Discrimination between non-functioning pituitary adenomas and hypophysitis using machine learning methods based on magnetic resonance imaging­derived texture features.

PURPOSE: Hypophysitis is a heterogeneous condition that includes inflammation of the pituitary gland and infundibulum, and it can cause symptoms related to mass effects and hormonal deficiencies. We aimed to evaluate the potential role of machine learning methods in differentiating hypophysitis from non-functioning pituitary adenomas. METHODS: The radiomic parameters obtained from T1A-C images were used. Among the radiomic parameters, parameters capable of distinguishing between hypophysitis and non-functioning pituitary adenomas were selected. In order to avoid the effects of confounding factors and to improve the performance of the classifiers, parameters with high correlation with each other were eliminated. Machine learning algorithms were performed with the combination of gray-level run-length matrix-low gray level run emphasis, gray-level co-occurrence matrix-correlation, and gray-level co-occurrence entropy. RESULTS: A total of 34 patients were included, 17 of whom had hypophysitis and 17 had non-functioning pituitary adenomas. Among the 38 radiomics parameters obtained from post-contrast T1-weighted images, 10 tissue features that could differentiate the lesions were selected. Machine learning algorithms were performed using three selected parameters; gray level run length matrix-low gray level run emphasis, gray-level co-occurrence matrix-correlation, and gray level co-occurrence entropy. Error matrices were calculated by using the machine learning algorithm and it was seen that support vector machines showed the best performance in distinguishing the two lesion types. CONCLUSIONS: Our analysis reported that support vector machines showed the best performance in distinguishing hypophysitis from non-functioning pituitary adenomas, emphasizing the importance of machine learning in differentiating the two lesions.

Ethical Issues in Neuromarketing: "I Consume, Therefore I am!".

Neuromarketing is a recent interdisciplinary field which crosses traditional boundaries between neuroscience, neuroeconomics and marketing research. Since this nascent field is primarily concerned with improving marketing strategies and promoting sales, there has been an increasing public aversion and protest against it. These protests can be exemplified by the reactions observed lately in Baylor School of Medicine and Emory University in the United States. The most recent attempt to stop ongoing neuromarketing research in France is also remarkable. The pertaining ethical issues have been continuously attracting much attention, especially since the number of neuromarketing companies has exceeded 300 world-wide. This paper begins with a brief introduction to the field of neurotechnology by presenting its current capabilities and limitations. Then, it will focus on the ethical issues and debates most related with the recent applications of this technology. The French Parliament's revision of rules on bioethics in 2004 has an exemplary role in our discussion. The proposal by Murphy et al. (2008) has attracted attention to the necessity of ethical codes structuring this field. A code has recently been declared by the Neuromarketing Science and Business Association. In this paper, it is argued that these technologies should be sufficiently discussed in public spheres and its use on humans should be fully carried out according to the ethical principles and legal regulations designed in line with human rights and human dignity. There is an urgent need in the interdisciplinary scientific bodies like ethics committees monitoring the research regarding the scientific and ethical values of nonmaleficence, beneficence, autonomy, confidentiality, right to privacy and protection of vulnerable groups.

Physical and chemical characteristics of goldenberry fruit (Physalis peruviana L.).

Some physical and chemical characteristics of goldenberry fruit (Physalis peruviana L.) were investigated. These characteristics are necessary for the design of equipments for harvesting, processing, transportation, sorting, separating and packing. The fruit length, diameter, geometric and arithmetic mean diameters, sphericity, surface area, projected areas (vertical-horizontal) and aspect ratio of goldenberries were determined as 17.52 mm, 17.31 mm, 17.33 mm, 17.38 mm, 98.9 %, 0.949 cm(2), 388.67-387.85 mm(2) and 0.988, respectively. The mass of fruit, bulk density, fruit density, porosity and fruit hardness were 3.091 g, 997.3 kg/m(3), 462.3 kg/m(3), 53.61 % and 8.01 N, respectively. The highest static coefficient of friction was observed on rubber surface, followed by stainless steel sheet, aluminum sheet, and plywood materials. The dry matter, water soluble dry matter, ash, protein, oil, carbohydrate, titratable acidity, pH, total sugar, reducing sugar, antioxidant capacity were 18.67 %, 14.17 %, 2.98 %, 1.66 %, 0.18 %, 13.86 %, 1.26 %, 6.07, 63.90 g/kg, 31.99 g/kg and 57.67 %, respectively. The fresh fruits have 145.22 mg gallic acid equivalent (GAE)/100 g total phenol content and skin colour data represented as L*, a*, b*, Chroma (C) and Hue angle (α) were 49.92, 25.11, 50.23, 56.12 and 63.48, respectively.

The historical development and nutritional importance of olive and olive oil constituted an important part of the Mediterranean diet.

The olive tree (Olea europaea) is widely cultivated for the production of both oil and table olives and very significant because of its economic value. Olive and olive oil, a traditional food product with thousands of years of history, are the essential components of the Mediterranean diet and are largely consumed in the world. Beside of their economical contribution to national economy, these are an important food in terms of their nutritional value. Olive and olive oil may have a role in the prevention of coronary heart disease and certain cancers because of their high levels of monosaturated fatty acids and phenolic compounds. In addition, olives (Olea europaea L.) and olive oils provide a rich source of natural antioxidants. These make them both fairly stable against auto-oxidation and suitable for human health. The aim of this paper is to define the historical development and nutritional importance of olive and olive oil constituted an important part of the Mediterranean diet.

