Diagnostic machine learning applications on clinical populations using functional near infrared spectroscopy: a review.

Functional near-infrared spectroscopy (fNIRS) and its interaction with machine learning (ML) is a popular research topic for the diagnostic classification of clinical disorders due to the lack of robust and objective biomarkers. This review provides an overview of research on psychiatric diseases by using fNIRS and ML. Article search was carried out and 45 studies were evaluated by considering their sample sizes, used features, ML methodology, and reported accuracy. To our best knowledge, this is the first review that reports diagnostic ML applications using fNIRS. We found that there has been an increasing trend to perform ML applications on fNIRS-based biomarker research since 2010. The most studied populations are schizophrenia (n = 12), attention deficit and hyperactivity disorder (n = 7), and autism spectrum disorder (n = 6) are the most studied populations. There is a significant negative correlation between sample size (>21) and accuracy values. Support vector machine (SVM) and deep learning (DL) approaches were the most popular classifier approaches (SVM = 20) (DL = 10). Eight of these studies recruited a number of participants more than 100 for classification. Concentration changes in oxy-hemoglobin (ΔHbO) based features were used more than concentration changes in deoxy-hemoglobin (ΔHb) based ones and the most popular ΔHbO-based features were mean ΔHbO (n = 11) and ΔHbO-based functional connections (n = 11). Using ML on fNIRS data might be a promising approach to reveal specific biomarkers for diagnostic classification.

Identification of TLE Focus from EEG Signals by Using Deep Learning Approach.

Temporal lobe epilepsy, a neurological disease that causes seizures as a result of excessive neural activities in the brain, is the most common type of focal seizure, accounting for 30-35% of all epilepsies. Detection of epilepsy and localization of epileptic focus are essential for treatment planning and epilepsy surgery. Currently, epileptic focus is decided by expert physician by examining the EEG records and determining EEG channel where epileptic patterns begins and continues intensely during seizure. Examination of long EEG recordings is very time-consuming process, requires attention and decision can vary depending on physician. In this study, to assist physicians in detecting epileptic focus side from EEG recordings, a novel deep learning-based computer-aided diagnosis system is presented. In the proposed framework, ictal epochs are detected using long short-term memory network fed with EEG subband features obtained by discrete wavelet transform, and then, epileptic focus identification is realized by using asymmetry score. This algorithm was tested on EEG database obtained from the Ankara University hospital. Experimental results showed ictal and interictal epochs were classified with accuracy of 86.84%, sensitivity of 86.96% and specificity of 89.68% on Ankara University hospital dataset, and 96.67% success rate was obtained on Bonn EEG dataset. In addition, epileptic focus was identified with accuracy of 96.10%, sensitivity of 100% and specificity of 93.80% by using the proposed deep learning-based algorithm and university hospital dataset. These results showed that proposed method can be used properly in clinical applications, epilepsy treatment and surgical planning as a medical decision support system.

Differentiation of Benign and Malignant Thyroid Nodules with ANFIS by Using Genetic Algorithm and Proposing a Novel CAD-Based Risk Stratification System of Thyroid Nodules.

The thyroid nodule risk stratification guidelines used in the literature are based on certain well-known sonographic features of nodules and are still subjective since the application of these characteristics strictly depends on the reading physician. These guidelines classify nodules according to the sub-features of limited sonographic signs. This study aims to overcome these limitations by examining the relationships of a wide range of ultrasound (US) signs in the differential diagnosis of nodules by using artificial intelligence methods. An innovative method based on training Adaptive-Network Based Fuzzy Inference Systems (ANFIS) by using Genetic Algorithm (GA) is used to differentiate malignant from benign thyroid nodules. The comparison of the results from the proposed method to the results from the commonly used derivative-based algorithms and Deep Neural Network (DNN) methods yielded that the proposed method is more successful in differentiating malignant from benign thyroid nodules. Furthermore, a novel computer aided diagnosis (CAD) based risk stratification system for the thyroid nodule's US classification that is not present in the literature is proposed.

Obstructive sleep apnea prediction from electrocardiogram scalograms and spectrograms using convolutional neural networks.

