Multi-modal deep learning for joint prediction of otitis media and diagnostic difficulty.

Objectives: In this study, we propose a diagnostic model for automatic detection of otitis media based on combined input of otoscopy images and wideband tympanometry measurements.

Methods: We present a neural network-based model for the joint prediction of otitis media and diagnostic difficulty. We use the subclassifications acute otitis media and otitis media with effusion.

A Deep Learning Approach for Detecting Otitis Media From Wideband Tympanometry Measurements.

Objective: In this study, wepropose an automatic diagnostic algorithm for detecting otitis media based on wideband tympanometry measurements.

Methods: We develop a convolutional neural network for classification of otitis media based on the analysis of the wideband tympanogram. Saliency maps are computed to gain insight into the decision process of the convolutional neural network.

Inter-rater reliability of the diagnosis of otitis media based on otoscopic images and wideband tympanometry measurements.

Objectives: This study aims to investigate the inter-rater reliability and agreement of the diagnosis of otitis media with effusion, acute otitis media, and no effusion cases based on an otoscopy image and in some cases an additional wideband tympanometry measurement of the patient.

Methods: 1409 cases were examined and diagnosed by an otolaryngologist in the clinic, and otoscopy examination and wideband tympanometry (WBT) measurement were conducted. Afterwards, four otolaryngologists (Ear, Nose, and Throat doctors, ENTs), who did not perform the acute examination of the patients, evaluated the otoscopy images and WBT measurements results for diagnosis (acute otitis media, otitis media with effusion, or no effusion).

Deep metric learning for otitis media classification.

In this study, we propose an automatic diagnostic algorithm for detecting otitis media based on otoscopy images of the tympanic membrane. A total of 1336 images were assessed by a medical specialist into three diagnostic groups: acute otitis media, otitis media with effusion, and no effusion. To provide proper treatment and care and limit the use of unnecessary antibiotics, it is crucial to correctly detect tympanic membrane abnormalities, and to distinguish between acute otitis media and otitis media with effusion.

Morphological correlates of hearing loss after cochlear implantation and electro-acoustic stimulation in a hearing-impaired Guinea pig model.

Hybrid or electro-acoustic stimulation (EAS) cochlear implants (CIs) are designed to provide high-frequency electric hearing together with residual low-frequency acoustic hearing. However, 30-50% of EAS CI recipients lose residual hearing after implantation. The objective of this study was to determine the mechanisms of EAS-induced hearing loss in an animal model with high-frequency hearing loss.

Factors associated with hearing loss in a normal-hearing guinea pig model of Hybrid cochlear implants.

The Hybrid cochlear implant (CI), also known as Electro-Acoustic Stimulation (EAS), is a new type of CI that preserves residual acoustic hearing and enables combined cochlear implant and hearing aid use in the same ear. However, 30-55% of patients experience acoustic hearing loss within days to months after activation, suggesting that both surgical trauma and electrical stimulation may cause hearing loss. The goals of this study were to: 1) determine the contributions of both implantation surgery and EAS to hearing loss in a normal-hearing guinea pig model; 2) determine which cochlear structural changes are associated with hearing loss after surgery and EAS.

An Src-protein tyrosine kinase inhibitor to reduce cisplatin ototoxicity while preserving its antitumor effect.

Ototoxicity remains a major dose-limiting side effect of cisplatin. The current studies were carried out to evaluate the effectiveness of a novel Src-protein tyrosine kinase inhibitor in protecting the ear from cisplatin ototoxicity without compromising cisplatin's antitumor effects. The Src inhibitor has been shown to be effective in protecting the ear from noise-induced hearing loss.

Expression pattern of oxidative stress and antioxidant defense-related genes in the aging Fischer 344/NHsd rat cochlea.

The biological mechanisms that give rise to age-related hearing loss (ARHL) are still poorly understood. However, there is growing recognition that oxidative stress may be an important factor. To address this issue, we measured the changes in the expression of cochlear oxidative stress and antioxidant defense-related genes in young (2 months old), middle-aged (12 months old), and old (21-25 months old) Fischer 344/NHsd (F344/NHsd) rats and compared gene expression changes with ARHL.

Interaural stacked auditory brainstem response measures for detecting small unilateral acoustic tumors.

The Stacked auditory brainstem response (SABR) was developed and investigated as a screening tool for small (≤1 cm) unilateral acoustic tumors (vestibular schwannomas) that were missed by standard clinical auditory brainstem response (ABR) measures [Don et al.: Am J Otol 1997;18:608-621; Audiol Neurotol 2005;10:274-290]. While the SABR measure provided much greater sensitivity than the standard ABR measures for small tumor detection, we believed that the large intersubject variability of the SABR measure compromised both the sensitivity and specificity of the measure.

Too much of a good thing: long-term treatment with salicylate strengthens outer hair cell function but impairs auditory neural activity.

Aspirin has been extensively used in clinical settings. Its side effects on auditory function, including hearing loss and tinnitus, are considered as temporary. A recent promising finding is that chronic treatment with high-dose salicylate (the active ingredient of aspirin) for several weeks enhances expression of the outer hair cell (OHC) motor protein (prestin), resulting in strengthened OHC electromotility and enhanced distortion product otoacoustic emissions (DPOAE).

