ABSTRACT
OBJECTIVES: Many studies have investigated aberrant functional connectivity (FC) using resting-state functional MRI (rs-fMRI) in subjective tinnitus patients. However, no studies have verified the efficacy of resting-state FC as a diagnostic imaging marker. We established a convolutional neural network (CNN) model based on rs-fMRI FC to distinguish tinnitus patients from healthy controls, providing guidance and fast diagnostic tools for the clinical diagnosis of subjective tinnitus. METHODS: A CNN architecture was trained on rs-fMRI data from 100 tinnitus patients and 100 healthy controls using an asymmetric convolutional layer. Additionally, a traditional machine learning model and a transfer learning model were included for comparison with the CNN, and each of the three models was tested on three different brain atlases. RESULTS: Of the three models, the CNN model outperformed the other two models with the highest area under the curve, especially on the Dos_160 atlas (AUC = 0.944). Meanwhile, the model with the best classification performance highlights the crucial role of the default mode network, salience network, and sensorimotor network in distinguishing between normal controls and patients with subjective tinnitus. CONCLUSION: Our CNN model could appropriately tackle the diagnosis of tinnitus patients using rs-fMRI and confirmed the diagnostic value of FC as measured by rs-fMRI.
Subject(s)
Brain Mapping , Tinnitus , Humans , Brain Mapping/methods , Tinnitus/diagnostic imaging , Magnetic Resonance Imaging/methods , Brain/diagnostic imaging , Neural Networks, ComputerABSTRACT
Age-related hearing loss (ARHL), one of the most common sensory deficits in elderly individuals, is a risk factor for dementia; however, it is unclear how ARHL affects the decline in cognitive function. To address this issue, a connectome gradient framework was used to identify critical features of information integration between sensory and cognitive processing centers using resting-state functional magnetic resonance imaging (rs-fMRI) data from 40 individuals with ARHL and 36 healthy controls (HCs). The first three functional gradient alterations associated with ARHL were investigated at the global, network and regional levels. Using a support vector machine (SVM) model, our analysis distinguished individuals with ARHL with normal cognitive function from those with cognitive decline. Compared to HCs, individuals with ARHL had a contracted principal primary-to-transmodal gradient axis, especially in the visual and default mode networks, with an altered gradient explained ratio and variance. Among individuals with ARHL, cognitive decline was detected in the visual network in the principal gradient as well as in the limbic, salience and default mode networks in the third gradient (salience to frontoparietal/default mode). These results suggest that ARHL is associated with disrupted information processing from the primary sensory networks to higher-order cognitive networks and highlight the key nodes closely associated with cognitive decline during cognitive processing in ARHL, providing new insights into the mechanism of cognitive impairment and suggesting potential treatments related to ARHL.
Subject(s)
Cognitive Dysfunction , Connectome , Presbycusis , Humans , Aged , Connectome/methods , Cognition , Risk Factors , Magnetic Resonance Imaging/methodsABSTRACT
BACKGROUND: Previous studies have demonstrated that tinnitus is associated with neural changes in the cerebral cortex. This study is aimed at investigating the central nervous characteristics of tinnitus patients with different severity by using a rs-EEG. PARTICIPANTS AND METHODS: rs-EEG was recorded in fifty-seven patients with chronic tinnitus and twenty-seven healthy controls. Tinnitus patients were divided into moderate-to-severe tinnitus group and slight-to-mild tinnitus group based on their Tinnitus Handicap Inventory (THI) scores. Source localization and functional connectivity analyses were used to measure the changes in central levels and examine the altered network patterns. The correlation between functional connectivity and tinnitus severity was analyzed. RESULT: Compared to the healthy controls, all tinnitus patients showed significant activation in the auditory cortex (middle temporal lobe, BA 21), while moderate-to-severe tinnitus group showed enhanced connectivity between the parahippocampus and posterior cingulate gyrus. Moreover, the moderate-to-severe tinnitus group had enhanced functional connectivity between auditory cortex and insula compared to the slight-to-mild tinnitus group. The connections between the insula and the parahippocampal and posterior cingulate gyrus were positively correlated with THI scores. CONCLUSION: The current study reveals that patients with moderate-to-severe tinnitus demonstrate greater changes in the central brain areas, including the auditory cortex, insula, parahippocampus and posterior cingulate gyrus. In addition, enhanced connections were found between the insula and the auditory cortex, as well as the posterior cingulate gyrus and the parahippocampus, which suggests abnormality in the auditory network, salience network, and default mode network. Specifically, the insula is the core region of the neural pathway that is composed of the auditory cortex, insula, and parahippocampus/posterior cingulate gyrus. This suggests that the severity of tinnitus is affected by multiple brain regions.