Objective.In this study, we conducted a comparative analysis of deep convolutional neural network (CNN) models in predicting obstructive sleep apnea (OSA) using electrocardiograms. Unlike other studies in the literature, this study automatically extracts time-frequency features by using CNNs instead of manual feature extraction from ECG recordings.Approach.The proposed model generates scalogram and spectrogram representations by transforming preprocessed 30 s ECG segments from time domain to the frequency domain using continuous wavelet transform and short time Fourier transform, respectively. We examined AlexNet, GoogleNet and ResNet18 models in predicting OSA events. The effect of transfer learning on success is also investigated. Based on the observed results, we proposed a new model that is found more effective in estimation. In total, 152 ECG recordings were included in the study for training and evaluation of the models.Main results.The prediction using scalograms immediately 30 s before potential OSA onsets gave the best performance with 82.30% accuracy, 83.22% sensitivity, 82.27% specificity and 82.95% positive predictive value. The prediction using spectrograms also achieved up to 80.13% accuracy and 81.99% sensitivity on prediction. Per-recording classification suggested considerable results with 91.93% accuracy for prediction of OSA events.Significance.Time-frequency deep features of scalograms and spectrograms of ECG segments prior to OSA events provided reliable information about the possible events in the future. The proposed CNN model can be used as a good indicator to accurately predict OSA events using ECG recordings.

Determination of initial electron parameters by means of Monte Carlo simulations for the Siemens Artiste Linac 6 MV photon beam.

AIM: In this study, we investigated initial electron parameters of Siemens Artiste Linac with 6 MV photon beam using the Monte Carlo method. BACKGROUND: It is essential to define all the characteristics of initial electrons hitting the target, i.e. mean energy and full width of half maximum (FWHM) of the spatial distribution intensity, which is needed to run Monte Carlo simulations. The Monte Carlo is the most accurate method for simulation of radiotherapy treatments. MATERIALS AND METHODS: Linac head geometry was modeled using the BEAMnrc code. The phase space files were used as input file to DOSXYZnrc simulation to determine the dose distribution in a water phantom. We obtained percent depth dose curves and the lateral dose profile. All the results were obtained at 100 cm of SSD and for a 10 × 10 cm2 field. RESULTS: We concluded that there existed a good conformity between Monte Carlo simulation and measurement data when we used electron mean energy of 6.3 MeV and 0.30 cm FWHM value as initial parameters. We observed that FWHM values had very little effect on PDD and we found that the electron mean energy and FWHM values affected the lateral dose profile. However, these effects are between tolerance values. CONCLUSIONS: The initial parameters especially depend on components of a linac head. The phase space file which was obtained from Monte Carlo Simulation for a linac can be used as calculation of scattering, MLC leakage, to compare dose distribution on patients and in various studies.

Classifying dysmorphic syndromes by using artificial neural network based hierarchical decision tree.

Dysmorphic syndromes have different facial malformations. These malformations are significant to an early diagnosis of dysmorphic syndromes and contain distinctive information for face recognition. In this study we define the certain features of each syndrome by considering facial malformations and classify Fragile X, Hurler, Prader Willi, Down, Wolf Hirschhorn syndromes and healthy groups automatically. The reference points are marked on the face images and ratios between the points' distances are taken into consideration as features. We suggest a neural network based hierarchical decision tree structure in order to classify the syndrome types. We also implement k-nearest neighbor (k-NN) and artificial neural network (ANN) classifiers to compare classification accuracy with our hierarchical decision tree. The classification accuracy is 50, 73 and 86.7% with k-NN, ANN and hierarchical decision tree methods, respectively. Then, the same images are shown to a clinical expert who achieve a recognition rate of 46.7%. We develop an efficient system to recognize different syndrome types automatically in a simple, non-invasive imaging data, which is independent from the patient's age, sex and race at high accuracy. The promising results indicate that our method can be used for pre-diagnosis of the dysmorphic syndromes by clinical experts.

Does hypericin boost the efficacy of high-power laser? A preliminary experimental study on rats / A hipericina aumenta a eficácia do laser de alta potência? Um estudo preliminar e experimental em ratos

