Tinnitus classification based on resting-state functional connectivity using a convolutional neural network architecture.

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.

Therapy effect of cochleural alternating acoustic beam therapy versus traditional sound therapy for managing chronic idiopathic tinnitus patients.

Idiopathic tinnitus is a common and complex disorder with no established cure. The CAABT (Cochleural Alternating Acoustic Beam Therapy CAABT), is a personalized sound therapy designed to target specific tinnitus frequencies and effectively intervene in tinnitus according to clinical tinnitus assessment. This study aimed to compare the effectiveness of the CAABT and Traditional Sound Therapy (TST) in managing chronic idiopathic tinnitus. This was a randomized, double-blind, parallel-group, single-center prospective study. Sixty adult patients with tinnitus were recruited and randomly assigned to the CAABT or TST group in a 1:1 ratio using a computer-generated randomization. The treatment lasted for 12 weeks, and participants underwent assessments using the tinnitus handicap inventory (THI), visual analog scale (VAS), tinnitus loudness measurements, and resting-state functional magnetic resonance imaging (rs-fMRI). Both groups showed significant reductions in THI scores, VAS scores, and tinnitus loudness after treatment. However, CAABT showed superiority to TST in THI Functional (p = 0.018), THI Emotional (p = 0.015), THI Catastrophic (p = 0.022), THI total score (p = 0.005) as well as VAS score (p = 0.022). More interesting, CAABT showed superiority to TST in the changes of THI scores, and VAS scores from baseline. The rs-fMRI results showed significant changes in the precuneus before and after treatment in both groups. Moreover, the CAABT group showed more changes in brain regions compared to the TST. No side effects were observed. These findings suggest that CAABT may be a promising treatment option for chronic idiopathic tinnitus, providing significant improvements in tinnitus-related symptoms and brain activity.Trial registration: ClinicalTrials.gov:NCT02774122.

Functional MRI Neurofeedback Outperforms Cognitive Behavioral Therapy for Reducing Tinnitus Distress: A Prospective Randomized Clinical Trial.

Background Cognitive behavioral therapy (CBT) is the current standard treatment for chronic severe tinnitus; however, preliminary evidence suggests that real-time functional MRI (fMRI) neurofeedback therapy may be more effective. Purpose To compare the efficacy of real-time fMRI neurofeedback against CBT for reducing chronic tinnitus distress. Materials and Methods In this prospective controlled trial, participants with chronic severe tinnitus were randomized from December 2017 to December 2021 to receive either CBT (CBT group) for 10 weekly group sessions or real-time fMRI neurofeedback (fMRI group) individually during 15 weekly sessions. Change in the Tinnitus Handicap Inventory (THI) score (range, 0-100) from baseline to 6 or 12 months was assessed. Secondary outcomes included four quality-of-life questionnaires (Beck Depression Inventory, Pittsburgh Sleep Quality Index, State-Trait Anxiety Inventory, and World Health Organization Disability Assessment Schedule). Questionnaire scores between treatment groups and between time points were assessed using repeated measures analysis of variance and the nonparametric Wilcoxon signed rank test. Results The fMRI group included 21 participants (mean age, 49 years ± 11.4 [SD]; 16 male participants) and the CBT group included 22 participants (mean age, 53.6 years ± 8.8; 16 male participants). The fMRI group showed a greater reduction in THI scores compared with the CBT group at both 6 months (mean score change, -28.21 points ± 18.66 vs -12.09 points ± 18.86; P = .005) and 12 months (mean score change, -30 points ± 25.44 vs -4 points ± 17.2; P = .01). Compared with baseline, the fMRI group showed improved sleep (mean score, 8.62 points ± 4.59 vs 7.25 points ± 3.61; P = .006) and trait anxiety (mean score, 44 points ± 11.5 vs 39.84 points ± 10.5; P = .02) at 1 month and improved depression (mean score, 13.71 points ± 9.27 vs 6.53 points ± 5.17; P = .01) and general functioning (mean score, 24.91 points ± 17.05 vs 13.06 points ± 10.1; P = .01) at 6 months. No difference in these metrics over time was observed for the CBT group (P value range, .14 to >.99). Conclusion Real-time fMRI neurofeedback therapy led to a greater reduction in tinnitus distress than the current standard treatment of CBT. ClinicalTrials.gov registration no.: NCT05737888; Swiss Ethics registration no.: BASEC2017-00813 © RSNA, 2024 Supplemental material is available for this article.

