The processing mechanism of the human brain for speech information is a significant source of inspiration for the study of speech enhancement technology. Attention and lateral inhibition are key mechanisms in auditory information processing that can selectively enhance specific information. Building on this, the study introduces a dual-branch U-Net that integrates lateral inhibition and feedback-driven attention mechanisms. Noisy speech signals input into the first branch of the U-Net led to the selective feedback of time-frequency units with high confidence. The generated activation layer gradients, in conjunction with the lateral inhibition mechanism, were utilized to calculate attention maps. These maps were then concatenated to the second branch of the U-Net, directing the network's focus and achieving selective enhancement of auditory speech signals. The evaluation of the speech enhancement effect was conducted by utilising five metrics, including perceptual evaluation of speech quality. This method was compared horizontally with five other methods: Wiener, SEGAN, PHASEN, Demucs and GRN. The experimental results demonstrated that the proposed method improved speech signal enhancement capabilities in various noise scenarios by 18% to 21% compared to the baseline network across multiple performance metrics. This improvement was particularly notable in low signal-to-noise ratio conditions, where the proposed method exhibited a significant performance advantage over other methods. The speech enhancement technique based on lateral inhibition and feedback-driven attention mechanisms holds significant potential in auditory speech enhancement, making it suitable for clinical practices related to artificial cochleae and hearing aids.
Humans ; Attention/physiology* ; Speech Perception/physiology* ; Neural Networks, Computer ; Speech ; Noise ; Feedback

Motor imagery (MI) is a mental process that can be recognized by electroencephalography (EEG) without actual movement. It has significant research value and application potential in the field of brain-computer interface (BCI) technology. To address the challenges posed by the non-stationary nature and low signal-to-noise ratio of MI-EEG signals, this study proposed a Riemannian spatial filtering and domain adaptation (RSFDA) method for improving the accuracy and efficiency of cross-session MI-BCI classification tasks. The approach addressed the issue of inconsistent data distribution between source and target domains through a multi-module collaborative framework, which enhanced the generalization capability of cross-session MI-EEG classification models. Comparative experiments were conducted on three public datasets to evaluate RSFDA against eight existing methods in terms of classification accuracy and computational efficiency. The experimental results demonstrated that RSFDA achieved an average classification accuracy of 79.37%, outperforming the state-of-the-art deep learning method Tensor-CSPNet (76.46%) by 2.91% ( P < 0.01). Furthermore, the proposed method showed significantly lower computational costs, requiring only approximately 3 minutes of average training time compared to Tensor-CSPNet's 25 minutes, representing a reduction of 22 minutes. These findings indicate that the RSFDA method demonstrates superior performance in cross-session MI-EEG classification tasks by effectively balancing accuracy and efficiency. However, its applicability in complex transfer learning scenarios remains to be further investigated.
Electroencephalography/methods* ; Brain-Computer Interfaces ; Humans ; Imagination/physiology* ; Signal Processing, Computer-Assisted ; Movement/physiology* ; Signal-To-Noise Ratio ; Deep Learning ; Algorithms

