Estimation of cerebral blood flow velocity during breath-hold challenge using artificial neural networks.

The effect of untreated Obstructive Sleep Apnoea (OSA) on cerebral haemodynamics and CA impairment is an active field of research interest. A breath-hold challenge is usually used in clinical and research settings to simulate cardiovascular and cerebrovascular changes that mimic OSA events. This work utilises temporal arterial oxygen saturation (SpO2) and photoplethysmography (PPG) signals to estimate the temporal cerebral blood flow velocity (CBFv) waveform. Measurements of CBFv, SpO2, and PPG, were acquired concurrently from volunteers performing two different protocols of breath-hold challenge in the supine position. Past values of the SpO2 and PPG signals were used to estimate the current values of CBFv using different permutations and topologies of supervised learning with shallow artificial neural networks (ANNs). The measurements from one protocol were used to train the ANNs and find the optimum topologies, which in turn were tested using the other protocol. Data collected from 10 normotensive, healthy subjects (four females, age 28.5 ±â€¯6.1 years, Body Mass Index (BMI) 24.0 ±â€¯4.7 kg/m2) were used in this study. The results show that different subjects have different optimum topologies for ANNs, thus indicating the effects of inter-subject variability on ANNs. Successfully reconstructed blind waveforms for the same subject group in the second protocol showed a reasonable accuracy of 60-80% estimation compared to the measured waveforms. HYPOTHESIS: Temporal waveforms for SpO2 and PPG contain adequate information to estimate the temporal CBFv waveform using ANNs. METHODOLOGY: Concurrent measurements of SpO2 and PPG using pulse oximetry from the forehead and CBFv from the middle cerebral artery (MCA) using transcranial Doppler (TCD) were recorded from healthy, normotensive subjects performing a breath-hold challenge. The breath-hold challenge mimicked the cerebrovascular response to apnoea, and was recorded by measuring CBFv in MCA. Two protocols were used, each consisting of five breath-holding manoeuvres and differing in terms of the time between the five successive breath-holds. Using data from one protocol, several permutations of the temporal values of SpO2 and PPG signals were used as inputs to different ANN topologies, in order to train and find the optimum model. The optimum model was evaluated using the data from the other protocol as a blind dataset. RESULTS: Using the first protocol for training, optimum ANN configurations were found to be different for each subject, and accuracy of 75-87% was achieved. When these optimum ANN models were tested using the second protocol as a blind dataset, the accuracy achieved was around 60-80%. CONCLUSIONS: A novel approach employing temporal records of SpO2 and PPG can be used to estimate the CBFv waveform using ANNs with acceptable accuracy. Increases in the size and diversity of the population dataset and the use of features extracted from SpO2 and PPG signals are needed for generalisation of the method and potential future clinical applications.

Quantifying Long QT Syndrome in Obese Sleep Apnea Patients Undergoing Roux-en-Y Gastric Bypass Surgery.

Obstructive Sleep Apnea/Hypopnea Syndrome (OSAHS) is sleep-disordered breathing distinguished by repetitive cessation or reduction of airflow due to the collapse or narrowing of the upper airway during sleep with continued respiratory effort. A high level of incidence of OSAHS is correlated with obesity. Both severely obese patients and OSAHS patients manifest Long QT Syndrome (LQTS). It is reported that most obese patients undergoing weight reduction surgery positively reverse symptoms of LQST. Also, severely obese OSAHS undergoing the same surgery report alleviation of OSAHS symptoms. In this study, we presented preliminary results of the changes in QT and QTc intervals for obese OSAHS patients undergoing Roux-en-Y Gastric Bypass (RYGB) surgery and had their weight reduced, and were treated from OSAHS post-RYGB surgery. We developed an algorithm to detect the different waveforms in the ECG signal and calculated QT and QTc intervals. Results comparing the changes in the QT and QTc pre- and post-RYGB surgery for four apneic subjects (Aged 37.0 ± 8.9 years, Pre-RYGB BMI 51.7 ± 10.1 kg/m2, Post-RYGB BMI 35.6 ± 7.9 kg/m2) were contrasted with a control group of 3 non-apneic subjects (Aged 32.7 ± 7.0 years, Pre-RYGB BMI 50.8 ± 11.8 kg/m2, Post-RYGB BMI 31.6 ± 2.9 kg/m2) who underwent the same surgery. The results suggest that although the RYGB surgery is successful in weight loss and OSAHS symptoms reduction, apneic patients may continue to have non-reversible LQTS despite long-term weight reduction.