Subject(s)
Brain Mapping , Tinnitus , Humans , Default Mode Network , Brain , Gyrus Cinguli , Magnetic Resonance ImagingABSTRACT
Electroencephalogram (EEG) is an important technology to explore the central nervous mechanism of tinnitus. However, it is hard to obtain consistent results in many previous studies for the high heterogeneity of tinnitus. In order to identify tinnitus and provide theoretical guidance for the diagnosis and treatment, we propose a robust, data-efficient multi-task learning framework called Multi-band EEG Contrastive Representation Learning (MECRL). In this study, we collect resting-state EEG data from 187 tinnitus patients and 80 healthy subjects to generate a high-quality large-scale EEG dataset on tinnitus diagnosis, and then apply the MECRL framework on the generated dataset to obtain a deep neural network model which can distinguish tinnitus patients from the healthy controls accurately. Subject-independent tinnitus diagnosis experiments are conducted and the result shows that the proposed MECRL method is significantly superior to other state-of-the-art baselines and can be well generalized to unseen topics. Meanwhile, visual experiments on key parameters of the model indicate that the high-classification weight electrodes of tinnitus' EEG signals are mainly distributed in the frontal, parietal and temporal regions. In conclusion, this study facilitates our understanding of the relationship between electrophysiology and pathophysiology changes of tinnitus and provides a new deep learning method (MECRL) to identify the neuronal biomarkers in tinnitus.
Subject(s)
Tinnitus , Humans , Tinnitus/diagnosis , Electroencephalography/methods , Neural Networks, Computer , BiomarkersABSTRACT
Patients with age-related hearing loss face hearing difficulties in daily life. The causes of age-related hearing loss are complex and include changes in peripheral hearing, central processing, and cognitive-related abilities. Furthermore, the factors by which aging relates to hearing loss via changes in auditory processing ability are still unclear. In this cross-sectional study, we evaluated 27 older adults (over 60 years old) with age-related hearing loss, 21 older adults (over 60 years old) with normal hearing, and 30 younger subjects (18-30 years old) with normal hearing. We used the outcome of the upper-threshold test, including the time-compressed threshold and the speech recognition threshold in noisy conditions, as a behavioral indicator of auditory processing ability. We also used electroencephalography to identify presbycusis-related abnormalities in the brain while the participants were in a spontaneous resting state. The time-compressed threshold and speech recognition threshold data indicated significant differences among the groups. In patients with age-related hearing loss, information masking (babble noise) had a greater effect than energy masking (speech-shaped noise) on processing difficulties. In terms of resting-state electroencephalography signals, we observed enhanced frontal lobe (Brodmann's area, BA11) activation in the older adults with normal hearing compared with the younger participants with normal hearing, and greater activation in the parietal (BA7) and occipital (BA19) lobes in the individuals with age-related hearing loss compared with the younger adults. Our functional connection analysis suggested that compared with younger people, the older adults with normal hearing exhibited enhanced connections among networks, including the default mode network, sensorimotor network, cingulo-opercular network, occipital network, and frontoparietal network. These results suggest that both normal aging and the development of age-related hearing loss have a negative effect on advanced auditory processing capabilities and that hearing loss accelerates the decline in speech comprehension, especially in speech competition situations. Older adults with normal hearing may have increased compensatory attentional resource recruitment represented by the top-down active listening mechanism, while those with age-related hearing loss exhibit decompensation of network connections involving multisensory integration.