OBJECTIVE: To explore the therapeutic effects and underlying mechanisms of Dendrobium officinale (Tiepi Shihu) extract (DOE) on insomnia. METHODS: Forty-two male Sprague-Dawley rats were randomly divided into 6 groups (n=7 per group): normal control, model control, melatonin (MT, 40 mg/kg), and 3-dose DOE (0.25, 0.50, and 1.00 g/kg) groups. Rats were raised in a strong-light (10,000 LUX) and -noise (>80 db) environment (12 h/d) for 16 weeks to induce insomnia, and from week 10 to week 16, MT and DOE were correspondingly administered to rats. The behavior tests including sodium pentobarbital-induced sleep experiment, sucrose preference test, and autonomous activity test were used to evaluate changes in sleep and emotions of rats. The metabolic-related indicators such as blood pressure, blood viscosity, blood glucose, and uric acid in rats were measured. The pathological changes in the cornu ammonis 1 (CA1) region of rat brain were evaluated using hematoxylin and eosin staining and Nissl staining. Additionally, the sleep-related factors gamma-aminobutyric acid (GABA), glutamate (GA), 5-hydroxytryptamine (5-HT), and interleukin-6 (IL-6) were measured using enzyme linked immunosorbent assay. Finally, we screened potential sleep-improving receptors of DOE using polymerase chain reaction (PCR) array and validated the results with quantitative PCR and immunohistochemistry. RESULTS: DOE significantly improved rats' sleep and mood, increased the sodium pentobarbital-induced sleep time and sucrose preference index, and reduced autonomic activity times (P<0.05 or P<0.01). DOE also had a good effect on metabolic abnormalities, significantly reducing triglyceride, blood glucose, blood pressure, and blood viscosity indicators (P<0.05 or P<0.01). DOE significantly increased the GABA content in hippocampus and reduced the GA/GABA ratio and IL-6 level (P<0.05 or P<0.01). In addition, DOE improved the pathological changes such as the disorder of cell arrangement in the hippocampus and the decrease of Nissel bodies. Seven differential genes were screened by PCR array, and the GABA_A receptors (Gabra5, Gabra6, Gabrq) were selected for verification. The results showed that DOE could up-regulate their expressions (P<0.05 or P<0.01). CONCLUSION DOE demonstrated remarkable potential for improving insomnia, which may be through regulating GABA_A receptors expressions and GA/GABA ratio.
Animals ; Dendrobium/chemistry* ; Rats, Sprague-Dawley ; Male ; Sleep Initiation and Maintenance Disorders/blood* ; Plant Extracts/therapeutic use* ; Receptors, GABA-A/metabolism* ; Noise/adverse effects* ; Light/adverse effects* ; gamma-Aminobutyric Acid/metabolism* ; Sleep/drug effects* ; Rats ; Receptors, GABA/metabolism*

Objective:To investigate the clinical characteristics and treatment outcomes of patients with blast-induced hearing loss（BIHL）. Methods:The clinical features, laboratory parameters, audiometric profiles, and treatment efficacy of patients with blast induced hearing loss and those with idiopathic sudden hearing loss（ISHL） were analyzed using t-tests, Wilcoxon rank-sum tests, and chi-square tests, with a significance level set at P<0.05. Results:A total of 59 patients in the BIHL group and 117 patients in the ISHL group were included in this study. The mean age of the BIHL group was（39.07±14.49） years, comprising 45 males and 14 females. After the blast, 21 patients went to the hospital within the initial 14-day period, and an additional 38 patients seeking admission thereafter. In the BIHL group, 33 patients had unilateral hearing loss with PTA of （50.30±28.85） dB HL, while 26 had bilateral hearing loss with a PTA of（44.54±26.22） dB HL. In comparison, among the ISHL group, 112 patients had unilateral hearing loss with a PTA of（56.28±14.19） dB HL, and 5 had bilateral involvement with a PTA of（56.25±35.14） dB HL. The effective treatment rate within 14 days for the BIHL group was 31.8%, while for the ISHL group, the effective rate within 14 days was 77.0%. Conclusion:Blast-induced hearing loss is caused by exposure to high-intensity noise. The overall treatment effectiveness during hospitalization is lower compared to idiopathic sudden hearing loss, and the treatment window is shorter. Therefore, greater emphasis should be placed on prevention.
Humans ; Male ; Female ; Adult ; Middle Aged ; Young Adult ; Blast Injuries/therapy* ; Treatment Outcome ; Hearing Loss, Sudden/etiology* ; Adolescent ; Hearing Loss, Noise-Induced/diagnosis*

