Physics-informed neural network for fast prediction of temperature distributions in cancerous breasts as a potential efficient portable AI-based diagnostic tool.

This work presents the development of a novel Physics-Informed Neural Network (PINN) method for fast forward simulation of heat transfer through cancerous breast models. The proposed PINN method combines deep learning and physical principles to predict the temperature distributions in breast tissues and identify potential abnormal regions indicating the presence of tumors. The PINN model is normally trained by physics in terms of the residuals of the heat transfer equation, as well as boundary conditions with and without datasets of surface thermal imaging data concerning cancerous breast tissues, which can be used for future inverse thermal modeling to calculate tumor sizes and locations. The model is validated by comparing its predictions with those obtained by traditional Finite Element Analysis (FEA) for various cases. The comparison validates the PINN model as an accurate and fast method for thermal modeling and breast cancer diagnostic tool as the PINN simulation is found to be around 12 times faster than its FEM counterpart. The utilization of deep learning and physical principles in a diagnostic tool provides a non-invasive and safer alternative for breast self-examination compared to traditional methods such as mammography. These findings hold promise for the ongoing development of a new portable Artificial Intelligence (AI) tool for the early detection of breast cancer in breast self-examination as promoted by WHO, which is crucial for reducing mortality rates of breast cancer in the world.

An Integrated Intelligent System for Breast Cancer Detection at Early Stages Using IR Images and Machine Learning Methods with Explainability.

Breast cancer is the second most common cause of death among women. An early diagnosis is vital for reducing the fatality rate in the fight against breast cancer. Thermography could be suggested as a safe, non-invasive, non-contact supplementary method to diagnose breast cancer and can be the most promising method for breast self-examination as envisioned by the World Health Organization (WHO). Moreover, thermography could be combined with artificial intelligence and automated diagnostic methods towards a diagnosis with a negligible number of false positive or false negative results. In the current study, a novel intelligent integrated diagnosis system is proposed using IR thermal images with Convolutional Neural Networks and Bayesian Networks to achieve good diagnostic accuracy from a relatively small dataset of images and data. We demonstrate the juxtaposition of transfer learning models such as ResNet50 with the proposed combination of BNs with artificial neural network methods such as CNNs which provides a state-of-the-art expert system with explainability. The novelties of our methodology include: (i) the construction of a diagnostic tool with high accuracy from a small number of images for training; (ii) the features extracted from the images are found to be the appropriate ones leading to very good diagnosis; (iii) our expert model exhibits interpretability, i.e., one physician can understand which factors/features play critical roles for the diagnosis. The results of the study showed an accuracy that varies for the most successful models amongst four implemented approaches from approximately 91% to 93%, with a precision value of 91% to 95%, sensitivity from 91% to 92 %, and with specificity from 91% to 97%. In conclusion, we have achieved accurate diagnosis with understandability with the novel integrated approach.

Extreme Electron Acceleration with Fixed Radiation Energy.

We examine the extreme situation of radiation from an electron that is asymptotically accelerated to the speed of light, resulting in finite emission energy. The analytic solution explicitly demonstrates the difference between radiation power loss and kinetic power loss (null).

Bound on Efficiency of Heat Engine from Uncertainty Relation Viewpoint.

Quantum cycles in established heat engines can be modeled with various quantum systems as working substances. For example, a heat engine can be modeled with an infinite potential well as the working substance to determine the efficiency and work done. However, in this method, the relationship between the quantum observables and the physically measurable parameters-i.e., the efficiency and work done-is not well understood from the quantum mechanics approach. A detailed analysis is needed to link the thermodynamic variables (on which the efficiency and work done depends) with the uncertainty principle for better understanding. Here, we present the connection of the sum uncertainty relation of position and momentum operators with thermodynamic variables in the quantum heat engine model. We are able to determine the upper and lower bounds on the efficiency of the heat engine through the uncertainty relation.

Binary Black Hole Information Loss Paradox and Future Prospects.

Various techniques to tackle the black hole information paradox have been proposed. A new way out to tackle the paradox is via the use of a pseudo-density operator. This approach has successfully dealt with the problem with a two-qubit entangle system for a single black hole. In this paper, we present the interaction with a binary black hole system by using an arrangement of the three-qubit system of Greenberger-Horne-Zeilinger (GHZ) state. We show that our results are in excellent agreement with the theoretical value. We have also studied the interaction between the two black holes by considering the correlation between the qubits in the binary black hole system. The results depict a complete agreement with the proposed model. In addition to the verification, we also propose how modern detection of gravitational waves can be used on our optical setup as an input source, thus bridging the gap with the gravitational wave's observational resources in terms of studying black hole properties with respect to quantum information and entanglement.

Data on advanced glycation end-products concentrations and haemodynamic parameters following caffeine and nicotine consumption in nursing students.

This work presents data from a non-invasive interventional trial investigating the early effects of caffeine and nicotine on both the concentrations of advanced glycation end-products (AGEs) and haemodynamic parameters in 178 healthy nursing students aged between 18 and 40. These students were allocated into four groups (A, B, C and D) and the concentrations of AGEs as well as haemodynamic parameters were measured non-invasively using the AgeReader and the Finometer devices, respectively. The haemodynamic parameters that were measured included systolic blood pressure, diastolic blood pressure, mean arterial pressure, heart rate, inter-beat interval, stroke volume, cardiac output, ventricular ejection time, total peripheral resistance, ascending aorta impedance and total arterial compliance. According to our protocol, each beverage contained 100 mg of caffeine each cigarette contained 1.5 mg of nicotine. The present data reveal the combined effect of smoke and caffeine consumption to several hemodynamic parameters that may be related to the onset of elevated blood pressure during smoking and following caffeine consumption.

