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 ◽  
...  

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.

1986 ◽  
Vol 95 (5) ◽  
pp. 472-476 ◽  
Author(s):  
Christine A. Avery ◽  
George A. Gates ◽  
Thomas J. Prihoda

The acoustic otoscope measures the amount of sound reflected from the tympanic membrane. Since the amount of reflected sound is increased by fluid in the middle ear, it seemed likely that the acoustic otoscope could be used for detection of otitis media. We compared acoustic reflectometry with over 4,000 tympanometric and otoscopic examinations in 451 children who were examined at regular intervals following surgery for chronic otitis media with effusion. The data indicate a lower sensitivity and specificity of acoustic reflectometry than had been reported previously. The receiver-operator characteristics of this device are discussed.


PEDIATRICS ◽  
1983 ◽  
Vol 71 (4) ◽  
pp. 639-652
Author(s):  
Charles D. Bluestone ◽  
Jerome O. Klein ◽  
Jack L. Paradise ◽  
Heinz Eichenwald ◽  
Fred H. Bess ◽  
...  

GOALS, DEFINITIONS, AND CLASSIFICATION OF OTITIS MEDIA —Charles D. Bluestone, MD The goal of this Workshop was to assess current knowledge concerning the effects of otitis media on the child. Experts in pediatrics, infectious disease, otolaryngology, audiology, speech, linguistics, and psychology met in Chicago on Aug 25, 1982 to participate in this Workshop. A summary of the discussions is presented here. Otitis media is broadly defined as an inflammation of the middle ear without reference to etiology or pathogenesis.1 Otitis media with effusion is an inflammation of the middle ear in which a collection of liquid (i.e., middle ear effusion) is present in the middle ear space (no perforation of the tympanic membrane is present). Atelectasis of the tympanic membrane, which may or may not be associated with otitis media, is defined as either collapse or retraction of the tympanic membrane. Acute otitis media implies a rapid and short onset of signs and symptoms lasting approximately 3 weeks. From 3 weeks to 3 months, the process may be resolving or subacute. If middle ear effusion persists beyond 3 months, the condition is classified as chronic otitis media with effusion. Many terms have been used for acute otitis media, such as "suppurative," "purulent," or "bacterial" otitis media; however, a "serous" effusion may also have an acute onset. Otitis media with effusion unaccompanied by signs and symptoms of acute inflammation has also had a plethora of other names: "serous," "secretory," "nonsuppurative," and "glue ear" have been the most commonly used. EPIDEMIOLOGY AND NATURAL HISTORY OF OTITIS MEDIA


1994 ◽  
Vol 103 (5_suppl) ◽  
pp. 27-30 ◽  
Author(s):  
Sam Levine ◽  
Kathleen Daly ◽  
G. Scott Giebink

Tympanoplasty and tympanostomy tubes were developed at the same time and have dramatically changed the treatment of chronic middle ear disease. One hundred forty-nine children who had tubes inserted between ages 6 months and 8 years for chronic otitis media with effusion have been prospectively followed up for an average of 4 years. Fourteen percent developed tympanic membrane perforations. No preoperative factor completely predicted the development of perforation. a majority of the perforations closed spontaneously. Three ears had noncontiguous observations of perforations during follow-up. The implications of these findings are discussed with respect to tympanoplasty.


2010 ◽  
Vol 124 (9) ◽  
pp. 945-949 ◽  
Author(s):  
A Daudia ◽  
S Yelavich ◽  
P J D Dawes

AbstractObjective:Long-term tympanostomy tubes are associated with a significant rate of complications, particularly persistent perforation. We describe the outcomes of 57 subannular ventilation tube insertions in 45 consecutive patients.Design:Retrospective case series.Subjects:We studied 45 consecutive patients with chronic otitis media with effusion and hearing loss (n = 54 cases), associated with adhesive otitis media (n = 7), tympanic membrane retraction (n = 17) and tympanic membrane perforation (n = 3). The mean follow up was 48 months (range, nine to 95 months).Results:The mean duration of ventilation for tubes still in situ was 22 months (range, one to 76 months; n = 29), and for tubes which extruded or were removed 23 months (range, one to 85 months; n = 28). The mean improvement in air–bone gap was 14 dB (range, −14 to 35 dB). Complications included blockage (16 per cent), perforation after extrusion (9 per cent), granulation (5 per cent) and infection (4 per cent).Conclusion:Subannular ventilation tubes provide an effective option for management of intractable middle-ear effusion and eustachian tube dysfunction.