CONTEXT AND OBJECTIVE: Lasers are widely used in treating symptomatic benign prostatic hyperplasia. In current practice, potassium titanyl phosphate (KTP) lasers are the most common type of laser systems used. The aim here was to evaluate the rapid effect of high-power laser systems after application of hypericin. DESIGN AND SETTING: Experimental animal study conducted in the Department of Urology, Gülhane Military Medical Academy, Ankara, Turkey, in 2012. METHODS: Sixteen rats were randomized into four groups: 120 W KTP laser + hypericin; 120 W KTP laser alone; 80 W KTP laser + hypericin; and 80 W KTP laser alone. Hypericin was given intraperitoneally two hours prior to laser applications. The laser incisions were made through the quadriceps muscle of the rats. The depth and the width of the laser incisions were evaluated histologically and recorded. RESULTS: To standardize the effects of the laser, we used the ratio of depth to width. These new values showed us the depth of the laser application per unit width. The new values acquired were evaluated statistically. Mean depth/width values were 231.6, 173.6, 214.1 and 178.9 in groups 1, 2, 3 and 4, respectively. The most notable result was that higher degrees of tissue penetration were achieved in the groups with hypericin (P < 0.05). CONCLUSIONS: The encouraging results from our preliminary study demonstrated that hypericin may improve the effects of KTP laser applications. .

CONTEXTO E OBJETIVO: Lasers são amplamente utilizados no tratamento de hiperplasia benigna de próstata sintomática. Na prática atual, lasers de fosfato de titanilo de potássio (KTP) são os tipos mais comuns usados dos sistemas. O objetivo foi avaliar o efeito rápido do sistema laser de alta potência após a aplicação de hipericina. TIPO DE ESTUDO E LOCAL: Estudo experimental animal, realizado no Departamento de Urologia, Academia de Medicina Militar de Gülhane, Ancara, Turquia, em 2012. MÉTODOS: 16 ratos foram divididos aleatoriamente em 4 grupos: 120W KTP laser + hipericina; 120W KTP laser somente; 80W KTP laser + hipericina; 80W KTP laser somente. Hipericina foi dada intraperitonealmente duas horas antes da aplicação do laser. As incisões a laser foram feitas através do músculo quadríceps dos ratos. A profundidade e a largura das incisões a laser foram avaliadas histologicamente e registradas. RESULTADOS: Para padronizar o efeito do laser foi utilizada a razão entre profundidade e largura. Estes novos valores nos mostraram a profundidade da aplicação do laser de largura por unidade. Os novos valores adquiridos foram avaliados estatisticamente. Os valores da média de profundidade/largura foram 231,6, 173,6, 214,1 e 178,9 nos grupos 1, 2, 3 e 4, respectivamente. O resultado mais notável foi atingir altos graus de penetração tecidual nos grupos com hipericina (P < 0,05). CONCLUSÕES: Os resultados promissores do nosso estudo preliminar mostraram que hipericina pode melhorar os efeitos das aplicações do laser KTP. .

Does hypericin boost the efficacy of high-power laser? A preliminary experimental study on rats.

CONTEXT AND OBJECTIVE: Lasers are widely used in treating symptomatic benign prostatic hyperplasia. In current practice, potassium titanyl phosphate (KTP) lasers are the most common type of laser systems used. The aim here was to evaluate the rapid effect of high-power laser systems after application of hypericin. DESIGN AND SETTING: Experimental animal study conducted in the Department of Urology, Gülhane Military Medical Academy, Ankara, Turkey, in 2012. METHODS: Sixteen rats were randomized into four groups: 120 W KTP laser + hypericin; 120 W KTP laser alone; 80 W KTP laser + hypericin; and 80 W KTP laser alone. Hypericin was given intraperitoneally two hours prior to laser applications. The laser incisions were made through the quadriceps muscle of the rats. The depth and the width of the laser incisions were evaluated histologically and recorded. RESULTS: To standardize the effects of the laser, we used the ratio of depth to width. These new values showed us the depth of the laser application per unit width. The new values acquired were evaluated statistically. Mean depth/width values were 231.6, 173.6, 214.1 and 178.9 in groups 1, 2, 3 and 4, respectively. The most notable result was that higher degrees of tissue penetration were achieved in the groups with hypericin (P < 0.05). CONCLUSIONS: The encouraging results from our preliminary study demonstrated that hypericin may improve the effects of KTP laser applications.

Down syndrome diagnosis based on Gabor Wavelet Transform.

Down syndrome is a chromosomal condition caused by the presence of all or part of an extra 21st chromosome. It has different facial symptoms. These symptoms contain distinctive information for face recognition. In this study, a novel method is developed to distinguish Down Syndrome in a custom face database. Gabor Wavelet Transform (GWT) is used as a feature extraction method. Dimension reduction is performed with Principal Component Analysis (PCA). New dimension which has most valuable information is derived with Linear Discriminant Analysis (LDA). Classification process is implemented with k-nearest neighbor (kNN) and Support Vector Machine (SVM) methods. The classification accuracy is carried out 96% and 97,34% with kNN and SVM methods, respectively. Different from the studies related with the Down Sydrome, feature selection process is applied before PCA according to the correlation between components of feature vectors. Best results are achieved with euclidean distance metric for kNN and linear kernel type for SVM. In this way, we developed an efficient system to recognize Down syndrome.