Age-related hearing loss: is it a preventable condition?

Numerous techniques have been tested to attempt to prevent the onset or progression of age-related hearing loss (ARHL): raising the animals in an augmented acoustic environment (used successfully in mouse and rat models), enhancing the antioxidant defenses with exogenous antioxidant treatments (used with mixed results in mouse and rat models), raising the animals with a calorie restricted diet (used successfully in mouse and rat models), restoring lost endocochlear potential voltage with exogenous electrical stimulation (used successfully in the Mongolian gerbil model), and hypothetical enhancement of outer hair cell electromotility with salicylate therapy. Studies of human ARHL have revealed a set of unique hearing loss configurations with unique underlying pathologies. Animal research has developed models for the different forms of age-related peripheral pathology.

The effects of acoustic environment after traumatic noise exposure on hearing and outer hair cells.

Previous studies reported that exposure to non-traumatic level sounds after traumatic noise exposure reduced the degree of noise-induced hearing loss and hair cell stereocilia damage. The current study investigated the effects of a 3-day post-noise acoustic environment on the degree of noise-induced hearing loss and cochlear damage. Female chinchillas were exposed to traumatic continuous noise (4 kHz octave-band noise) at 107 dB SPL for 1h and then placed in either an augmented acoustic environment (AAE) or deprived acoustic environment (DAE) for 3 days.

Ameliorative effects of an augmented acoustic environment on age-related hearing loss in middle-aged Fischer 344/NHsd rats.

Objectives/hypothesis: To investigate the effects of an augmented acoustic environment (AAE) on age-related hearing loss (ARHL) and outer hair cell (OHC) pathology in middle-aged Fischer 344/NHsd (F344/NHsd) rats.

Methods: Eleven F344/NHsd rats were divided into two groups: 1) the AAE group (n = 5), which was exposed to 4-20 kHz broadband noise at 80 dB SPL for 12 h/d, 5 d/wk for 13 weeks starting from 16 months of age; and 2) the control group (n = 6), which did not receive the AAE during the same time span. Auditory brainstem response thresholds were obtained at different time points, and OHC pathology was examined after 13 weeks of AAE using propidium iodide and antiprestin antibody staining.

Aging outer hair cells (OHCs) in the Fischer 344 rat cochlea: function and morphology.

As previously reported [Popelar, J., Groh, D., Pelanova, J.

Relation between outer hair cell loss and hearing loss in rats exposed to styrene.

The relationship between outer hair cell (OHC) loss and cochlear sensitivity is still unclear, because in many animal models there exist surviving but dysfunctional OHCs and also injured/dead inner hair cells (IHC). Styrene is an ototoxic agent, which targets and destroys OHCs starting from the third row to the second and first rows depending on the exposure level. The remaining cells may be less affected.

Age-related hearing loss in the Fischer 344/NHsd rat substrain.

Studies of the F344 rat have shown a variety of age-related auditory anatomy and physiology changes. The current study was undertaken to clarify the ARHL in the F344 rat, by examining the auditory pathway of the F344/NHsd substrain that is distributed by Harlan Laboratories for research in the United States. The F344/NHsd rat begins to lose its hearing at about 12 months, and by 24 months, there are 50-60 dB auditory brainstem response threshold shifts at 20 and 40 kHz and 20 dB losses at 5-10 kHz.

An alternative diagnostic test for active Ménière's disease and cochlear hydrops using high-pass noise masked responses: the complex amplitude ratio.

We [Don et al.: Otol Neurotol 2005;26:711-722] previously demonstrated that patients diagnosed with an active case of Ménière's disease could be distinguished from non-Ménière's normal-hearing subjects by a special auditory brainstem response method involving clicks and ipsilateral high-pass masking pink noise. Specifically, auditory brainstem responses to clicks presented alone and clicks with masking noise high-pass filtered at 8, 4, 2, 1 and 0.

A diagnostic test for Ménière's Disease and Cochlear Hydrops: impaired high-pass noise masking of auditory brainstem responses.

Hypothesis: Endolymphatic hydrops in patients diagnosed with Ménière's disease causes changes in the response properties of the basilar membrane that lead to impaired high-pass noise masking of auditory brainstem responses to clicks.

Background: Ménière's disease is defined as the idiopathic syndrome of endolymphatic (cochlear) hydrops, which is an abnormal increase in the volume of cochlear fluid (endolymph) in the inner ear. Accurate detection and diagnosis are important but difficult because of the lack of sufficiently sensitive tests.

The stacked ABR: a sensitive and specific screening tool for detecting small acoustic tumors.

The failure of standard ABR measures to detect small (< or =1 cm) acoustic tumors has led to the use of enhanced magnetic resonance imaging (MRI) as the standard to screen for small tumors. This study investigates the suitability of the stacked ABR as a sensitive screening alternative to MRI for small acoustic tumors (SATs). The objective of the study was to determine the sensitivity and specificity of the stacked ABR technique for detecting SATs.