Automatic classification of sleep stages using EEG signals and convolutional neural networks.

Sleep stages classification is one of the new topics in studying human life quality because it plays a crucial role in getting a healthy lifestyle. Abnormal changes or absence of normal sleep may lead to different diseases such as heart-related diseases, diabetes, and obesity. In general, sleep staging analysis can be performed using electroencephalography (EEG) signals. This study proposes a convolutional neural network (CNN) based methodology for sleep stage classification using EEG signals taken by six channels and transformed into time-frequency analysis images. The proposed methodology consists of three major steps: (i) segment the EEG signal into epochs with 30 seconds in length, (ii) convert epochs into 2D representation using time-frequency analysis, and (iii) feed the 2D time-frequency analysis to the 2D CNN. The results showed that the proposed methodology is robust and achieved a very high accuracy of 99.39% for channel C4-A1. All other channels have accuracy values above 98.5%, which indicates that any channel can be used for sleep stage classification with high accuracy. The proposed methodology outperformed the methods in the literature in terms of overall accuracy or single channel accuracy. It is expected to provide a great benefit for physicians, especially neurologists; by providing them with a new powerful tool to support the clinical diagnosis of sleep-related diseases.

CT-based generation of synthetic-pseudo MR images with different weightings for human knee.

Synthetic MR images are generated for their high soft-tissue contrast avoiding the discomfort by the long acquisition time and placing claustrophobic patients in the MR scanner's confined space. The aim of this study is to generate synthetic pseudo-MR images from a real CT image for the knee region in vivo. 19 healthy subjects were scanned for model training, while 13 other healthy subjects were imaged for testing. The approach used in this work is novel such that the registration was performed between the MR and CT images, and the femur bone, patella, and the surrounding soft tissue were segmented on the CT image. The tissue type was mapped to its corresponding mean and standard deviation values of the CT# of a window moving on each pixel in the reconstructed CT images, which enabled the remapping of the tissue to its MRI intrinsic parameters: T1, T2, and proton density (ρ). To generate the synthetic MR image of a knee slice, a classic spin-echo sequence was simulated using proper intrinsic and contrast parameters. Results showed that the synthetic MR images were comparable to the real images acquired with the same TE and TR values, and the average slope between them (for all knee segments) was 0.98, while the average percentage root mean square difference (PRD) was 25.7%. In conclusion, this study has shown the feasibility and validity of accurately generating synthetic MR images of the knee region in vivo with different weightings from a single real CT image.

Generation of Synthetic-Pseudo MR Images from Real CT Images.

This study aimed to generate synthetic MR images from real CT images. CT# mean and standard deviation of a moving window across every pixel in the reconstructed CT images were mapped to their corresponding tissue-mimicking types. Identification of the tissue enabled remapping it to its corresponding intrinsic parameters: T1, T2, and proton density (ρ). Lastly, synthetic weighted MR images of a selected slice were generated by simulating a spin-echo sequence using the intrinsic parameters and proper contrast parameters (TE and TR). Experiments were performed on a 3D multimodality abdominal phantom and on human knees at different TE and TR parameters to confirm the clinical effectiveness of the approach. Results demonstrated the validity of the approach of generating synthetic MR images at different weightings using only CT images and the three predefined mapping functions. The slope of the fitting line and percentage root-mean-square difference (PRD) between real and synthetic image vector representations were (0.73, 10%), (0.9, 18%), and (0.2, 8.7%) for T1-, T2-, and ρ-weighted images of the phantom, respectively. The slope and PRD for human knee images, on average, were 0.89% and 18.8%, respectively. The generated MR images provide valuable guidance for physicians with regard to deciding whether acquiring real MR images is crucial.

ß-hydroxy-ß-methylbutyrate did not enhance high intensity resistance training-induced improvements in myofiber dimensions and myogenic capacity in aged female rats.

