin kontrollerinde dengenin degerlendirilmesi gerekmektedir. Bunun icin birinci basamak saglik kuruluslarinda kullanilabilecek basit, ucuz ve guvenilir bir denge degerlendirme metodunun gelistirilmesi onemlidir. Durus ve hareket siniflandirmasi, enerji harcama tahmini, anlik dusme tespiti ve denge kontrolu gibi fiziksel aktivite izleme ve degerlendirme arastirmalarinda siklikla kullanilan ivmeolcerler yaslilarda dusme riskinin degerlendirmesi icin rahatlikla kullanilabilir. Bu calismada yaslari 65 ile 87 arasinda degisen 71 yaslidan (38 kontrol 35 dusme riski olan) duz zeminde yurume esnasinda kayit edilen bir dakikalik uc eksen ivmelenme sinyalleri kullanilarak yaslilarda dusme riskini tanimlayici parametreler bulunmaya calisilmistir. Once kayit edilen ivmelenme sinyalinden yer cekiminden kaynaklanan bilesen cikarilmis, daha sonra 0.5Hz-5Hz bant geciren filtreyle yuksek frekansli gurultuler temizlenmistir. Gurultu temizleme isleminden sonra bir dakikalik kayitlar adimlara bolunmus ve normalize edilerek ozellik cikarma islemine gecilmistir. Ozellik cikarma asamasinda literaturden farkli olarak daha once yaslilarda dusme riski icin kullanilmayan zaman-domeni ozellikleri de degerlendirilmeye alinmistir. Elde edilen ozellikler bagimsiz-orneklem t-testi kullanilarak %99 guvenirlik seviyesinde karsilastirilmistir. Sonuc olarak literaturde anlamli olarak farkli oldugu daha onceki calismalarda belirtilen kadans, adim suresi, cift adim suresi ozellikleri benzer sekilde bizim calismamizda da kontrol ile dusen gruplari arasinda anlamli farklilik gostermistir. Ayrica literaturde daha once dusme riskinin degerlendirilmesi icin yapilan calismalarda kullanilmayan carpiklik, ceyrekler arasi aralik, ortalama mutlak sapma ve dinamik zaman atlama ozelliklerinde de anlamli farklilik oldugu gorulmustur. Calismamizda ivmelenme sinyallerinden elde edilebilecek butun zaman domeni ozellikleri dusme riskinin belirlenmesi icin degerlendirilmistir. Sonuc olarak literaturde daha once dusme riski icin kullanilmayan dort yeni zaman domeni ozelliginin dusme riskini belirlemede kullanilabilecegi ortaya konmustur.

Every year, about 28-35% of people aged 65 and over in the world fall at least once, and this number will increase rapidly in the coming years. Apart from physical injury after fall, it is seen in post-fall syndromes such as addiction, loss of autonomy and depression after treatment. The impact of the fall on the individual and economically on the society is at a level that cannot be ignored and is gradually increasing. However, the fall can be prevented by correct approaches. In order to prevent fall in the elderly, balance assessment should be done frequently and precaution should be taken for individuals at risk of fall. A wide range of tools are available for balance assessment, from simple questionnaires to complex computerized tests. However, questionnaire are subjective. Computerized tests, on the other hand, are not suitable to be used in primary health care centers due to their cost and volume. Therefore, it is very important to develop a simple method that can be used in primary health care centers. Accelerometers have taken their place in wearable technology with their light, cheap and simple structures and can be used in balance assessment. In this study, it was tried to find parameters that define fall risk of the elderly by using the three axis acceleration signal recorded from the elderly with 38 non-faller 35 faller in PhysioNet database. For this, the component caused by gravity was first removed from the acceleration signal, filtered with 0.5 Hz high pass and 25 Hz low pass filter and normalized to maximum. Then, power spectrum density of acceleration signals were found using autoregressive model with 25 model order by Burg's algorithm. 29 features were obtained for all three axes, namely the descriptive features of the first and second dominant peaks in the power spectrum, the statistical features of the power spectrum, and the features related to the energy of the power spectrum. These features were compared using the independent-sample t-test at 99% confidence level. As a result, it was observed that a total of four different features showed statistically significant difference between the two groups. Among these features, the kurtosis of the power spectrum and the width of the second largest hill are added to the literature with this study.