Effects of electromagnetic radiation from a cellular phone on human sperm motility: an in vitro study.

BACKGROUND: There has been growing public concern on the effects of electromagnetic radiation (EMR) emitted by cellular phones on human health. Many studies have recently been published on this topic. However, possible consequences of the cellular phone usage on human sperm parameters have not been investigated adequately. METHODS: A total number of 27 males were enrolled in the study. The semen sample obtained from each participant was divided equally into two parts. One of the specimens was exposed to EMR emitted by an activated 900 MHz cellular phone, whereas the other was not. The concentration and motility of the specimens were compared to analyze the effects of EMR. Assessment of sperm movement in all specimens was performed using four criteria: (A) rapid progressive, (B) slow progressive, (C) nonprogressive, (D) no motility. RESULTS: Statistically significant changes were observed in the rapid progressive, slow progressive and no-motility categories of sperm movement. EMR exposure caused a subtle decrease in the rapid progressive and slow progressive sperm movement. It also caused an increase in the no-motility category of sperm movement. There was no statistically significant difference in the sperm concentration between two groups. CONCLUSIONS: These data suggest that EMR emitted by cellular phone influences human sperm motility. In addition to these acute adverse effects of EMR on sperm motility, long-term EMR exposure may lead to behavioral or structural changes of the male germ cell. These effects may be observed later in life, and they are to be investigated more seriously.

The addition of O2 to the CO2 does not prevent the systemic effects of the CO2 pneumoperitoneum in a rabbit model.

CO2 pneumoperitoneum used in endoscopic surgery induces systemic effects by CO2 absorption. It was claimed that a reduction in CO2 pneumoperitoneum-induced metabolic hypoxemia was achieved by the addition of small amounts of O2 to the CO2 in a rabbit ventilated model. We reevaluated the effects of the addition of O2 to the CO2 pneumoperitoneum upon CO2 absorption in a rabbit model. The effects of a pneumoperitoneum using 100% CO2, 90% CO2 + 10% O2, 95% CO2 + 5% O2, or 100% O2 on arterial blood gases, acid base and O2 homeostasis were evaluated in nonintubated rabbits. A pneumoperitoneum pressure of 10 cm H2O (approximately 7.35 mm Hg) was used. CO2 pneumoperitoneum of 120 minutes affected blood gases and acid base homeostasis. Whereas partial pressure of CO2 and HCO3 increased (P < 0.001) during pneumoperitoneum, pH and partial pressure of O2 decreased (P < 0.001). Similar results were obtained in O2-CO2 pneumoperitoneum (P > 0.05). CO2 pneumoperitoneum profoundly affected blood gases and acid base homeostasis, resulting in metabolic hypoxemia. The addition of O2 to the CO2 did not prevent the systemic effects of CO2 pneumoperitoneum in nonintubated animals.

Effects of tonsillectomy on speech spectrum.

Changes in the speech spectrum of vowels and consonants before and after tonsillectomy were investigated to find out the impact of the operation on speech quality. Speech recordings obtained from patients were analyzed using the Kay Elemetrics, Multi-Dimensional Voice Processing (MDVP Advanced) software. Examination of the time-course changes after the operation revealed that certain speech parameters changed. These changes were mainly F3 (formant center frequency) and B3 (formant bandwidth) for the vowel /o/ and a slight decrease in B1 and B2 for the vowel /a/. The noise-to-harmonic ratio (NHR) also decreased slightly, suggesting less nasalized vowels. It was also observed that the fricative, glottal consonant /h/ has been affected. The larger the tonsil had been, the more changes were seen in the speech spectrum. The changes in the speech characteristics (except F3 and B3 for the vowel /o/) tended to recover, suggesting an involvement of auditory feedback and/or replacement of a new soft tissue with the tonsils. Although the changes were minimal and, therefore, have little effect on the extracted acoustic parameters, they cannot be disregarded for those relying on their voice for professional reasons, that is, singers, professional speakers, and so forth.