Objective detection of chronic stress using physiological parameters.

The aim of this study was to design a system to diagnose chronic stress, based on blunted reactivity of the autonomic nervous system (ANS) to cognitive load (CL). The system concurrently measures CL-induced variations in pupil diameter (PD), heart rate (HR), pulse wave amplitude (PWA), galvanic skin response (GSR), and breathing rate (BR). Measurements were recorded from 58 volunteers whose stress level was identified using the State-Trait Anxiety Inventory. Number-multiplication questions were used as CLs. HR, PWA, GSR, and PD were significantly (p < 0.05) changed during CL. CL-induced changes in PWA (16.87 ± 21.39), GSR (- 13.71 ± 7.86), and PD (11.56 ± 9.85) for non-stressed subjects (n = 36) were significantly different (p < 0.05) from those in PWA (2.92 ± 12.89), GSR (- 6.87 ± 9.54), and PD (4.51 ± 10.94) for stressed subjects (n = 22). ROC analysis for PWA, GSR, and PD illustrated their usefulness to identify stressed subjects. By inputting all features to different classification algorithms, up to 91.7% of sensitivity and 89.7% of accuracy to identify stressed subjects were achieved using 10-fold cross-validation. This study was the first to document blunted CL-induced changes in PWA, GSR, and PD in stressed subjects, compared to those in non-stressed subjects. Preliminary results demonstrated the ability of our system to objectively detect chronic stress with good accuracy, suggesting the potential for monitoring stress to prevent dangerous stress-related diseases. Graphical abstract Chronic stress degrads the autonomic nervous system reaction to cognitive loads. Measurement of reduced changes in physiological signals during asking math questions was useful to identify people with high STAI score (stressed subjects).

Improvement of medical content in the curriculum of biomedical engineering based on assessment of students outcomes.

BACKGROUND: Improvement of medical content in Biomedical Engineering curricula based on a qualitative assessment process or on a comparison with another high-standard program has been approached by a number of studies. However, the quantitative assessment tools have not been emphasized. The quantitative assessment tools can be more accurate and robust in cases of challenging multidisciplinary fields like that of Biomedical Engineering which includes biomedicine elements mixed with technology aspects. The major limitations of the previous research are the high dependence on surveys or pure qualitative approaches as well as the absence of strong focus on medical outcomes without implicit confusion with the technical ones. The proposed work presents the development and evaluation of an accurate/robust quantitative approach to the improvement of the medical content in the challenging multidisciplinary BME curriculum. METHODS: The work presents quantitative assessment tools and subsequent improvement of curriculum medical content applied, as example for explanation, to the ABET (Accreditation Board for Engineering and Technology, USA) accredited biomedical engineering BME department at Jordan University of Science and Technology. The quantitative results of assessment of curriculum/course, capstone, exit exam, course assessment by student (CAS) as well as of surveys filled by alumni, seniors, employers and training supervisors were, first, mapped to the expected students' outcomes related to the medical field (SOsM). The collected data were then analyzed and discussed to find curriculum weakness points by tracking shortcomings in every outcome degree of achievement. Finally, actions were taken to fill in the gaps of the curriculum. Actions were also mapped to the students' medical outcomes (SOsM). RESULTS: Weighted averages of obtained quantitative values, mapped to SOsM, indicated accurately the achievement levels of all outcomes as well as the necessary improvements to be performed in curriculum. Mapping the improvements to SOsM also helps in the assessment of the following cycle. CONCLUSION: The suggested assessment tools can be generalized and extended to any other BME department. Robust improvement of medical content in BME curriculum can subsequently be achieved.

Classification of Normal, Ictal and Inter-ictal EEG via Direct Quadrature and Random Forest Tree.