ABSTRACT
OBJECTIVES: Chronic subjective tinnitus can have a serious effect on daily life, even causing serious psychological disorders. Currently there are no specific effective solutions or cures. Tailor-made notched music training (TMNMT) is a recently proposed sound therapy that has simpler processes and a higher compliance rate than tinnitus retraining therapy (TRT), a widely used treatment for chronic subjective tinnitus. This study explores the therapeutic effect of TMNMT in comparison to TRT to highlight its clinical value. DESIGN: The study was a randomized controlled, single-blinded clinical trial. One hundred twenty eligible participants were randomly assigned to receive TMNMT (n = 60) or TRT (n = 60) for 3 mo with concurrent follow-up. It should be noted that the duration of sound treatment in TRT was modified to 2 hr per day for better feasibility in practice. The primary outcome was mean change in tinnitus handicap inventory (THI) measured at baseline ( T0 ), 1 mo ( T1 ) and 3 mo ( T2 ) after intervention. Change in visual analog scale (VAS) was measured as a secondary outcome. A comparison of therapeutic effectiveness between TMNMT and TRT was evaluated by repeated measure analysis of variance. RESULTS: One hundred and twelve (93%) of participants took part in the study, of which 64 were men and 48 women. Mean (SD) age was 42.80 (12.91) years. Fifty-eight were allocated to receive TMNMT and 54 to receive TRT. The between-group difference in primary outcome was -6.90 points (95% confidence interval [CI], -13.53 to -0.27) at T1 and -6.17 points (95% CI, -13.04 to 0.71) at T2 . These results closely reached to clinical significance of tinnitus-related effective relief. For the secondary outcome, the mean value in the TMNMT group was 0.83 points (95% CI, 0.12 to 1.54), significantly lower than the mean value of the TRT group. The differences in THI and VAS between the two groups were statistically significant after intervention. Further analysis showed that age and baseline THI and VAS scores were associated with change in THI and VAS scores after interventions. CONCLUSIONS: Both TMNMT and TRT were able to alleviate chronic subjective tinnitus effectively after a 3 month intervention. When the two forms of therapy were compared TMNMT appeared to be more effective and consequently potentially superior to TRT for reducing tinnitus loudness and functional and emotional disturbance associated with chronic subjective tinnitus.
Subject(s)
Music , Tinnitus , Male , Humans , Adult , Female , Tinnitus/psychology , Treatment Outcome , Sound , Visual Analog ScaleABSTRACT
OBJECTIVE: To systematically evaluate the development of Machine Learning (ML) models and compare their diagnostic accuracy for the classification of Middle Ear Disorders (MED) using Tympanic Membrane (TM) images. METHODS: PubMed, EMBASE, CINAHL, and CENTRAL were searched up until November 30, 2021. Studies on the development of ML approaches for diagnosing MED using TM images were selected according to the inclusion criteria. PRISMA guidelines were followed with study design, analysis method, and outcomes extracted. Sensitivity, specificity, and area under the curve (AUC) were used to summarize the performance metrics of the meta-analysis. Risk of Bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool in combination with the Prediction Model Risk of Bias Assessment Tool. RESULTS: Sixteen studies were included, encompassing 20254 TM images (7025 normal TM and 13229 MED). The sample size ranged from 45 to 6066 per study. The accuracy of the 25 included ML approaches ranged from 76.00% to 98.26%. Eleven studies (68.8%) were rated as having a low risk of bias, with the reference standard as the major domain of high risk of bias (37.5%). Sensitivity and specificity were 93% (95% CI, 90%-95%) and 85% (95% CI, 82%-88%), respectively. The AUC of total TM images was 94% (95% CI, 91%-96%). The greater AUC was found using otoendoscopic images than otoscopic images. CONCLUSIONS: ML approaches perform robustly in distinguishing between normal ears and MED, however, it is proposed that a standardized TM image acquisition and annotation protocol should be developed. LEVEL OF EVIDENCE: NA Laryngoscope, 133:732-741, 2023.
Subject(s)
Ear Diseases , Tympanic Membrane , Humans , Tympanic Membrane/diagnostic imaging , Ear Diseases/diagnosis , Machine Learning , Otoscopy/methods , Ear, Middle/diagnostic imagingABSTRACT
BACKGROUND: This study aimed to develop and validate a deep learning (DL) model to identify atelectasis and attic retraction pocket in cases of otitis media with effusion (OME) using multi-center otoscopic images. METHOD: A total of 6393 OME otoscopic images from three centers were used to develop and validate a DL model for detecting atelectasis and attic retraction pocket. A threefold random cross-validation procedure was adopted to divide the dataset into training validation sets on a patient level. A team of otologists was assigned to diagnose and characterize atelectasis and attic retraction pocket in otoscopic images. Receiver operating characteristic (ROC) curves, including area under the ROC curve (AUC), accuracy, sensitivity, and specificity were used to assess the performance of the DL model. Class Activation Mapping (CAM) illustrated the discriminative regions in the otoscopic images. RESULTS: Among all OME otoscopic images, 3564 (55.74%) were identified with attic retraction pocket, and 2460 (38.48%) with atelectasis. The diagnostic DL model of attic retraction pocket and atelectasis achieved a threefold cross-validation accuracy of 89% and 79%, AUC of 0.89 and 0.87, a sensitivity of 0.93 and 0.71, and a specificity of 0.62 and 0.84, respectively. Larger and deeper cases of atelectasis and attic retraction pocket showed greater weight, based on the red color depicted in the heat map of CAM. CONCLUSION: The DL algorithm could be employed to identify atelectasis and attic retraction pocket in otoscopic images of OME, and as a tool to assist in the accurate diagnosis of OME.