What is the role of the hippocampus and parahippocampal gyrus in the persistence of tinnitus?

The hippocampus and parahippocampal gyrus have been implicated as part of a tinnitus network by a number of studies. These structures are usually considered in the context of a "limbic system," a concept typically invoked to explain the emotional response to tinnitus. Despite this common framing, it is not apparent from current literature that this is necessarily the main functional role of these structures in persistent tinnitus. Here, we highlight a different role that encompasses their most commonly implicated functional position within the brain-that is, as a memory system. We consider tinnitus as an auditory object that is held in memory, which may be made persistent by associated activity from the hippocampus and parahippocampal gyrus. Evidence from animal and human studies implicating these structures in tinnitus is reviewed and used as an anchor for this hypothesis. We highlight the potential for the hippocampus/parahippocampal gyrus to facilitate maintenance of the memory of the tinnitus percept via communication with auditory cortex, rather than (or in addition to) mediating emotional responses to this percept.

Alterations of resting-state functional network connectivity in patients with noise-induced hearing loss: A study based on independent component analysis.

Functional reorganization is a response to auditory deficits or deprivation, and less is known about the overall brain network alterations involving resting-state networks (RSNs) and multiple functional networks in patients with occupational noise-induced hearing loss (NIHL). So this study evaluated resting-state functional network connectivity (FNC) alterations in occupational NIHL using an independent component analysis (ICA). In total, 79 mild NIHL patients (MP), 32 relatively severe NIHL patients (RSP), and 84 age- and education- matched healthy controls (HC) were recruited. All subjects were tested using the Mini-mental State Examination scale, the tinnitus Handicap Inventory scale, the Hamilton Anxiety scale (HAMA) and scanned by T1-3DFSPGR, resting-state functional magnetic resonance imaging sequence in 3.0 T and analysed by the ICA. Seven RSNs were identified, compared with the HC, the MP showed increased FNC within the executive control network (ECN) and enhanced FNC within the default mode network (DMN) and the visual network (VN); compared with the HC, the RSP showed decreased FNC within the ECN and auditory network (AUN), DMN and VN; no significant changes in FNC were found in the MP compared with the RSP. Furthermore, the correlation analysis between the noise exposure time and hearing loss level, HAMA were both negative, and there were no significant correlations between the abnormal RSNs and the hearing level, noise exposure time and HAMA. These findings indicate that different degrees of NIHL involve different alterations in RSNs connectivity and may reveal the neural mechanisms related to emotion-related features and functional abnormalities following long-term NIHL.

Association of anatomical features of the petrotympanic fissure and presence of foramen of Huschke with otalgia and tinnitus.

The petrotympanic fissure (PTF) and foramen of Huschke (FH) are anatomical structures in the temporal bone that can connect the temporomandibular joint (TMJ) and the ear. The purpose of this retrospective study was to investigate the association between PTF morphology and otalgia and tinnitus, as well as the prevalence of the FH and otological symptoms, using cone beam computed tomography (CBCT). CBCT images from 114 patients presenting with symptoms of a temporomandibular disorder were examined retrospectively. The PTF was classified into three subtypes (open, semi-open, closed) and the presence of the FH was identified. Symptoms of otalgia and tinnitus were obtained from the patient files. The FH was observed in 12.3% of patients examined, and in 12.0% of those with otalgia and 18.9% of those with tinnitus. There was no significant association between the PTF subtypes or the presence of the FH and otalgia or tinnitus (all P > 0.05). The PTF subtype and presence of the FH alone do not appear to contribute to otalgia or tinnitus in patients with temporomandibular disorders.

ACR Appropriateness Criteria® Tinnitus: 2023 Update.

Tinnitus is abnormal perception of sound and has many subtypes. Clinical evaluation, audiometry, and otoscopy should be performed before ordering any imaging, as the choice of imaging will depend on various factors. Type of tinnitus (pulsatile or nonpulsatile) and otoscopy findings of a vascular retrotympanic lesion are key determinants to guide the choice of imaging studies. High-resolution CT temporal bone is an excellent tool to detect glomus tumors, abnormal course of vessels, and some other abnormalities when a vascular retrotympanic lesion is seen on otoscopy. CTA or a combination of MR and MRA/MRV are used to evaluate arterial or venous abnormalities like dural arteriovenous fistula, arteriovenous malformation, carotid stenosis, dural sinus stenosis, and bony abnormalities like sigmoid sinus wall abnormalities in cases of pulsatile tinnitus without a vascular retrotympanic lesion. MR of the brain is excellent in detecting mass lesions such as vestibular schwannomas in cases of unilateral nonpulsatile tinnitus. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Auditory cortex hyperconnectivity before rTMS is correlated with tinnitus improvement.