Clustering analysis of countries using the COVID-19 cases dataset.

There is a worldwide effort of the research community to explore the medical, economic and sociologic impact of the COVID-19 pandemic. Many different disciplines try to find solutions and drive strategies to a great variety of different very crucial problems. The present study presents a novel analysis which results to clustering countries with respect to active cases, active cases per population and active cases per population and per area based on Johns Hopkins epidemiological data. The presented cluster results could be useful to a variety of different policy makers, such as physicians and managers of the health sector, economy/finance experts, politicians and even to sociologists. In addition, our work suggests a new specially designed clustering algorithm adapted to the request for comparison of the various COVID time-series of different countries.

Oligomenorrhoea in adolescents with type 1 diabetes mellitus: relationship to glycaemic control.

OBJECTIVE: To investigate oligomenorrhoea in adolescents with type 1 diabetes and the possible relationship with glycaemic control. STUDY DESIGN: The study group consisted of 81 female adolescents with type 1 diabetes whose mean age was 15.0 years (range 12-18). The control group consisted of 205 healthy adolescents with a mean age of 15.5 years (range 12-18). Data on menstruation were collected by two parallel self-administered questionnaires. Oligomenorrhoea was defined as having a menstrual cycle longer than 36 days throughout the past year (5-6/year). The metabolic control of diabetes was evaluated by calculating the mean value of HbA1c during the past year. RESULTS: Age of menarche was greater for adolescents with type 1 diabetes (12.2 ± 1.4 vs. 11.7 ± 1.2, p < 0.000) compared to healthy age-matched controls. Logistic regression analysis with oligomenorrhoea as the dependent binary variable revealed an odds ratio equal to 7.8 (95% CI 3.411-17.853) for adolescents with type 1 diabetes (p < 0.000). Finally, a second logistic regression analysis, concerning only adolescents with type 1 diabetes and with the same binary variable, estimated an odds ratio of 4.8 (95% CI 1.784-13.057, p < 0.002) for HbA1c, and an odds ratio of 5.3 (95% CI 1.821-15.130, p < 0.002) for the frequency of hypoglycaemia. CONCLUSION: In adolescents with type 1 diabetes, menarche occurs later and oligomenorrhoea is more frequent. The relative risk of having oligomenorrhoea is greater when there is an increased value of HbA1c or when hypoglycaemia is more frequent.

Test-retest reliability of p13n23 and n34p44 components of vestibular evoked myogenic potentials in a large healthy population.

OBJECTIVE: The aim of this study is to evaluate the reliability of the VEMP characteristics recorded in a large number of healthy subjects. METHODS: VEMP response was obtained on 75 healthy volunteers. Thirty-nine (39) of them were males and 36 were females. Their age varied between 25 and 63 years (mean value 43). Recording was achieved using monaural acoustic stimulation and ipsilateral muscle contraction. Latencies of p13, n23, n34, p44 peaks, p13n23 and n34p44 amplitudes and the interaural amplitude differences (IAD) were assessed. RESULTS: The stability of latencies, amplitudes of the first p12-n23 and second n34-p44 waveforms was verified. The second complex was present in 76%. No factor indicates statistically significant side difference for both runs. IAD variable was not statistically different from zero in all cases. Results show very good reliability for amplitudes, good for some latencies, poor for some other latencies and IAD34-44 and very poor for IAD13-23. No strong and significant correlations were also found between IAD34-44 and IAD13-23 and between p13n23 and n34p44 amplitudes. CONCLUSION: It is the first time that optimal latencies and amplitudes for early and late components of VEMP are described in a large sample of healthy subjects. The p13, n23, n34 and p44 latencies and p13-n23, and n34-p44 amplitudes were reliable, verifying that the method is reproducible and feasible. The IAD13-23 has the disadvantage of low reliability.

Vestibular evoked myogenic potential eliciting in normal subjects: comparison of four different methods.

OBJECTIVE: Vestibular evoked myogenic potential (VEMP) recording is a new method for testing the otolith receptors and vestibulospinal pathways. The aim of this study was to evaluate the characteristics of VEMP using four different techniques to find reasons to prefer one type of recording over the others. MATERIAL AND METHODS: Twenty healthy persons, 10 males and 10 females with ages ranging from 20 to 57 years (mean age 41 years), were enrolled in this study. Eliciting of VEMPs by using monaural or binaural acoustic stimulation and unilateral or bilateral SCM contraction was evaluated; 105 dB NHL acoustic stimulation consisting of 145 dB rarefaction clicks was applied. Latencies of p13, n23, n34, p44 peaks; amplitudes p13-n23 and n34-p44; and interaural amplitude differences (IADs) were assessed. RESULTS: All four methods elicited constant and evident waveforms. The reliability coefficients of amplitudes were high for all four methods and for both waves. However, the higher scores of reliability appeared for the monaural-ipsilateral recording. The results indicated no statistically significant difference between the right and left sides for all four types of VEMP eliciting. No correlation was found between IAD13-23 and IAD34-44 for all four methods. Statistically significant differences were found only for n23 latency among the four methods. CONCLUSIONS: Although no evidence to reject or strongly favour a specific method was found, the monaural-ipsilateral recording was associated with some advantages.