Objective:To compare the changes in distortion product otoacoustic emission （DPOAE） test results in clinical patients with negative middle ear pressure after equalizing the pressure in the external canal and the middle ear cavity. This study aims to analyze the effect of negative middle ear pressure on otoacoustic emissions and investigate the correlation between the degree of negative middle ear pressure and the changes in amplitude and signal-to-noise ratio of DPOAE. Methods:Twenty-seven clinical patients were included, with 34 ears exhibiting negative middle ear pressure. Acoustic conductance tests, pure tone hearing threshold tests, and DPOAE tests were conducted under ambient pressure and peak pressure after equalizing the middle ear pressure for all tested ears. The amplitude and signal-to-noise ratio of DPOAE before and after compensating for middle ear pressure were recorded and statistically analyzed. Results:At 1.0 k Hz, 1.5 k Hz, and 8.0 k Hz, the DPOAE amplitude under ambient pressure was significantly higher than that under negative pressure （P<0.05）. A significant difference in the DPOAE signal-to-noise ratio was observed at 1.0 k Hz and 8.0 k Hz （P<0.05）. The difference in both amplitude and signal-to-noise ratio between these two test conditions was more pronounced at 1.0 k Hz （P<0.01）. There was no correlation between the negative pressure value from the tympanogram and the change in amplitude, with a weak negative correlation trend observed only at 0.75 k Hz （r=-0.328, P=0.054）. However, a significant negative correlation was found between the negative pressure value from the tympanogram and the change in signal-to-noise ratio at 0.75 k Hz （r=-0.366, P<0.05）. Conclusion:Compensating for middle ear pressure significantly improves the amplitude and signal-to-noise ratio of DPOAE in cases of negative middle ear pressure, particularly in the medium-frequency range. The smaller the degree of negative pressure in the middle ear, the weaker the effect of equalizing middle ear pressure is, especially in the low-frequency range.
Humans ; Ear, Middle/physiopathology* ; Male ; Female ; Adult ; Otoacoustic Emissions, Spontaneous ; Young Adult ; Middle Aged ; Pressure ; Adolescent ; Aged ; Signal-To-Noise Ratio

Objective:This study aims to investigate the mechanism and potential effects of two exposures to 100 dB sound pressure level（SPL） broadband white noise, with a 14-days interval, on the myelin sheath of the cochlear auditory nerve in mice. The research provides experimental evidence for understanding the pathophysiological processes of noise-induced hearing loss and hidden hearing loss. Methods:Fifteen 6-week-old male C57BL/6J mice with normal hearing thresholds were randomly divided into three groups: a control group（no noise exposure）, a single noise exposure group, and a double noise exposure group. The single noise exposure group was exposed to 100 dB SPL white noise for 2 hours, and ABR thresholds were measured 1 day（P1） and 14 days（P14） after the exposure. The double noise exposure group was exposed to the same conditions of 100 dB SPL white noise for 2 hours, followed by a second identical exposure 14 days later. ABR thresholds were measured 1 day（P15） and 14 days（P28） after the second exposure. The cochleae of all three groups were then collected for immunofluorescence observation of the basilar membrane and transmission electron microscopy to observe changes in the structure of the auditory nerve myelin sheath. Results:In the single noise exposure group, ABR thresholds at all frequencies were significantly elevated compared to the control group at P1. There were no significant changes in ABR thresholds at any frequency at P14. In the double noise exposure group, ABR thresholds at all frequencies were significantly elevated compared to the control group at P15 and P28（P<0.001）. After the first noise exposure, immunofluorescence observation revealed no significant weakening of the auditory nerve myelin sheath signal; transmission electron microscopy showed no significant changes in myelin sheath morphology. However, after the second noise exposure, immunofluorescence observation revealed a weakening of the myelin sheath signal, and transmission electron microscopy showed thinning of the myelin sheath, disruption of the lamellar structure, and separation from the axon, indicating demyelination. Conclusion:Two exposures to 100 dB SPL broadband white noise can lead to damage to the auditory nerve myelin sheath in mice, whereas a single exposure does not cause significant changes.
Animals ; Male ; Myelin Sheath/pathology* ; Mice ; Cochlear Nerve/pathology* ; Mice, Inbred C57BL ; Noise/adverse effects* ; Hearing Loss, Noise-Induced/physiopathology* ; Cochlea ; Evoked Potentials, Auditory, Brain Stem