A new approach to enhance quinoa protein nano-aggregates: Combined pH shifting - High pressure homogenization.

The physicochemical characteristics of soluble nano-sized quinoa protein isolates prepared by combined pH shifting and high-pressure homogenization were studied. Commercial quinoa protein isolates were exposed to pH shifting at acidic (pH 2-6) or alkaline (pH 8-12) conditions followed by high-pressure homogenization earlier than neutralizing of pH to 7.0. The pH method under pH 12 followed by high-pressure homogenization was found as the most efficient treatment in the reduction of protein aggregate sizes and transparency, improving soluble protein content and surface hydrophobicity. Quinoa protein isolates treated with pH 12 and high-pressure homogenization increased the solubility from 7.85% to 78.97%, creating quinoa protein isolate nanoaggregates with an average size around 54 nm. The quinoa isolate aggregates were used to produce oil-in-water nanoemulsions, which demonstrated the good stability for 14 d at 4 °C. This new approach might present an effective technique for the modification of functional features of quinoa protein isolates.

Can diffusion tensor imaging have a diagnostic utility to differentiate early-onset forms of bipolar disorder and schizophrenia: A neuroimaging study with explainable machine learning algorithms.

BACKGROUND/AIM: Accurate diagnosis of early-onset psychotic disorders is crucial to improve clinical outcomes. This study aimed to differentiate patients with early-onset schizophrenia (EOS) from early-onset bipolar disorder (EBD) with machine learning (ML) algorithms using white matter tracts (WMT). METHOD: Diffusion tensor imaging was obtained from adolescents with either EOS (n = 43) or EBD (n = 32). Global probabilistic tractography using an automated tract-based TRACULA software was performed to analyze the fractional anisotropy (FA) of forty-two WMT. The nested cross-validation was performed in feature selection and model construction. EXtreme Gradient Boosting (XGBoost) was applied to select the features that can give the best performance in the ML model. The interpretability of the model was explored with the SHApley Additive exPlanations (SHAP). FINDINGS: The XGBoost algorithm identified nine out of the 42 major WMTs with significant predictive power. Among ML models, Support Vector Machine-Linear showed the best performance. Higher SHAP values of left acoustic radiation, bilateral anterior thalamic radiation, and the corpus callosum were associated with a higher likelihood of EOS. CONCLUSIONS: Our findings suggested that ML models based on the FA values of major WMT reconstructed by global probabilistic tractography can unveil hidden microstructural aberrations to distinguish EOS from EBD.

Automatic detection of bubbles in the subclavian vein using Doppler ultrasound signals.

INTRODUCTION: It is possible to detect venous gas bubbles by listening to the Doppler audio signals. However, a serious disadvantage of the audio evaluation is the inability of continuous monitoring and the inter-rater agreement. Several researchers have worked on the automated detection of emboli, but no current system has the required sensitivity and specificity for clinical use. METHOD: We developed software that integrated frequency filtering, processing, and detection phases of microemboli into a graphical user interface. The detection algorithm consists of a rule-based criterion with a user-defined threshold sliding in-time axis that estimates the duration of the embolic event. Subclavian Doppler audio recordings obtained from a high altitude diving expedition were analyzed using digital filtering and non-linear operator combinations of the software. The data set includes 43 embolic events in 9 recordings from 4 different subjects. RESULTS: It was determined that embolic signals are best differentiated from the background signal at the 4500-8000-Hz frequency band. By using the non-linear "Teager Energy Operator", embolic signals were amplified against their background and a high level of sensitivity and specificity was obtained (83.7% and 97.3%, respectively). The duration of the detected emboli was estimated as 12.17 +/- 4.36 ms (mean +/- SD). DISCUSSION: The optimal frequency band for the detection of subclavian emboli is significantly higher than previous findings for the transcranial site. The duration output of the software can be used to estimate the size and the composition of emboli. Successful integration of the software into an ambulatory detection system may provide important site-specific bubble size distribution data for decompression modeling.

Bayesian EEG dipole source localization using SA-RJMCMC on realistic head model.

In this study, electroencephalography (EEG) inverse problem is formulated using Bayesian inference. The posterior probability distribution of current sources is sampled by Markov Chain Monte Carlo (MCMC) methods. Sampling algorithm is designed by combining Reversible Jump (RJ) which permits trans-dimensional iterations and Simulated Annealing (SA), a heuristic to escape from local optima. Two different approaches to EEG inverse problem, Equivalent Current Dipole (ECD) and Distributed Linear Imaging (DLI) are combined in terms of probability. EEG inverse problem is solved with this probabilistic approach using simulated data on a realistic head model. Localization errors are computed. Comparing to Multiple Signal Classification algorithm (MUSIC) and Low-Resolution Electromagnetic Tomography (LORETA), using MCMC methods with a Bayesian approach is useful for solving the EEG inverse problem.