2021 ◽  
pp. 014556132110581
Author(s):  
Yuan-Jun Liu ◽  
Lin Han ◽  
Jie Cao ◽  
Hong-Wei Zheng ◽  
Li-Sheng Yu

Primary ectopic meningioma of the middle ear is relatively rare in clinical practice. It is often difficult to distinguish it from chronic otitis media or otitis media with effusion due to its similar and atypical clinical symptoms. We report a case of epithelial tympanic ectopic meningioma with the main complaints of otalgia, aural fullness, and hearing loss. It was accidentally discovered during tympanotomy due to the symptoms of recurring refractory secretory otitis media. This article briefly reviews the relevant literature in recent years, summarizes the characteristics of primary ectopic tympanic meningioma with intact tympanic membrane, and emphasizes the diagnosis and treatment strategy of the middle ear mass.


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

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.


2001 ◽  
Vol 58 (1) ◽  
pp. 59-64 ◽  
Author(s):  
Linda Brodsky ◽  
Steve Cook ◽  
Ellen Deutsch ◽  
Patrick Brookhouser ◽  
Charles Bower ◽  
...  

1989 ◽  
Vol 103 (4) ◽  
pp. 369-371 ◽  
Author(s):  
C. Diamond ◽  
P. R. Sisson ◽  
A. M. Kearns ◽  
H. R. Ingham

AbstractSamples of middle ear effusions from 102 children with serous and mucoid otitis media were cultured for mycoplasmas and bacteria. No sample yielded mycoplasmas but bacteria were cultured from 48 (47 per cent). Organisms commonly regarded as pathogens were present in 25 samples (Haemophilus influenzae 17, Streptococcus pneumoniae four, other streptococci four). The only sample from which anaerobic bacteria were isolated was from a patient with cholesteatoma.


Pathogens ◽  
2020 ◽  
Vol 9 (3) ◽  
pp. 224 ◽  
Author(s):  
Nicola Malagutti ◽  
John Charles Rotondo ◽  
Luca Cerritelli ◽  
Claudio Melchiorri ◽  
Monica De Mattei ◽  
...  

Background. Previous studies reported human papillomaviruses (HPVs) in middle ear tumors, whereas these viruses have been poorly investigated in chronic inflammatory middle ear diseases. We investigated HPVs in non-tumor middle ear diseases, including chronic otitis media (COM). Methods. COM specimens (n = 52), including chronic suppurative otitis media (CSOM) (n =38) and cholesteatoma (COMC) (n = 14), as well as normal middle ear (NME) specimens (n = 56) were analyzed. HPV sequences and DNA loads were analyzed by quantitative-PCR. HPV genotyping was performed by direct sequencing. Results. HPV DNA was detected in 23% (12/52) of COM and in 30.4% (17/56) of NME (p > 0.05). Specifically, HPV DNA sequences were found in 26.3% (10/38) of CSOM and in 14.3% (2/14) of COMC (p > 0.05). Interestingly, the HPV DNA load was higher in COMC (mean 7.47 copy/cell) than in CSOM (mean 1.02 copy/cell) and NME (mean 1.18 copy/cell) (P = 0.03 and P = 0.017 versus CSOM and NME, respectively). HPV16 and HPV18 were the main genotypes detected in COMC, CSOM and NME. Conclusions. These data suggest that HPV may infect the middle ear mucosa, whereas HPV-positive COMCs are associated with higher viral DNA loads as compared to NME.


Sign in / Sign up

Export Citation Format

Share Document