Üst ekstremite fonksiyonları ve özellikle el beceresi kişilerin günlük yaşam kalitesini etkileyen en önemli faktörlerden biridir. Üst ekstremite fonksiyon bozuklukları çoklu sertleşim (multipl skleroz, MS), Parkinson gibi merkezi sinir sistemi hastalıklarının bir belirtisi olabileceği gibi, kaza sonrası yaralanmalar ve inme gibi durumlarda da ortaya çıkmaktadır. Üst ekstremitenin değerlendirilmesinde basit, ucuz bir yöntem olan dokuz-delik çubuk testi altın standart olarak kullanılmaktadır. Bu testte hastadan çubukları istedikleri sırayla deliklere yerleştirmesi ve geri toplaması istenir. Testin süresi uzman tarafından bir kronometre aracılığıyla ölçülür. Literatürde bu testi geliştirmek amacıyla yapılmış bazı çalışmalar vardır. Bu çalışmalarda test haptik cihazlar, kameralar vb. kullanılarak sanal gerçeklik ortamında yapılmıştır. Ancak bütün bu yenilikçi yaklaşımlarda testin basitliği ve sistem maliyeti göz ardı edilmektedir. Bu çalışmada üst ekstremite fonksiyonlarının özellikle el becerisinin değerlendirilmesi için uzmandan bağımsız süre ölçümü yapan, basit ve ucuz bir elektronik dokuz-delik çubuk test cihazı geliştirmek amaçlanmıştır. Bunun yanında standart teste ilave olarak testin yönlendirilmiş olarak (hangi çubuğun hangi deliğe yerleştirileceğinin belirtilmesiyle) gerçekleştirileceği yeni bir versiyonu önerilmiş ve ayrı bir test seçeneği olarak programlanmıştır. Bu amaçla standart dokuz-delik çubuk testi ile aynı ölçülerde lazer kesim ahşap yapıştırma yöntemiyle dış çerçeve oluşturulmuştur. Çubukların yerleştirilip yerleştirilmediğini anlayabilmek için deliklerin altında optik sensörler, sonuçların gösterilmesi ve testin yönlendirilmesi için bir LCD ekran ve yedi segment gösterge, gelen verileri değerlendirmek ve sistem kontrolünü sağlamak için bir mikrodenetleyici kullanılmıştır. Sonuç olarak amaçlanan uzmandan bağımsız, güvenilir bir süre ölçümü sağlayacak elektronik test cihazı başarı ile yapılmıştır. Ayrıca her bir çubuğun yerleştirilmesi için harcanan sürenin de ölçülüp testin kapsamı genişletilerek uzmana kronometre ile tek tek ölçülmesi mümkün olmayan ekstra veriler sunulmuştur. Ek olarak hastanın zihinsel fonksiyonunu değerlendirebileceğini düşündüğümüz yönlendirilmiş test yazılıma ilave edilmiştir.

Thrombosis on the valve that prevents the movement of mechanical heart valves is a fatal disease requiring urgent intervention. Thrombosis is detected by echocardiographic findings and/or CT images. In this study, it has been tried to determine the formation of thrombosis by listening method which has been used for controlling the functionality of the heart valves for years. For this firstly heart sounds of patients with thrombosis and normal mechanical heart valves were recorded. Then the first and second heart sounds (S1 and S2) were separated from the recorded sounds. After the frequency spectrum of S1 and S2 were found using autoregressive spectrum estimation methods, six features were obtained regarding the frequency components. Then the features obtained are classified by support vector machine methods. The accuracy value was found to be 100% by using the 3 fold cross-validation. The average accuracy is 95.18% as a result of running the classifier 500 times using 3 fold-cross validation.

The aim of this study is to examine mechanical heart valve sounds using discrete wavelet transform for the diagnosis of paravalvular leakage (PVL) occurs after mechanical heart valve (MHV) replacement. For this aim, mechanical heart sounds of 2 patients with PVL and 5 volunteers with normal MHV was recorded. The recorded mechanical heart valve sounds are decomposed to detail and approximation coefficient using discrete wavelet transform. Features extracted from detail and approximation coefficients used for statically comparison of normal and patients data groups. As a result of comparison, it seen that the features obtained from Daubechies 2 wavelet function can be used to detect paravalvular leakage on mechanical heart valve. As a result, it is statically shown that Daubechies 2 wavelet function is suitable for diagnosis of PVL.