INTRODUCTION: Repetitive transcranial magnetic stimulation (rTMS) has been used as a potential treatment for tinnitus; however, its effectiveness is variable and unpredictable. We hypothesized that resting-state functional connectivity before rTMS may be correlated with rTMS treatment effectiveness. METHODS: We applied 1-Hz rTMS to the left primary auditory (A1) and dorsolateral prefrontal cortices (DLPFC) of 10 individuals with tinnitus and 10 age-matched controls. Resting-state functional magnetic resonance imaging (fMRI) studies were performed approximately one week before rTMS. Seed-based connectivity analyses were conducted for each individual, with seed regions as rTMS target areas. RESULTS: Compared to controls, the left superior temporal areas showed significantly increased positive connectivity with the left A1 and negative connectivity with the left DLPFC in the tinnitus group. The left frontoparietal and right cerebellar areas showed significantly increased negative connectivity with the left A1 and positive connectivity with the left DLPFC. Seed-based hyperconnectivity was correlated with tinnitus improvement (pre-rTMS vs. 2-week post-rTMS Tinnitus Handicap Inventory scores). Tinnitus improvement was significantly correlated with left A1 hyperconnectivity; however, no correlation was observed with left DLPFC connectivity. Positive rTMS outcomes were associated with significantly increased positive connectivity in bilateral superior temporal areas and significantly increased negative connectivity in bilateral frontal areas. CONCLUSIONS: Our results suggest that oversynchronisation of left A1 connectivity before rTMS of the left A1 and DLPFC is associated with treatment effectiveness.

[Progress in neural network mechanism of tinnitus using functional magnetic resonance imaging].

Tinnitus refers to the perception of abnormal sound in the absence of external sound stimulation. It can have an impact on a person's mood, memory, attention, and mental state, although the mechanism of tinnitus is still unclear. In recent years, the research on the central neural mechanism of tinnitus has attracted the attention of scholars.Functional magnetic resonance imaging （fMRI）,as an effective imaging technology, has been actively employed in this field. This paper provides a systematic summary of studies on the central neural mechanism of tinnitus by fMRI in recent years,revealed the changes of functional connections among tinnitus-related neural networks,such as auditory network,limbic system,default mode network and salience network. The central neural mechanism of tinnitus involves multiple networks that interact with each other. By understanding this mechanism, we hope to develop more targeted prevention and treatment strategies to help patients alleviate long-term tinnitus.

Multimodal quantitative magnetic resonance imaging of the thalamus in tinnitus patients with different outcomes after sound therapy.

AIMS: This study systematically investigated structural and functional alterations in the thalamus and its subregions using multimodal magnetic resonance imaging (MRI) and examined its clinical relevance in tinnitus patients with different outcomes after sound therapy (narrowband noise). METHODS: In total, 60 patients with persistent tinnitus and 57 healthy controls (HCs) were recruited. Based on treatment efficacy, 28 patients were categorized into the effective group and 32 into the ineffective group. Five MRI measurements of the thalamus and its seven subregions, including gray matter volume, fractional anisotropy, fractional amplitude of low-frequency fluctuation, and functional connectivity (FC), were obtained for each participant and compared between the groups. RESULTS: Patients in both the groups exhibited widespread functional and diffusion abnormalities in the whole thalamus and several subregions, with more obvious changes observed in the effective group. All tinnitus patients had abnormal FC compared with the HCs; FC differences between the two patient groups were only observed in the striatal network, auditory-related cortex, and the core area of the limbic system. We combined the multimodal quantitative thalamic alterations and used it as an imaging indicator to evaluate prognosis before sound therapy and achieved a sensitivity of 71.9% and a specificity of 85.7%. CONCLUSION: Similar patterns of thalamic alterations were identified in tinnitus patients with different outcomes, with more obvious changes observed in the effective group. Our findings support the tinnitus generation hypothesis of frontostriatal gating system dysfunction. A combination of multimodal quantitative thalamic properties may be used as indicators to predict tinnitus prognosis before sound therapy.

[Functional neuroimaging options for tinnitus]. / Möglichkeiten der funktionellen Bildgebung bei Tinnitus.

