scholarly journals Analysing wideband absorbance immittance in normal and ears with otitis media with effusion using machine learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Emad M. Grais ◽  
Xiaoya Wang ◽  
Jie Wang ◽  
Fei Zhao ◽  
Wen Jiang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Statistical Analysis ◽  
Otitis Media ◽  
Middle Ear ◽  
Otitis Media With Effusion ◽  
Model Development ◽  
Classification Model ◽  
Clinical Use ◽  
Automated Diagnosis

AbstractWideband 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.

scholarly journals Investigating the use of a two-stage attention-aware convolutional neural network for the automated diagnosis of otitis media from tympanic membrane images: a prediction model development and validation study

BMJ Open ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. e041139
Author(s):  
Yuexin Cai ◽  
Jin-Gang Yu ◽  
Yuebo Chen ◽  
Chu Liu ◽  
Lichao Xiao ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Tympanic Membrane ◽  
Otitis Media ◽  
Validation Study ◽  
Model Development ◽  
Classification Model ◽  
Automated Diagnosis ◽  
Two Stage ◽  
Development And Validation

ObjectivesThis 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.DesignA 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 participantsThis 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).ResultsThe 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.ConclusionsCNNs 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.

scholarly journals An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases

2021 ◽  
Vol 10 (15) ◽  
pp. 3198
Author(s):  
Hayoung Byun ◽  
Sangjoon Yu ◽  
Jaehoon Oh ◽  
Junwon Bae ◽  
Myeong Seong Yoon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Tympanic Membrane ◽  
Otitis Media ◽  
Middle Ear ◽  
Otitis Media With Effusion ◽  
Chronic Otitis Media ◽  
Diagnostic Process ◽  
Ear Diseases ◽  
Learning Network ◽  
Resident Physicians

The present study aimed to develop a machine learning network to diagnose middle ear diseases with tympanic membrane images and to identify its assistive role in the diagnostic process. The medical records of subjects who underwent ear endoscopy tests were reviewed. From these records, 2272 diagnostic tympanic membranes images were appropriately labeled as normal, otitis media with effusion (OME), chronic otitis media (COM), or cholesteatoma and were used for training. We developed the “ResNet18 + Shuffle” network and validated the model performance. Seventy-one representative cases were selected to test the final accuracy of the network and resident physicians. We asked 10 resident physicians to make diagnoses from tympanic membrane images with and without the help of the machine learning network, and the change of the diagnostic performance of resident physicians with the aid of the answers from the machine learning network was assessed. The devised network showed a highest accuracy of 97.18%. A five-fold validation showed that the network successfully diagnosed ear diseases with an accuracy greater than 93%. All resident physicians were able to diagnose middle ear diseases more accurately with the help of the machine learning network. The increase in diagnostic accuracy was up to 18% (1.4% to 18.4%). The machine learning network successfully classified middle ear diseases and was assistive to clinicians in the interpretation of tympanic membrane images.

S220 – Characteristics of Fluid and Tympanometry Profiles in OME

2008 ◽  
Vol 139 (2_suppl) ◽  
pp. P149-P149
Author(s):  
Seung-Hwan Lee ◽  
Youngseok Lee ◽  
Yunjeong Kim ◽  
Bum-Suk Kim ◽  
Seung-Won Jeong ◽  
...  
Keyword(s):  
Statistical Analysis ◽  
Otitis Media ◽  
Middle Ear ◽  
Peak Pressure ◽  
Otitis Media With Effusion ◽  
Objective Measure ◽  
T Test ◽  
Type B ◽  
Middle Ear Fluid ◽  
Curve Maximum

Objectives The aim of this study was to compare the characteristics of the type B tympanogram curve (maximum admittance, tympanometric peak pressure) to the volume and viscosity of middle ear fluid. Methods We conducted preoperative tympanometry from 175 ears in 94 children with otitis media with effusion. The volume and viscosity of middle ear fluid collected during myringotomy were classified into 3 groups respectively. We analysed the correlations between the characteristcs of middle ear fluid and tympanometric profiles such as maximum admittance, tympanometric peak pressure. Student t test was used for statistical analysis. Results No correlation was found between peak pressure of the tympanogram and the characteristics of middle ear fluid. However, as the volume of middle ear fluid increases, the viscosity and the straight type B tympanogram increased significantly (p<0.001, p=0.002 respectively). And as the volume and the viscosity of the middle ear fluid increased, the Admmax significantly decreased (p<0.001). Conclusions Characteristics of type B tympanogram curve were correlated with the volume and viscosity of middle ear fluid. And it can be suggested that tympanometry may be used as an objective measure to estimate the characteristics of the middle ear fluid.