Discrete wavelet transform has been proposed for the diagnosis of paravalvular leakage(PVL) occurs after Mechanical Heart Valve(MHV) replacement. Mechanical heart sounds of 2 patients with PVL and 5 volunteers with normal MHV was recorded and analyzed with different wavelets. As a result, it is statically shown that Daubechies 2 wavelet function is suitable for diagnosis of PVL.

A mechanical heart valve is a device substituted for native heart valve. These valves are generally replaced with mitral or aorta valves. To found whether aorta or mitral heart valve replaced with mechanical one of patients is easy for specialist using stethoscope or chest X-ray. Expert system evaluating mechanical heart valve disease cannot deduce position of replaced heart valve. Thus, we aimed to determine which heart valve of patients was replaced with mechanical one to use preprocessing step in expert systems finding malfunctioning mechanical valve in this study. Electrocardiogram signal and 6 features extracted from power density of heart sounds were used to determine replaced heart valve using artificial neural networks. The heart sounds were separated into four parts according to recording area and sound component. Then, artificial neural networks was separately trained and tested for four sounds using the 6 features. As a result, the mechanical heart valve of patients was detected with 96.55% accuracy from the features of second heart sounds recorded from mitral area.

In this article, the spectral features of first heart sounds (S1) and second heart sounds (S2), which comprise the mechanical heart valve sounds obtained after aortic valve replacement (AVR) and mitral valve replacement (MVR), are compared to find out the effect of mechanical heart valve replacement and recording area on S1 and S2. For this aim, the Welch method and the autoregressive (AR) method are applied on the S1 and S2 taken from 66 recordings of 8 patients with AVR and 98 recordings from 11 patients with MVR, thereby yielding power spectrum of the heart sounds. Three features relating to frequency of heart sounds and three features relating to energy of heart sounds are obtained. Results show that in comparison to natural heart valves, mechanical heart valves contain higher frequency components and energy, and energy and frequency components do not show common behaviour for either AVR or MVR depending on the recording areas. Aside from the frequency content and energy of the sound generated by mechanical heart valves being affected by the structure of the lungsthorax and the recording areas, the pressure across the valve incurred during AVR or MVR is a significant factor in determining the frequency and energy levels of the valve sound produced. Though studies on native heart sounds as a non-invasive diagnostic method has been done for many years, it is observed that studies on mechanical heart valves sounds are limited. The results of this paper will contribute to other studies on using a non-invasive method for assessing the mechanical heart valve sounds.

Thrombosis of implanted heart valve is a rare but lethal complication for patients with mechanical heart valve. Echocardiogram of mechanical heart valves is necessary to diagnose valve thrombosis definitely. Because of the difficulty in making early diagnosis of thrombosis, and the cost of diagnosis equipment and operators, improving noninvasive, cheap and simple methods to evaluate the functionality of mechanical heart valves are quite significant especially for first step medical center. Because of this, time domain features obtained from auscultation of heart sounds are proposed to evaluate mechanical heart valve thrombosis as a simple method in this chapter. For this aim, heart sounds of one patient with mechanical heart valve thrombosis and five patients with normally functioning mechanical heart valve were recorded. Time domain features of recorded heart sounds, the skewness and kurtosis, were calculated and statistically evaluated using paired and unpaired t-test. As a result, it is clearly seen that the skewness of first heart sound is the most discriminative features (p < 0.01) and it may be used fairly well in differentiating normally functioning mechanical heart valve from malfunctioning mechanical heart valve.

Thrombosis is a serious complication and important cause of mortality and morbidity reason for patients with mechanical heart valve. Echocardiogram of mechanical heart valves is necessary to diagnose valve thrombosis definitely. Because of the difficulty in making early diagnosis of thrombosis, and the cost of diagnosis equipment and operators, improving noninvasive, cheap and simple methods to evaluate the functionality of mechanical heart valves are quite significant. In this study, statistical features obtained from auscultation of heart sounds are proposed to evaluate mechanical heart valve thrombosis as a simple method. For this aim, heart sounds of one patient with mechanical heart valve thrombosis and five patients with normally functioning mechanical heart valve were recorded. Statistical features of these sounds, the skewness and kurtosis, were calculated and statistically evaluated using t-test. As a result, it is clearly seen that the skewness of Si sounds is the most discriminative features (p < 0.01) and it may be used fairly well in differentiating normally functioning mechanical heart valve from malfunctioning mechanical heart valve.