BACKGROUND: The pathophysiology behind tinnitus is still not well understood. Different imaging methods help in the understanding of the complex relationships that lead to the perception of tinnitus. OBJECTIVE: Herein, different functional imaging methods that can be used in the study of tinnitus are presented. MATERIALS AND METHODS: Considering the recent literature on the subject, the relevant imaging methods used in tinnitus research are discussed. RESULTS AND CONCLUSION: Functional imaging can reveal correlates of tinnitus. Due to the still limited temporal and spatial resolution of current imaging modalities, a conclusive explanation of tinnitus remains elusive. With increasing use of functional imaging, additional important insights into the explanation of tinnitus will be gained in the future.

Hyperacusis is associated with smaller gray matter volumes in the supplementary motor area.

Hyperacusis is a disorder in loudness perception characterized by increased sensitivity to ordinary environmental sounds and associated with otologic conditions, including hearing loss and tinnitus (the phantom perception of sound) as well as neurologic and neuropsychiatric conditions. Hyperacusis is believed to arise centrally in the brain; however, the underlying causes are unknown. To gain insight into differences in brain morphology associated with hyperacusis, we undertook a retrospective case-control study comparing whole-brain gray matter morphology in participants with sensorineural hearing loss and tinnitus who either scored above or below the threshold for hyperacusis based on a standard questionnaire. We found that participants reporting hyperacusis had smaller gray matter volumes and cortical sheet thicknesses in the right supplementary motor area (SMA), independent of anxiety, depression, tinnitus burden, or sex. In fact, the right SMA volumes extracted from an independently defined volume of interest could accurately classify participants. Finally, in a subset of participants where functional data were also available, we found that individuals with hyperacusis showed increased sound-evoked responses in the right SMA compared to individuals without hyperacusis. Given the role of the SMA in initiating motion, these results suggest that in hyperacusis the SMA is involved in a motor response to sounds.

Tinnitus-frequency specific activity and connectivity: A MEG study.

Tinnitus pathophysiology has been associated with an atypical cortical network that involves functional changes in auditory and non-auditory areas. Numerous resting-state studies have replicated a tinnitus brain network to be significantly different from healthy-controls. Yet it is still unknown whether the cortical reorganization is attributed to the tinnitus frequency specifically or if it is frequency-irrelevant. Employing magnetoencephalography (MEG), the current study aimed to identify frequency-specific activity patterns by using an individual tinnitus tone (TT) and a 500 Hz-control tone (CT) as auditory stimuli, across 54 tinnitus patients. MEG data were analyzed in a data-driven approach employing a whole-head model in source space and in sources' functional connectivity. Compared to the CT, the event related source space analysis revealed a statistically significant response to TT involving fronto-parietal regions. The CT mainly involved typical auditory activation-related regions. A comparison of the cortical responses to a healthy control group that underwent the same paradigm rejected the alternative interpretation that the frequency-specific activation differences were due to the higher frequency of the TT. Overall, the results suggest frequency-specificity of tinnitus-related cortical patterns. In line with previous studies, we demonstrated a tinnitus-frequency specific network comprising left fronto-temporal, fronto-parietal and tempo-parietal junctions.

Blood Flow Velocity: a Decision Tool for Stenting Indication in Venous Pulsatile Tinnitus.

BACKGROUND AND PURPOSE: Lateral sinus stenosis is the most common cause of venous pulsatile tinnitus (VPT). Stenting is an effective treatment after demonstration of a trans-stenotic pressure gradient; however, pressure measurement has many technical limitations. In 2018, a study showed that a combined approach with intravascular velocity measurement could be effective in identifying most appropriate candidates for stenting. The aim of the present study was to evaluate a new strategy using this biomarker for the indication of stenting even without a significant pressure gradient. MATERIAL AND METHODS: Consecutive patients with disabling VPT were included from 2016 to 2019 and analyzed retrospectively. Intrasinusal pressures were measured and blood flow velocities (with a dual-sensor guidewire) were used for the indication of stenting independent of the pressure gradient. We evaluated the clinical outcome after stenting based on this new biomarker. RESULTS: A total of 41 patients were treated according to this strategy. At last follow-up (mean = 30.2 months), 32/33 patients (97%) treated by stenting showed complete resolution or a significant decrease in VPT intensity. The use of velocity as the threshold for indicating stenting identified 8 patients (24%) missed by the pressure gradient. Their clinical outcome after stenting was excellent and no complications occurred. CONCLUSION: Measurement of sinus blood flow velocity provides a hemodynamic explanation of disease and may be a better tool than pressure gradient for the indication of stenting in VPT.

