Cargando…

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

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 u...

Descripción completa

Detalles Bibliográficos
Autores principales: Viscaino, Michelle, Talamilla, Matias, Maass, Juan Cristóbal, Henríquez, Pablo, Délano, Paul H., Auat Cheein, Cecilia, Auat Cheein, Fernando
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9031192/
https://www.ncbi.nlm.nih.gov/pubmed/35453965
http://dx.doi.org/10.3390/diagnostics12040917
Descripción
Sumario: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.