Subject(s)
Deep Learning , Otitis Media with Effusion , Otitis Media , Pulmonary Atelectasis , Humans , Ear, Middle , Otitis Media with Effusion/diagnosis , Otitis Media with Effusion/diagnostic imaging , Tympanic MembraneABSTRACT
BACKGROUND: Clinically, the evidence of endolymphatic hydrops (EH) in Meniere's disease (MD) primarily relies on audiological examinations, such as glycerol tests and electrocochleography, to suggest the presence of EH indirectly. However, these techniques lack sensitivity and specificity, and they do not sufficiently assess the degree of EH. This study aims to explore the application of three-dimensional fluid-attenuated inversion recovery (3D-FLAIR) and three-dimensional real inversion recovery (3D-real IR) sequence imaging of EH in MD and to assess the image quality and grading of EH. METHODS: The study included 50 patients with definite MD. The 3D-FLAIR and 3D-real IR sequence images were performed 24 h after bilateral intratympanic injection of gadolinium. The image quality of both sequences was reviewed by two experienced radiologists. The vestibular and cochlear EH grades of both sequences were reviewed by two experienced otologists using a visual grading method. The Cohen's kappa and Pearson tests were used to analyze the data. RESULTS: The reliability of image quality between the two radiologists was excellent (0.7 < kappa < 0.9). There were significant statistical differences in the image quality between the 3D-real IR and 3D-FLAIR sequences (p = 0.023 and p = 0.035, respectively). The reliability for the grading of vestibular and cochlear EH between the two otologists was excellent (0.7 < kappa < 0.9). The 3D-real IR sequence detected more severe hydrops than did the 3D-FLAIR sequence (p < 05). CONCLUSION: The image quality of the 3D-real IR sequence is better than that of the 3D-FLAIR sequence, and there are differences in the vestibular and cochlear EH grades of both sequences. The sensitivity of the 3D-real IR sequence in the cochlea is higher. The method of visual grading can be applied to both technologies when combined with 3D-real IR.
Subject(s)
Endolymphatic Hydrops , Meniere Disease , Humans , Meniere Disease/diagnostic imaging , Gadolinium , Reproducibility of Results , Glycerol , Contrast Media , Endolymphatic Hydrops/diagnostic imaging , Magnetic Resonance Imaging/methods , Imaging, Three-DimensionalABSTRACT
Purpose: The possible relationship between migraine and tinnitus still remains elusive although migraine is often accompanied by chronic tinnitus. Several neuroimaging studies have reinforced the cognitive network abnormality in migraine and probably as well as tinnitus. The present work aims to investigate the dynamic neurocognitive network alterations of migraine comorbid with tinnitus. Materials and Methods: Participants included migraine patients (n = 32), tinnitus patients (n = 20), migraine with tinnitus (n = 27), and healthy controls (n = 47), matched for age and gender. Resting-state functional magnetic resonance imaging (rs-fMRI) with independent component analysis (ICA), sliding window cross-correlation, and clustering state analysis was used to detect the dynamic functional network connectivity (dFNC) of each group. Correlation analyses illustrated the association between clinical symptoms and abnormal dFNC in migraine as well as tinnitus. Results: Compared with healthy controls, migraine patients exhibited decreased cerebellar network and visual network (CN-VN) connectivity in State 2; migraine with tinnitus patients showed not only decreased CN-VN connectivity in State 2 but also decreased cerebellar network and executive control network (CN-ECN) connectivity in State 2 and increased cerebellar network and somatomotor network (SMN-VN) connectivity in State 1. The abnormal cerebellum dFNC with the executive control network (CN-ECN) was negatively correlated with headache frequency of migraine (rho = -0.776, p = 0.005). Conclusion: Brain network characteristics of migraine with tinnitus patients may indicate different mechanisms for migraine and tinnitus. Our results demonstrated a transient pathologic state with atypical cerebellar-cortical connectivity in migraine with tinnitus patients, which might be used to identify the neuro-pathophysiological mechanisms in migraine accompanied by tinnitus.