Brain alterations in patients with intractable tinnitus before and after rTMS: A resting-state functional magnetic resonance imaging study.

OBJECTIVE: To observe abnormal tinnitus activity by evaluating the amplitude of low-frequency fluctuation (ALFF) changes in the brain was which detected by resting-state functional magnetic resonance imaging (rs-fMRI) in patients with intractable tinnitus before and after repetitive transcranial magnetic stimulation (rTMS). We hypothesized that rTMS could progressively revert local brain function back to a relatively normal range. METHODS: This prospective observational research study recruited 25 patients with intractable tinnitus, with 28 healthy controls matched by age, sex, and education level. Participants' Tinnitus Handicap Inventory (THI) scores and the visual analog scale (VAS) were used to determine the severity of their tinnitus before and after treatment. We processed the brain spontaneous neural activity of intractable tinnitus patients by ALFF, then, we determined its association with clinically evaluated indicators of intractable tinnitus. RESULTS: The total and the three sub-modules (functional [F], emotional [E], and catastrophic [C]) score of the THI and VAS in patients with intractable tinnitus decreased after treatment (P < 0.001). The effective rate of tinnitus patients was 66.9%. A few patients had a slight left facial muscle tremor or temporary mild scalp pain during treatment. Compared with healthy controls, participants with tinnitus significantly reduced ALFF within the left and right medial superior frontal gyrus (P < 0.005). After rTMS treatment, the left fusiform gyrus and right superior cerebellar lobe increased ALFF in those with tinnitus (P < 0.005). The changes in THI, VAS, and ALFF were positively correlated (P < 0.05). CONCLUSION: RTMS is effective in the treatment of tinnitus. It significantly reduces the THI/VAS score and improves the symptoms of tinnitus. No serious adverse reaction during rTMS were reported. The changes in the left fusiform gyrus and right superior part of the cerebellum may explain the mechanism of rTMS treatment in intractable tinnitus.

Radiographic Sigmoid Sinus Wall Abnormalities and Pulsatile Tinnitus: A Case-Control Study.

OBJECTIVE: Compare incidence of sigmoid sinus wall abnormalities (SSWAs) and other radiographic abnormalities in patients with pulsatile tinnitus (PT) versus controls. STUDY DESIGN: Retrospective case-control. SETTING: Tertiary referral center. PATIENTS: Adults with PT and high-resolution computed tomography imaging were compared with adults undergoing cochlear implant workup including high-resolution computed tomography imaging. MAIN OUTCOME MEASURES: Incidence of SSWA in PT cohort (n = 141) compared with control (n = 149, n = 298 ears). Secondary outcome measures included differences in demographics and in other radiographic abnormalities between cohorts. RESULTS: Patients with PT had a higher incidence of SSWA (34% versus 9%, p < 0.001) and superior canal dehiscence (23% versus 12%, p = 0.017) than controls. Spearman product component correlations demonstrated that ipsilateral PT was weakly associated with SSWA ( r = 0.354, p < 0.001). When SSWA was present in the PT cohort (n = 48 patients, n = 59 ears), in 31 cases (64.6%), the SSWA correlated with PT laterality (e.g., left SSWA, left PT); in 12 (25.0%), SSWA partially correlated with PT laterality (e.g., bilateral SSWA, right PT); and in 5 (10.4%), the SSWA did not correlate with PT laterality (e.g., right SSWA, left PT). CONCLUSIONS: For our patients with both PT and SSWA, the SSWA is likely a contributing factor in approximately 65% of cases. For a third of patients with PT and concomitant SSWA, the association between the two is either not causative or not solely causative. Surgeons counseling patients with PT and SSWA may be optimistic overall regarding sigmoid resurfacing procedures but must appreciate the possibility of treatment failure, likely because of untreated comorbid conditions.

CT evaluation of unilateral pulsatile tinnitus with jugular bulb wall dehiscence.