This paper presents an accurate nonlinear classification method that can help physicians diagnose seizure in electroencephalographic (EEG) signal characterized by a disturbance in temporal and spectral content. This is accomplished by applying four steps. First, different EEG signals containing healthy, ictal and seizure-free (inter-ictal) activities are decomposed by empirical mode decomposition method. The instantaneous amplitudes and frequencies of resulted bands (intrinsic mode functions, IMF) are then tracked by the direct quadrature method (DQ). In contrast to other approaches, DQ cancels the effect of amplitude modulation on frequency calculation. The dissociation between instantaneous amplitude and frequency information is therefore fully achieved to avoid features confusion. Afterwards, the Shannon entropy values of both sets of instantaneous values (amplitudes and frequencies)-related to every IMF-are calculated. Finally, the obtained entropy values are classified by random forest tree. The proposed procedure yields 100% accuracy for (healthy)/(ictal) and 98.3-99.7% for (healthy)/(ictal)/(interictal) classification problems. The suggested method is hence robust, accurate, fast, user-friendly, data driven with open access interpretability.

Algorithm for automatic angles measurement and screening for Developmental Dysplasia of the Hip (DDH).

Developmental Dysplasia of the Hip (DDH) is a medical term represent the hip joint instability that appear mainly in infants. The examination for this condition can be done by ultrasound for children under 6 months old and by X-ray for children over 6 months old. Physician's assessment is based on certain angles derived from those images, namely the Acetabular Angle, and the Center Edge Angle. In this paper, we are presenting a novel, fully automatic algorithm for measuring the diagnostic angles of DDH from the X-ray images. Our algorithm consists of Automatic segmentation and extraction of anatomical landmarks from X-ray images. Both of Acetabular angle and Center edge angle are automatically calculated. The analysis included X-ray images for 16 children recruited for the purposed of this study. The automatically acquired angles accuracy for Acetabular Angle was around 85%, and an absolute deviation of 3.4°±3.3° compared to the physician's manually calculated angle. The results of this method are very promising for the future development of an automatic method for screening X-ray images DDH that complement and aid the physicians' manual methods.

Internal jugular vein valve morphology in the patients with chronic cerebrospinal venous insufficiency (CCSVI); angiographic findings and schematic demonstrations.

Chronic cerebrospinal venous insufficiency (CCSVI) is a syndrome recently described in multiple sclerosis patients. It is characterized by abnormal venous hemodynamics resulting from numerous obstacles in the main veins draining the central nervous system, usually: the internal jugular veins and the azygous vein. Internal jugular vein is the most commonly vein affected. Most of the abnormalities in this vein are located at the level of jugular valve. The aim of this review is to give venographic and schematic descriptions of the most common valvular and perivalvular anomalies found in the lower part of internal jugular vein.

Monitoring sunitinib-induced vascular effects to optimize radiotherapy combined with soy isoflavones in murine xenograft tumor.

Using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to monitor vascular changes induced by sunitinib within a murine xenograft kidney tumor, we previously determined a dose that caused only partial destruction of blood vessels leading to "normalization" of tumor vasculature and improved blood flow. In the current study, kidney tumors were treated with this dose of sunitinib to modify the tumor microenvironment and enhance the effect of kidney tumor irradiation. The addition of soy isoflavones to this combined antiangiogenic and radiotherapy approach was investigated based on our studies demonstrating that soy isoflavones can potentiate the radiation effect on the tumors and act as antioxidants to protect normal tissues from treatment-induced toxicity. DCE-MRI was used to monitor vascular changes induced by sunitinib and schedule radiation when the uptake and washout of the contrast agent indicated regularization of blood flow. The combination of sunitinib with tumor irradiation and soy isoflavones significantly inhibited the growth and invasion of established kidney tumors and caused marked aberrations in the morphology of residual tumor cells. DCE-MRI studies demonstrated that the three modalities, sunitinib, radiation, and soy isoflavones, also exerted antiangiogenic effects resulting in increased uptake and clearance of the contrast agent. Interestingly, DCE-MRI and histologic observations of the normal contralateral kidneys suggest that soy could protect the vasculature of normal tissue from the adverse effects of sunitinib. An antiangiogenic approach that only partially destroys inefficient vessels could potentially increase the efficacy and delivery of cytotoxic therapies and radiotherapy for unresectable primary renal cell carcinoma tumors and metastatic disease.

Dynamic contrast-enhanced magnetic resonance imaging of sunitinib-induced vascular changes to schedule chemotherapy in renal cell carcinoma xenograft tumors.