ABSTRACT
PURPOSE: Previous studies have demonstrated that people with tinnitus show attention dysfunctions. In this study, we investigated the influence of tinnitus on attention orienting, especially whether the ability of attention orienting could be modulated by the degree of tinnitus. METHOD: Fifty-nine and 54 unilateral tinnitus participants were included in Experiment 1 and Experiment 2, respectively. All participants reported subjective tinnitus for at least 3 months and were divided into a mild tinnitus group (Tinnitus Handicap Inventory [THI] < 37) or a moderate to severe tinnitus group (THI ≥ 37) according to the THI score. An auditory exogenous attention task and an auditory endogenous attention task were adopted. In the exogenous task, a target sound following a cue sound was presented on either the left or right side. Participants were required to discriminate whether the target was pure tone or white noise. In the endogenous task, participants were required to pay attention to the stimuli on one side and judge the pitch of a target sound. Mixed-design analyses of variance were conducted for the mean reaction times and accuracy across the experimental conditions. RESULTS: Our results showed that in the endogenous attention task, compared with the mild tinnitus group, moderate to severe tinnitus participants had better performance for stimuli presented on the tinnitus side but not on the nontinnitus side. In contrast, in the exogenous attention task, no differences were found between mild and moderate to severe tinnitus groups. CONCLUSION: The results suggest that the degree of tinnitus influences the performance of auditory endogenous attention but not auditory exogenous attention orienting.
Subject(s)
Tinnitus , Humans , Reaction Time , SoundABSTRACT
PURPOSE: Logistic regression analysis was used to explore the factors that influence tinnitus improvement after idiopathic sudden sensorineural hearing loss (ISSNHL) treatment. MATERIALS AND METHODS: In this retrospective study, 137 ISSNHL patients with tinnitus were recruited at the Sun Yatsen Memorial Hospital of Sun Yat-sen University, China. They underwent audiological examinations, vestibular assessments, tinnitus examinations, a Tinnitus Handicap Inventory (THI) assessment and ISSNHL treatments. Logistic regression analysis was performed to investigate factors that affected tinnitus improvement. RESULTS: Participants were divided into an effective group (73 patients) and noneffective group (64 patients) according to THI scores before and after treatment. The effective group had better averaged hearing threshold than the noneffective group (effective group vs. noneffective group: 74.47 vs. 87.66 dB HL; t = 3.03, p < 0.05). Additionally, before intervention there were significant difference in profound audiogram configuration (effective group vs. noneffective group: 17.81% vs. 46.88%, x2 = 23.63; p < 0.001), mid tinnitus pitch (effective group vs. noneffective group: 19.18% vs. 35.94%, x2 = 6.58; p = 0.037) and mean THI scores (effective group vs. noneffective group: 57.07 ± 22.27 vs. 36.78 ± 24.41, t = -5.09, p < 0.001) between the effective and noneffective tinnitus groups. Logistic regression analysis showed that audiogram configurations (profound audiogram: OR = 0.10, 95% CI 0.01-0.72, p = 0.022), tinnitus pitch (mid tinnitus pitch: OR = 0.16, 95% CI 0.05-0.57, p = 0.004) and THI scores (OR = 1.05, 95% CI 1.03-1.07, p < 0.001) were independent factors associated with tinnitus improvement. CONCLUSION: Audiogram configuration, tinnitus pitch, and THI scores before intervention appear to be predictive of the effectiveness of acute tinnitus improvement following ISSNHL treatment.