Objective:To investigate the impact of Waardenburg syndrome（WS） -associated Sox10 p.S100Rfs*9 mutation on inner ear function and its mechanism in noise-induced hearing impairment. Methods:A mice model carrying the Sox10 p.S100Rfs*9 mutation was established using CRISPR-Cas9 gene editing technology. Auditory phenotypes were assessed under baseline conditions and after noise exposure（96 dB SPL, 2 hours）. Auditory brainstem response（ABR） tests were performed to evaluate hearing function, combined with immunofluorescence staining of cochlear basilar membrane whole-mounts to observe hair cells and ribbon synapses. Transcriptome sequencing was conducted to analyze molecular mechanisms. Results:Sox10 p.S100Rfs*9 heterozygous mice exhibited normal hearing thresholds with characteristic ventral pigmentation abnormalities under baseline conditions. Following noise exposure, mutant mice showed significantly higher ABR thresholds at 24 000 Hz compared to wild-type controls（[60.00±6.12]vs[48.13±4.28]dB SPL, P<0.000 1）, and a significant reduction in ribbon synapses（CtBP2-positive puncta） in the basal turn（[55.0±2.3]vs[64.8±3.3]per inner hair cell, P=0.006 6）, while hair cell morphology and number remained intact. Transcriptome analysis revealed altered expression of genes involved in immune regulation, membrane structures, ion channels, and neuroactive ligand-receptor interactions. Conclusion:The Sox10 p.S100Rfs*9 mutation does not alter baseline hearing function but significantly increases inner ear susceptibility to noise damage, primarily manifested as enhanced ribbon synapse vulnerability, especially in high-frequency regions. This gene-environment interaction reveals that Sox10 haploinsufficiency may compromise noise tolerance by affecting synaptic stability and inner ear protective mechanisms. These findings provide new perspectives on the phenotypic heterogeneity in WS patients and theoretical basis for individualized noise protection strategies for patients carrying SOX10 mutations.
Animals ; SOXE Transcription Factors/genetics* ; Waardenburg Syndrome/physiopathology* ; Mice ; Hearing Loss, Noise-Induced/genetics* ; Evoked Potentials, Auditory, Brain Stem ; Mutation ; Noise ; Disease Models, Animal ; Ear, Inner/physiopathology*

OBJECTIVES: To explore the synthesis of high-quality CT (sCT) from cone-beam CT (CBCT) using PE-CycleGAN for adaptive radiotherapy (ART) for nasopharyngeal carcinoma. METHODS: A perception-enhanced CycleGAN model "PE-CycleGAN" was proposed, introducing dual-contrast discriminator loss, multi-perceptual generator loss, and improved U-Net structure. CBCT and CT data from 80 nasopharyngeal carcinoma patients were used as the training set, with 7 cases as the test set. By quantifying the mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), as well as the dose gamma pass rate and the relative dose deviations of the target area and organs at risk (OAR) between sCT and reference CT, the image quality and dose calculation accuracy of sCT were evaluated. RESULTS: The MAE of sCT generated by PE-CycleGAN compared to the reference CT was (56.89±13.84) HU, approximately 30% lower than CBCT's (81.06±15.86) HU (P<0.001). PE-CycleGAN's PSNR and SSIM were 26.69±2.41dB and 0.92±0.02 respectively, significantly higher than CBCT's 21.54±2.37dB and 0.86±0.05 (P<0.001), indicating substantial improvements in image quality and structural similarity. In gamma analysis, under the 2 mm/2% criterion, PE-CycleGAN's sCT achieved a pass rate of (90.13±3.75)%, significantly higher than CBCT's (81.65±3.92)% (P<0.001) and CycleGAN's (87.69±3.50)% (P<0.05). Under the 3 mm/3% criterion, PE-CycleGAN's sCT pass rate of (90.13±3.75)% was also significantly superior to CBCT's (86.92±3.51)% (P<0.001) and CycleGAN's (94.58±2.23)% (P<0.01). The mean relative dose deviation of the target area and OAR between sCT and planned CT was within ±3% for all regions, except for the Lens Dmax (Gy), which had a deviation of 3.38% (P=0.09). The mean relative dose deviations for PTVnx HI, PTVnd HI, PTVnd CI, PTV1 HI, PRV_SC, PRV_BS, Parotid, Larynx, Oral, Mandible, and PRV_ON were all less than ±1% (P>0.05). CONCLUSIONS PE-CycleGAN demonstrates the ability to rapidly synthesize high-quality sCT from CBCT, offering a promising approach for CBCT-guided adaptive radiotherapy in nasopharyngeal carcinoma.
Humans ; Cone-Beam Computed Tomography/methods* ; Nasopharyngeal Neoplasms/diagnostic imaging* ; Nasopharyngeal Carcinoma/radiotherapy* ; Radiotherapy Planning, Computer-Assisted/methods* ; Radiotherapy Dosage ; Signal-To-Noise Ratio ; Radiotherapy, Intensity-Modulated