In an attempt to develop better therapeutic approaches for metastatic renal cell carcinoma (RCC), the combination of the antiangiogenic drug sunitinib with gemcitabine was studied. Using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), we have previously determined that a sunitinib dosage of 20 mg/kg per day increased kidney tumor perfusion and decreased vascular permeability in a preclinical murine RCC model. This sunitinib dosage causing regularization of tumor vessels was selected to improve delivery of gemcitabine to the tumor. DCE-MRI was used to monitor regularization of vasculature with sunitinib in kidney tumors to schedule gemcitabine. We established an effective and nontoxic schedule of sunitinib combined with gemcitabine consisting of pretreatment with sunitinib for 3 days followed by four treatments of gemcitabine at 20 mg/kg given 3 days apart while continuing daily sunitinib treatment. This treatment caused significant tumor growth inhibition resulting in small residual tumor nodules exhibiting giant tumor cells with degenerative changes, which were observed both in kidney tumors and in spontaneous lung metastases, suggesting a systemic antitumor response. The combined therapy caused a significant increase in mouse survival. DCE-MRI monitoring of vascular changes induced by sunitinib, gemcitabine, and both combined showed increased tumor perfusion and decreased vascular permeability in kidney tumors. These findings, confirmed histologically by thinning of tumor blood vessels, suggest that both sunitinib and gemcitabine exert antiangiogenic effects in addition to cytotoxic antitumor activity. These studies show that DCE-MRI can be used to select the dose and schedule of antiangiogenic drugs to schedule chemotherapy and improve its efficacy.

Dynamic contrast-enhanced magnetic resonance imaging of vascular changes induced by sunitinib in papillary renal cell carcinoma xenograft tumors.

To investigate further the antiangiogenic potential of sunitinib for renal cell carcinoma (RCC) treatment, its effects on tumor vasculature were monitored by dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using an orthotopic KCI-18 model of human RCC xenografts in nude mice. Tumor-bearing mice were treated with various doses of sunitinib, and vascular changes were assessed by DCE-MRI and histologic studies. Sunitinib induced dose-dependent vascular changes, which were observed both in kidney tumors and in normal kidneys by DCE-MRI. A dosage of 10 mg/kg per day caused mild changes in Gd uptake and clearance kinetics in kidney tumors. A dosage of 40 mg/kg per day induced increased vascular tumor permeability with Gd retention, probably resulting from the destruction of tumor vasculature, and also caused vascular alterations of normal vessels. However, sunitinib at 20 mg/kg per day caused increased tumor perfusion and decreased vascular permeability associated with thinning and regularization of tumor vessels while mildly affecting normal vessels as confirmed by histologic diagnosis. Alterations in tumor vasculature resulted in a significant inhibition of KCI-18 RCC tumor growth at sunitinib dosages of 20 and 40 mg/kg per day. Sunitinib also exerted a direct cytotoxic effect in KCI-18 cells in vitro. KCI-18 cells and tumors expressed vascular endothelial growth factor receptor 2 and platelet-derived growth factor receptor beta molecular targets of sunitinib that were modulated by the drug treatment. These data suggest that a sunitinib dosage of 20 mg/kg per day, which inhibits RCC tumor growth and regularizes tumor vessels with milder effects on normal vessels, could be used to improve blood flow for combination with chemotherapy. These studies emphasize the clinical potential of DCE-MRI in selecting the dose and schedule of antiangiogenic compounds.

New algorithm for quantifying vascular changes in dynamic contrast-enhanced MRI independent of absolute T1 values.

In this work, we present a new method for predicting changes in tumor vascularity using only one flip angle in dynamic contrast-enhanced (DCE) imaging. The usual DCE approach finds the tissue initial T1 value T1(0) prior to injection of a contrast agent. We propose finding changes in the tissue contrast agent uptake characteristics pre- and postdrug treatment by fixing T1(0). Using both simulations and imaging pre- and postadministration of caffeine, we find that the relative change (NR50) in the median of the cumulative distribution (R50) is almost independent of T1(0). Fixing T1(0) leads to a concentration curve c(t) more robust to the presence of noise than calculating T1(0). Consequently, the NR50 for the tumor remains roughly the same as the ideal NR50 when T1(0) is exactly known. Further, variations in eating habits are shown to create significant changes in the R50 response for both liver and muscle. In conclusion, analyzing data with fixed T1(0) leads to a more stable measure of changes in NR50 and does not require knowledge of T1(0). Both caffeine and eating introduce major changes in blood flow that can significantly modify the NR50 and lead to incorrect conclusions regarding drug treatment.