Subject(s)
Hearing Loss, Sensorineural , Hearing Loss, Sudden , Tinnitus , Hearing Loss, Sensorineural/complications , Hearing Loss, Sensorineural/therapy , Hearing Loss, Sudden/complications , Hearing Loss, Sudden/therapy , Humans , Prognosis , Retrospective Studies , Tinnitus/therapyABSTRACT
Importance: Otitis media with effusion (OME) is one of the most common causes of acquired conductive hearing loss (CHL). Persistent hearing loss is associated with poor childhood speech and language development and other adverse consequence. However, to obtain accurate and reliable hearing thresholds largely requires a high degree of cooperation from the patients. Objective: To predict CHL from otoscopic images using deep learning (DL) techniques and a logistic regression model based on tympanic membrane features. Design, Setting, and Participants: A retrospective diagnostic/prognostic study was conducted using 2790 otoscopic images obtained from multiple centers between January 2015 and November 2020. Participants were aged between 4 and 89 years. Of 1239 participants, there were 209 ears from children and adolescents (aged 4-18 years [16.87%]), 804 ears from adults (aged 18-60 years [64.89%]), and 226 ears from older people (aged >60 years, [18.24%]). Overall, 679 ears (54.8%) were from men. The 2790 otoscopic images were randomly assigned into a training set (2232 [80%]), and validation set (558 [20%]). The DL model was developed to predict an average air-bone gap greater than 10 dB. A logistic regression model was also developed based on otoscopic features. Main Outcomes and Measures: The performance of the DL model in predicting CHL was measured using the area under the receiver operating curve (AUC), accuracy, and F1 score (a measure of the quality of a classifier, which is the harmonic mean of precision and recall; a higher F1 score means better performance). In addition, these evaluation parameters were compared to results obtained from the logistic regression model and predictions made by three otologists. Results: The performance of the DL model in predicting CHL showed the AUC of 0.74, accuracy of 81%, and F1 score of 0.89. This was better than the results from the logistic regression model (ie, AUC of 0.60, accuracy of 76%, and F1 score of 0.82), and much improved on the performance of the 3 otologists; accuracy of 16%, 30%, 39%, and F1 scores of 0.09, 0.18, and 0.25, respectively. Furthermore, the DL model took 2.5 seconds to predict from 205 otoscopic images, whereas the 3 otologists spent 633 seconds, 645 seconds, and 692 seconds, respectively. Conclusions and Relevance: The model in this diagnostic/prognostic study provided greater accuracy in prediction of CHL in ears with OME than those obtained from the logistic regression model and otologists. This indicates great potential for the use of artificial intelligence tools to facilitate CHL evaluation when CHL is unable to be measured.
Subject(s)
Deep Learning , Otitis Media with Effusion , Otitis Media , Adolescent , Adult , Aged , Aged, 80 and over , Artificial Intelligence , Child , Child, Preschool , Hearing Loss, Conductive/diagnosis , Hearing Loss, Conductive/etiology , Humans , Male , Middle Aged , Otitis Media/complications , Otitis Media with Effusion/complications , Otitis Media with Effusion/diagnostic imaging , Retrospective Studies , Young AdultABSTRACT
BACKGROUND: The aberrant brain network that gives rise to the phantom sound of tinnitus is believed to determine the effectiveness of tinnitus therapies involving neuromodulation with repetitive transcranial magnetic stimulation (rTMS) and sound therapy utilizing tailor-made notch music training (TMNMT). To test this hypothesis, we determined how effective rTMS or TMNMT were in ameliorating tinnitus in patients with different functional brain networks. METHODS: Resting-state functional MRI was used to construct brain functional networks in patients with tinnitus (41 males/45 females, mean age 49.53±11.19 years) and gender-matched healthy controls (22 males/35 females, mean age 46.23±10.23 years) with independent component analysis (ICA). A 2 × 2 analysis of variance with treatment outcomes (Effective group, EG/Ineffective group, IG) and treatment types (rTMS/TMNMT) was used to test the interaction between outcomes and treatment types associated with functional network connections (FNCs). FINDINGS: The optimal neuroimaging indicator for responding to rTMS (AUC 0.804, sensitivity 0.700, specificity 0.913) was FNCs in the salience network-right frontoparietal network (SN-RFPN) while for responding to TMNMT (AUC 0.764, sensitivity 0.864, specificity 0.667) was the combination of FNCs in the auditory network- salience network (AUN-SN) and auditory network-cerebellar network (AUN-CN). INTERPRETATION: Tinnitus patients with higher FNCs in the SN-RFPN is associated with a recommendation for rTMS whereas patients with lower FNCs in the AUN-SN and AUN-CN would suggest TMNMT as the better choice. These results indicate that brain network-based measures aid in the selection of the optimal form of treatment for a patient contributing to advances in precision medicine. FUNDING: Yuexin Cai is supported by Key R&D Program of Guangdong Province, China (Grant No. 2018B030339001), National Natural Science Foundation of China (82071062), Natural Science Foundation of Guangdong province (2021A1515012038), the Fundamental Research Funds for the Central Universities (20ykpy91), and Sun Yat-Sen Clinical Research Cultivating Program (SYS-Q-201903). Yu-Chen Chen is supported by Medical Science and Technology Development Foundation of Nanjing Department of Health (No. ZKX20037), and Natural Science Foundation of Jiangsu Province (No. BK20211008).
