UDD Logo
CRIS - Current Research Information System
New user? Click here to register.Have you forgotten your password?
Communities & Collections
Research Outputs
Fundings & Projects
Researchers
Datasets
Statistics
  1. Home
  2. CRIS
  3. Publications
  4. Color Dependence Analysis in a CNN-Based Computer-Aided Diagnosis System for Middle and External Ear Diseases
Details

Color Dependence Analysis in a CNN-Based Computer-Aided Diagnosis System for Middle and External Ear Diseases

Journal
Diagnostics
ISSN
2075-4418
Date Issued
2022
Author(s)
Michelle Viscaino
Matias Talamilla
Juan Cristóbal Maass
Facultad de Medicina Clínica Alemana Universidad del Desarrollo  
Pablo Henríquez
Paul H. Délano
Cecilia Auat Cheein
Fernando Auat Cheein
Type
Resource Types::text::journal::journal article
Scopus ID
2-s2.0-85128704787
WoS ID
WOS:000785666100001
DOI
10.3390/diagnostics12040917
URL
https://investigadores.udd.cl/handle/123456789/5523
URL Institutional Repository
https://repositorio.udd.cl/handle/11447/8202
Abstract
<jats:p>Artificial intelligence-assisted otologic diagnosis has been of growing interest in the scientific community, where middle and external ear disorders are the most frequent diseases in daily ENT practice. There are some efforts focused on reducing medical errors and enhancing physician capabilities using conventional artificial vision systems. However, approaches with multispectral analysis have not yet been addressed. Tissues of the tympanic membrane possess optical properties that define their characteristics in specific light spectra. This work explores color wavelengths dependence in a model that classifies four middle and external ear conditions: normal, chronic otitis media, otitis media with effusion, and earwax plug. The model is constructed under a computer-aided diagnosis system that uses a convolutional neural network architecture. We trained several models using different single-channel images by taking each color wavelength separately. The results showed that a single green channel model achieves the best overall performance in terms of accuracy (92%), sensitivity (85%), specificity (95%), precision (86%), and F1-score (85%). Our findings can be a suitable alternative for artificial intelligence diagnosis systems compared to the 50% of overall misdiagnosis of a non-specialist physician.</jats:p>
Subjects
otoscopy

; 

analysis

; 

article

; 

artificial intelligence

; 

chronic otitis media

; 

color

; 

color dependence analysis

; 

computer assisted diagnosis

; 

convolutional neural network

; 

diagnostic accuracy

; 

diagnostic error

; 

diagnostic test accuracy study

; 

earwax plug

; 

external ear

; 

external ear disease

; 

false positive result

; 

human

; 

intermethod comparison

; 

k means clustering

; 

middle ear

; 

middle ear disease

; 

otoscopy

; 

physician

; 

predictive value

; 

principal component analysis

; 

retrospective study

; 

secretory otitis media

; 

sensitivity and specificity

; 

true positive rate
Logo Universidad de Desarrollo
Encuéntranos en:

Sede Santiago

Av. Plaza 680, Las Condes

Contacto|Mapa

Sede Concepción

Ainavillo 456, Concepción

Contacto|Mapa

Hosting & SupportLogo Scimago Lab

Built with DSpace-CRIS software - Extension maintained and optimized by 4science

  • Accessibility settings
  • Privacy policy
  • End User Agreement
  • Send Feedback
Repository logo COAR Notify