OBJECTIVES: We propose a segmented backprojection tensor degradation feature encoding (SBP-MAC) model for motion artifact correction in dental cone beam computed tomography (CBCT) to improve the quality of the reconstructed images. METHODS: The proposed motion artifact correction model consists of a generator and a degradation encoder. The segmented limited-angle reconstructed sub-images are stacked into the tensors and used as the model input. A degradation encoder is used to extract spatially varying motion information in the tensor, and the generator's skip connection features are adaptively modulated to guide the model for correcting artifacts caused by different motion waveforms. The artifact consistency loss function was designed to simplify the learning task of the generator. RESULTS: The proposed model could effectively remove motion artifacts and improve the quality of the reconstructed images. For simulated data, the proposed model increased the peak signal-to-noise ratio by 8.28%, increased the structural similarity index measurement by 2.29%, and decreased the root mean square error by 23.84%. For real clinical data, the proposed model achieved the highest expert score of 4.4221 (against a 5-point scale), which was significantly higher than those of all the other comparison methods. CONCLUSIONS The SBP-MAC model can effectively extract spatially varying motion information in the tensors and achieve adaptive artifact correction from the tensor domain to the image domain to improve the quality of reconstructed dental CBCT images.
Cone-Beam Computed Tomography/methods* ; Artifacts ; Humans ; Motion ; Image Processing, Computer-Assisted/methods* ; Signal-To-Noise Ratio ; Algorithms

Noise-induced hearing loss is a worldwide public health issue that is characterized by temporary or permanent changes in hearing sensitivity. This condition is closely linked to inflammatory responses, and interventions targeting the inflammatory gene tumor necrosis factor-alpha (TNFα) are known to mitigate cochlear noise damage. TNFα-induced proteins (TNFAIPs) are a family of translucent acidic proteins, and TNFAIP6 has a notable association with inflammatory responses. To date, there have been few reports on TNFAIP6 levels in the inner ear. To elucidate the precise mechanism, we generated transgenic mouse models with conditional knockout of Tnfaip6 (Tnfaip6 cKO). Evaluation of hair cell morphology and function revealed no significant differences in hair cell numbers or ribbon synapses between Tnfaip6 cKO and wild-type mice. Moreover, there were no notable variations in hair cell numbers or hearing function in noisy environments. Our results indicate that Tnfaip6 does not have a substantial impact on the auditory system.
Animals ; Mice, Knockout ; Hair Cells, Auditory, Inner/pathology* ; Mice ; Mice, Transgenic ; Hearing Loss, Noise-Induced ; Evoked Potentials, Auditory, Brain Stem/physiology*