Subject(s)
Auditory Cortex , Tinnitus , Adult , Brain/diagnostic imaging , Female , Humans , Magnetic Resonance Imaging , Male , Middle Aged , Tinnitus/diagnostic imaging , Tinnitus/therapy , Transcranial Magnetic Stimulation/methods , Treatment OutcomeABSTRACT
PURPOSE: The reorganization of the limbic regions extend to general cognitive network is believed to exist in the chronicity of tinnitus with particular 'hubs' contributing to a 'noise-cancellation' mechanism. To test this hypothesis, we investigated the topological brain network of tinnitus in different periods. METHODS: Resting-state functional magnetic resonance imaging were obtained from 32 patients with acute tinnitus, 41 patients with chronic tinnitus and 60 age- and gender- matched healthy controls (HC). The topological features of their brain networks were explored using graph theory analysis. RESULTS: Common small-world attributes were compared between the three groups, all showed a significantly increased values in Cp, Lp, λ (all p < 0.05). Significantly increased nodal centralities in the left superior frontal gyrus and the right precuneus, significantly decreased nodal centralities in the right inferior temporal gyrus were observed for acute tinnitus patients compared to HC. While for chronic tinnitus patients, there were significant increased nodal centralities in the left hippocampus, amygdala, and temporal pole, but decreased nodal centralities in the right inferior temporal gyrus. Additionally, significant higher nodal centralities were found in bilateral medial superior frontal gyrus for acute tinnitus patients compared to chronic tinnitus patients. Besides, alterations in rich-club organization were found in acute tinnitus patients and chronic tinnitus patients compared with HC, with increased functional connections among rich-club nodes and peripheral nodes in patients with tinnitus. CONCLUSIONS: Brain network topological properties altered across prefrontal-limbic-subcortical regions in tinnitus. The existed hubs in tinnitus might indicate an emotional and cognitive burden in 'noise-cancellation' mechanism.
Subject(s)
Hearing/physiology , Limbic System/physiopathology , Neural Pathways , Tinnitus/pathology , Amygdala , Brain/pathology , Female , Hippocampus , Humans , Magnetic Resonance Imaging , Male , Middle Aged , Parietal Lobe , Prefrontal CortexABSTRACT
The incidence of tinnitus is very high, which can affect the patient's attention, emotion and sleep, and even cause serious psychological distress and suicidal tendency. Currently, there is no uniform and objective method for tinnitus detection and therapy, and the mechanism of tinnitus is still unclear. In this study, we first collected the resting state electroencephalogram (EEG) data of tinnitus patients and healthy subjects. Then the power spectrum topology diagrams were compared of in the band of δ (0.5-3 Hz), θ (4-7 Hz), α (8-13 Hz), ß (14-30 Hz) and γ (31-50 Hz) to explore the central mechanism of tinnitus. A total of 16 tinnitus patients and 16 healthy subjects were recruited to participate in the experiment. The results of resting state EEG experiments found that the spectrum power value of tinnitus patients was higher than that of healthy subjects in all concerned frequency bands. The t-test results showed that the significant difference areas were mainly concentrated in the right temporal lobe of the θ and α band, and the temporal lobe, parietal lobe and forehead area of the ß and γ band. In addition, we designed an attention-related task experiment to further study the relationship between tinnitus and attention. The results showed that the classification accuracy of tinnitus patients was significantly lower than that of healthy subjects, and the highest classification accuracies were 80.21% and 88.75%, respectively. The experimental results indicate that tinnitus may cause the decrease of patients' attention.
Subject(s)
Tinnitus , Attention , Brain , Electroencephalography , Humans , Parietal LobeABSTRACT
OBJECTIVES: Numerous task-based functional magnetic resonance imaging studies indicate the presence of compensatory functional improvement in patients with congenital cataracts. However, there is neuroimaging evidence that shows decreased sensory perception or cognition information processing related to visual dysfunction, which favors a general loss hypothesis. This study explored the functional connectivity between visual and other networks in children with congenital cataracts using resting state electroencephalography. METHODS: Twenty-one children with congenital cataracts (age: 8.02 ± 2.03 years) and thirty-five sex- and age-matched normal sighted controls were enrolled to investigate functional connectivity between the visual cortex and the default mode network, the salience network, and the cerebellum network during resting state electroencephalography (eyes closed) recordings. RESULT: The congenital cataract group was less active, than the control group, in the occipital, temporal, frontal and limbic lobes in the theta, alpha, beta1 and beta2 frequency bands. Additionally, there was reduced alpha-band connectivity between the visual and somatosensory cortices and between regions of the frontal and parietal cortices associated with cognitive and attentive control. CONCLUSION: The results indicate abnormalities in sensory, cognition, motion and execution functional connectivity across the developing brains of children with congenital cataracts when compared with normal controls. Reduced frontal alpha activity and alpha-band connectivity between the visual cortex and salience network might reflect attenuated inhibitory information flow, leading to higher attentional states, which could contribute to adaptation of environmental change in this group of patients.