OBJECTIVES: To investigate the imaging features of unilateral pulsatile tinnitus (PT) with jugular bulb wall dehiscence (JBWD). METHODS: Computerized tomography angiography images of unilateral PT patients were reviewed between 2019 and 2021. Thirty-one symptomatic JBWD patients without sigmoid sinus wall dehiscence (SSWD) were included. Thirty-eight patients with SSWD were used as the control group. The prevalence of JBWD was calculated. The area and height of the jugular bulb, the extent of dehiscence, the presence of jugular bulb diverticulum, posterior condylar emissary vein (PCEV), oblique occipital sinus (OOS), venous outflow laterality (VOL), the degree of transverse sinus stenosis (TSS), and the pituitary height to sella turcica ratio were compared between the two groups. RESULTS: The prevalence of JBWD was 12.1%, and JBWD was established as a causative diagnosis in 5.0% of unilateral PT patients. There were no statistical differences in the gender, symptomatic side, or VOL between the two groups. The area of the jugular bulb was larger and the height was higher (parea < 0.001, pheight = 0.005). The prevalence of jugular bulb diverticulum was higher in the JBWD group (p = 0.002). The degree of symptomatic TSS was less severe (p < 0.001), and the prevalence of bilateral TSS was lower in the JBWD group (p < 0.001). The pituitary height to sella turcica ratio was greater (p = 0.004), the prevalence of PCEV (p = 0.014) was lower, and OOS (p = 0.015) was greater in the JBWD group. CONCLUSIONS: The correlating factors of PT with JBWD and PT with SSWD are significantly different. These findings can further facilitate early and efficient PT treatment. KEY POINTS: • The incidence of jugular bulb dehiscence (JBWD) accounted for approximately 12.1% in pulsatile tinnitus (PT) patients, and JBWD was established as a causative diagnosis in 5.0% of PT patients. • PT required large blood flows and abnormal flow patterns, whether in JBWD or sigmoid sinus wall dehiscence groups. • JBWD causing PT has some unique characteristic findings on CT.

Multi-tasking deep network for tinnitus classification and severity prediction from multimodal structural MR images.

Objective:Subjective tinnitus is an auditory phantom perceptual disorder without an objective biomarker. Fast and efficient diagnostic tools will advance clinical practice by detecting or confirming the condition, tracking change in severity, and monitoring treatment response. Motivated by evidence of subtle anatomical, morphological, or functional information in magnetic resonance images of the brain, we examine data-driven machine learning methods for joint tinnitus classification (tinnitus or no tinnitus) and tinnitus severity prediction.Approach:We propose a deep multi-task multimodal framework for tinnitus classification and severity prediction using structural MRI (sMRI) data. To leverage complementary information multimodal neuroimaging data, we integrate two modalities of three-dimensional sMRI-T1 weighted (T1w) and T2 weighted (T2w) images. To explore the key components in the MR images that drove task performance, we segment both T1w and T2w images into three different components-cerebrospinal fluid, grey matter and white matter, and evaluate performance of each segmented image.Main results:Results demonstrate that our multimodal framework capitalizes on the information across both modalities (T1w and T2w) for the joint task of tinnitus classification and severity prediction.Significance:Our model outperforms existing learning-based and conventional methods in terms of accuracy, sensitivity, specificity, and negative predictive value.

Cerebrovascular pulsatile tinnitus: causes, treatments, and outcomes in 164 patients with neuroangiographic correlation.

BACKGROUND: Pulsatile tinnitus (PT) can cause significant detriment to quality of life and may herald a life-threatening condition. Endovascular evaluation is the gold standard for the definitive diagnosis of PT and facilitates treatment. However, no large study has determined the distribution of causes and treatment outcomes of PT evaluated endovascularly. METHODS: Consecutive patients evaluated at a multidisciplinary PT clinic from a single academic center were retrospectively reviewed. Patients with a suspected cerebrovascular etiology of PT based on clinical and/or non-invasive imaging, who were evaluated by endovascular techniques (arteriography, venography, manometry, and/or balloon test occlusion), were included in analysis. Baseline clinical features and treatment results by final etiology of PT were compared. RESULTS: Of 552 patients referred for PT evaluation, 164 patients (29.7%) who underwent endovascular evaluation of PT were included. Mean (±SD) age at first clinical evaluation was 54.3±14.1 years (range 25-89 years); 111 patients (67.7%) were female. PT causes were 75.6% vascular and 24.4% non-vascular. Arteriovenous shunting lesions caused 20.7% of cases, venous etiologies 48.2%, and arterial etiologies 6.7%. Of patients with a shunting lesion treated with endovascular embolization, 96.9% had lasting significant improvement or resolution in PT. Endovascular stenting for venous sinus stenosis gave 84.6% of patients lasting improvement or resolution in PT. Arterial and non-vascular PT had fewer patients treated endovascularly and less improvement in PT symptoms. CONCLUSION: PT with a suspected vascular cause is most often attributable to venous etiologies. PT caused by arteriovenous shunting or venous sinus stenosis may be effectively treated endovascularly.