Older women exhibit blunted skeletal muscle hypertrophy following resistance training (RT) compared to other age and gender cohorts that is partially due to an impaired regenerative capacity. In the present study, we examined whether ß-hydroxy-ß-methylbutyrate (HMB) provision to aged female rodents would enhance regenerative mechanisms and facilitate RT-induced myofiber growth. Nineteen-month old female Sprague-Dawley rats were randomly divided into three groups: HMB (0.48 g/kg/d; n = 6), non-HMB (n = 6), and control (n = 4). HMB and non-HMB groups underwent RT every third day for 10 weeks using a ladder climbing apparatus. Whole body strength, grip strength, and body composition was evaluated before and after RT. The gastrocnemius and soleus muscles were analyzed using magnetic resonance diffusion tensor imaging, RT-PCR, and immunohistochemistry to determine myofiber dimensions, transcript expression, and satellite cells/myonuclei, respectively. ANOVAs were used with significance set at p < 0.05. There were significant time effects (pre vs. post) for whole body strength (+262%), grip strength (+17%), lean mass (+20%), and fat mass (-19%). Both RT groups exhibited significant increases in the mean myofiber cross-sectional area (CSA) in the gastrocnemius and soleus (+8-22%) compared to control. Moreover, both groups demonstrated significant increases in the numbers of satellite cells (+100-108%) and myonuclei (+32%) in the soleus but not the gastrocnemius. A significant IGF-I mRNA elevation was only observed in soleus of the HMB group (+33%) whereas MGF and myogenin increased significantly in both groups (+32-40%). Our findings suggest that HMB did not further enhance intense RT-mediated myogenic mechanisms and myofiber CSA in aged female rats.

A volume birdcage coil with an adjustable sliding tuner ring for neuroimaging in high field vertical magnets: ex and in vivo applications at 21.1T.

A tunable 900 MHz transmit/receive volume coil was constructed for ¹H MR imaging of biological samples in a 21.1 T vertical bore magnet. To accommodate a diverse range of specimen and RF loads at such a high frequency, a sliding-ring adaptation of a low-pass birdcage was implemented through simultaneous alteration of distributed capacitance. To make efficient use of the constrained space inside the vertical bore, a modular probe design was implemented with a bottom-adjustable tuning and matching apparatus. The sliding ring coil displays good homogeneity and sufficient tuning range for different samples of various dimensions representing large span of RF loads. High resolution in vivo and ex vivo images of large rats (up to 350 g), mice and human postmortem tissues were obtained to demonstrate coil functionality and to provide examples of potential applications at 21.1 T.

Beta-hydroxy-beta-methyl-butyrate blunts negative age-related changes in body composition, functionality and myofiber dimensions in rats.

PURPOSE: To determine the effects of 16 wk. of beta-hydroxy-beta-methylbutyrate (HMB) administration on age-related changes in functionality and diffusion tensor imaging (DTI) determined myofiber dimensions. METHODS: Twelve young (44 wk.), 6 middle-aged (60 wk.), 10 old (86 wk.), and 5 very old (102 wk.) male Fisher-344 rat's body composition and grip strength were assessed at baseline. Following, 6 young, 6 middle-aged, 5 old and 5 very old rats were sacrificed for baseline myofiber dimensions and gene transcript factor expression in the soleus (SOL) and gastrocnemius (GAS). The remaining 6 young and 5 old rats were given HMB for 16 wk. and then sacrificed. RESULTS: Fat mass increased in the middle-aged control condition (+49%) but not the middle-aged HMB condition. In addition, fat mass declined (-56%) in the old HMB condition but not the old control condition. Normalized strength declined and maintained respectively in the control and HMB conditions from 44 to 60 wk. and increased (+23%) (p < 0.05) from 86 to 102 wk. in only the HMB condition. Declines occurred in myofiber size in all muscles from 44 to 102 wk. in the control condition(-10 to -15%), but not HMB condition. Atrogin-1 mRNA expression in the SOL and GAS muscles was greater in the 102-wk control condition than all other conditions: SOL (+45%) and GAS (+100%). This elevation was blunted by HMB in the 102 wk. old SOL. There was a condition effect in the SOL for myogenin, which significantly increased (+40%) only in the 102-wk. HMB group relative to the 44-wk. group. CONCLUSIONS: HMB may blunt age-related losses of strength and myofiber dimensions, possibly through attenuating the rise in protein breakdown.

A retunable surface coil for high field 31P and 1H magnetic resonance evaluations of the living mouse leg.

This study presents a retunable surface coil that can be adjusted to at least two Larmor frequencies sequentially without the need to remove the coil from the magnet and while avoiding interference between channels. A prototype (1)H/(31)P surface coil for the analysis of the in vivo mouse leg under electrical stimulation was designed for operation at 11.75 T. The coil has a high-quality factor of over 100 for both operational frequencies. To demonstrate the capabilities of this simple design, in vivo experiments were conducted to acquire high-resolution (1)H images and (31)P spectra of the C57BL/6 mouse leg, both with high temporal resolution. Proton diffusion tensor imaging was also performed to evaluate rodent skeletal muscle architecture. This design makes the acquisition of physiological data about both muscle structure and energetics (PCr, ATP and Pi) possible in a single experimental session.