ABSTRACT
Wideband Absorbance Immittance (WAI) has been available for more than a decade, however its clinical use still faces the challenges of limited understanding and poor interpretation of WAI results. This study aimed to develop Machine Learning (ML) tools to identify the WAI absorbance characteristics across different frequency-pressure regions in the normal middle ear and ears with otitis media with effusion (OME) to enable diagnosis of middle ear conditions automatically. Data analysis included pre-processing of the WAI data, statistical analysis and classification model development, and key regions extraction from the 2D frequency-pressure WAI images. The experimental results show that ML tools appear to hold great potential for the automated diagnosis of middle ear diseases from WAI data. The identified key regions in the WAI provide guidance to practitioners to better understand and interpret WAI data and offer the prospect of quick and accurate diagnostic decisions.
Subject(s)
Acoustic Impedance Tests , Ear/pathology , Machine Learning , Otitis Media with Effusion/diagnosis , Adolescent , Adult , Aged , Child , Child, Preschool , Databases as Topic , Humans , Image Processing, Computer-Assisted , Infant , Middle Aged , Neural Networks, Computer , Otitis Media with Effusion/diagnostic imaging , Pressure , ROC Curve , Radio Waves , Statistics as Topic , Young AdultABSTRACT
OBJECTIVES: This study investigated the usefulness and performance of a two-stage attention-aware convolutional neural network (CNN) for the automated diagnosis of otitis media from tympanic membrane (TM) images. DESIGN: A classification model development and validation study in ears with otitis media based on otoscopic TM images. Two commonly used CNNs were trained and evaluated on the dataset. On the basis of a Class Activation Map (CAM), a two-stage classification pipeline was developed to improve accuracy and reliability, and simulate an expert reading the TM images. SETTING AND PARTICIPANTS: This is a retrospective study using otoendoscopic images obtained from the Department of Otorhinolaryngology in China. A dataset was generated with 6066 otoscopic images from 2022 participants comprising four kinds of TM images, that is, normal eardrum, otitis media with effusion (OME) and two stages of chronic suppurative otitis media (CSOM). RESULTS: The proposed method achieved an overall accuracy of 93.4% using ResNet50 as the backbone network in a threefold cross-validation. The F1 Score of classification for normal images was 94.3%, and 96.8% for OME. There was a small difference between the active and inactive status of CSOM, achieving 91.7% and 82.4% F1 scores, respectively. The results demonstrate a classification performance equivalent to the diagnosis level of an associate professor in otolaryngology. CONCLUSIONS: CNNs provide a useful and effective tool for the automated classification of TM images. In addition, having a weakly supervised method such as CAM can help the network focus on discriminative parts of the image and improve performance with a relatively small database. This two-stage method is beneficial to improve the accuracy of diagnosis of otitis media for junior otolaryngologists and physicians in other disciplines.
Subject(s)
Neural Networks, Computer , Neuroendoscopy/methods , Otitis Media/diagnostic imaging , Tympanic Membrane/diagnostic imaging , China , Humans , Neuroendoscopy/instrumentation , Reproducibility of Results , Retrospective StudiesABSTRACT
The objective of this study was to investigate alterations to brain activity and functional connectivity in patients with tinnitus, exploring neural features in the transition from acute to chronic phantom perception. Twenty-four patients with acute tinnitus, 23 patients with chronic tinnitus, and 32 healthy controls were recruited. High-density electroencephalography (EEG) was used to explore changes in brain areas and functional connectivity in different groups. When compared with healthy subjects, acute tinnitus patients had a significant reduction in superior frontal cortex activity across all frequency bands, whereas chronic tinnitus patients had a significant reduction in the superior frontal cortex at beta 3 and gamma frequency bands as well as a significant increase in the inferior frontal cortex at delta-band and superior temporal cortex at alpha 1 frequency band. When compared to the chronic tinnitus group, the acute tinnitus group activity was significantly increased in the middle frontal and parietal gyrus at the gamma-band. Functional connectivity analysis showed that the chronic tinnitus group had increased connections between the parahippocampus gyrus, posterior cingulate cortex, and precuneus when compared with the healthy group. Alterations of local brain activity and connections between the parahippocampus gyrus and other nonauditory areas appeared in the transition from acute to chronic tinnitus. This indicates that the appearance and development of tinnitus is a dynamic process involving aberrant local neural activity and abnormal connectivity in multifunctional brain networks.