Determining Otitis Media Severity from Middle Ear Fluid Analysis

1994 ◽  
Vol 103 (5_suppl) ◽  
pp. 43-45 ◽  
Author(s):  
Steven K. Juhn ◽  
William J. Garvis ◽  
Chap T. Le ◽  
Chris J. Lees ◽  
C. S. Kim
Keyword(s):  
Otitis Media ◽  
Middle Ear ◽  
Otitis Media With Effusion ◽  
Chronic Otitis Media ◽  
Complex Nature ◽  
Fluid Analysis ◽  
Factor Α ◽  
Necrosis Factor ◽  
Ear Effusion ◽  
Chemical Mediators

Otitis media has a complex multifactorial pathogenesis, and the middle ear inflammatory response is typified by the accumulation of cellular and chemical mediators in middle ear effusion. However, specific biochemical and immunochemical factors that may be responsible for the severity or chronicity of otitis media have not been identified. Identification of factors involved in chronicity appears to be an essential step in the treatment and ultimate prevention of chronic otitis media. We analyzed 70 effusion samples from patients 1 to 10 years of age who had chronic otitis media with effusion for two cytokines (interleukrn-1β and tumor necrosis factor α) and total collagenase. The highest concentrations of all three inflammatory mediators were found in purulent otitis media, and concentrations were higher in younger than in older patients. Mediator concentrations were similar in samples obtained from patients having their first myringotomy for otitis media with effusion and in those who had had multiple previous myringotomies. The multiresponse star, which incorporates several biochemical parameters in one graphic illustration, may best characterize the complex nature of middle ear inflammation.

scholarly journals Nontypeable Haemophilus influenzae Gene Expression Induced In Vivo in a Chinchilla Model of Otitis Media

2003 ◽  
Vol 71 (6) ◽  
pp. 3454-3462 ◽  
Author(s):  
Kevin M. Mason ◽  
Robert S. Munson ◽  
Lauren O. Bakaletz
Keyword(s):  
Gene Expression ◽  
Haemophilus Influenzae ◽  
Otitis Media ◽  
Middle Ear ◽  
Fluorescent Protein ◽  
Otitis Media With Effusion ◽  
Acute Otitis Media ◽  
Bacterial Gene ◽  
Nthi Strain

ABSTRACT The gram-negative bacterium nontypeable Haemophilus influenzae (NTHI) is the predominant pathogen in chronic otitis media with effusion and, with Streptococcus pneumoniae and Moraxella catarrhalis, is a causative agent of acute otitis media. To identify potential virulence determinants, bacterial gene expression was monitored by differential fluorescence induction during early disease progression in one specific anatomical niche of a chinchilla model of NTHI-induced otitis media. Genomic DNA fragments from NTHI strain 86-028NP were cloned upstream of the promoterless gfpmut3 gene. NTHI strain 86-028NP served as the host for the promoter trap library. Pools of 2,000 transformants were inoculated into the left and right middle ear cavities of chinchillas. Middle ear effusions were recovered by epitympanic tap at 24 and 48 h, and clones containing promoter elements that were induced in vivo and producing green fluorescent protein were isolated by two-color fluorescence-activated cell sorting. Insert DNA was sequenced and compared to the complete genome sequence of H. influenzae strain Rd. In a screen of 16,000 clones, we have isolated 44 clones that contain unique gene fragments encoding biosynthetic enzymes, metabolic and regulatory proteins, and hypothetical proteins of unknown function. An additional eight clones contain gene fragments unique to our NTHI isolate. Using quantitative reverse transcription-PCR, we have confirmed that 26 clones demonstrated increased gene expression in vivo relative to expression in vitro. These data provide insight into the response of NTHI bacteria as they sense and respond to the middle ear microenvironment during early events of otitis media.

Effects of Platelet Activating Factor on the Tubotympanic Mucosa and Inner Ear in the Guinea Pig

1998 ◽  
Vol 107 (10) ◽  
pp. 876-884 ◽  
Author(s):  
Yoshiharu Ohno ◽  
Yoshihiro Ohashi ◽  
Hideki Okamoto ◽  
Yoshikazu Sugiura ◽  
Yoshiaki Nakai
Keyword(s):  
Hearing Loss ◽  
Sensorineural Hearing Loss ◽  
Inner Ear ◽  
Otitis Media ◽  
Middle Ear ◽  
Otitis Media With Effusion ◽  
Platelet Activating Factor ◽  
Sensorineural Hearing ◽  
Ciliary Activity ◽  
Middle Ear Mucosa

The effect of platelet activating factor (PAF) was studied to elucidate its role in the pathogenesis of otitis media and sensorineural hearing loss. The PAF alone did not induce a reduction of ciliary activity of the cultured middle ear mucosa. However, a dose-dependent decrease in ciliary activity was observed in the presence of the medium containing both PAF and macrophages. Intravenous injection of PAF did not induce dysfunction of the mucociliary system or morphologic changes of epithelium in the tubotympanum, but cytoplasmic vacuolization and ballooning were observed in the inner ear within 1 hour after injection of PAF. In contrast, intratympanic injection of PAF induced mucociliary dysfunction and some pathologic changes in the tubotympanum. Intratympanic inoculation of PAF induced no pathologic findings in the inner ear. These results suggest that PAF is at least partially involved in the pathogenesis of certain middle ear diseases such as otitis media with effusion. Additionally, PAF might be involved in the pathogenesis of some types of unexplained sensorineural hearing loss.

Sign in / Sign up

Export Citation Format

Share Document