Use of Convolutional Neural Networks in Smartphones for the Identification of Oral Diseases Using a Small Dataset
Image recognition and processing is a suitable tool in systems using machine learning methods. The addition of smartphones as complementary tools in the health area for diagnosis is a fact nowadays due to the advantages they present. Following the trend of providing tools for diagnosis, this researc...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Online |
| Language: | eng spa |
| Published: |
Universidad Pedagógica y Tecnológica de Colombia
2021
|
| Subjects: | |
| Online Access: | https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11846 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1801706090509893632 |
|---|---|
| author | Quintero-Rojas, Jormany González, Jesús David |
| author_facet | Quintero-Rojas, Jormany González, Jesús David |
| author_sort | Quintero-Rojas, Jormany |
| collection | OJS |
| description | Image recognition and processing is a suitable tool in systems using machine learning methods. The addition of smartphones as complementary tools in the health area for diagnosis is a fact nowadays due to the advantages they present. Following the trend of providing tools for diagnosis, this research aimed to develop a prototype mobile application for the identification of oral lesions, including potentially malignant lesions, based on convolutional neural networks, as early detection of indications of possible types of cancer in the oral cavity. A mobile application was developed for the Android operating system that implemented the TensorFlow library and the Mobilenet V2 convolutional neural network model. The training of the model was performed by transfer learning with a database of 500 images distributed in five classes for recognition (Leukoplakia, Herpes Simplex Virus Type 1, Aphthous stomatitis, Nicotinic stomatitis, and No lesion). The 80% of the images were used for training and 20% for validation. It was obtained that the application presented at least 80% precision in the recognition of four class. The f1-score and area under curve metrics were used to evaluate performance. The developed mobile application presented an acceptable performance with metrics higher than 75% for the recognition of three lesions, on the other hand, it yielded an unfavorable performance lower than 70% for identifying nicotinic stomatitis cases with the chosen dataset. |
| format | Online |
| id | oai:oai.revistas.uptc.edu.co:article-11846 |
| institution | Revista Facultad de Ingeniería |
| language | eng spa |
| publishDate | 2021 |
| publisher | Universidad Pedagógica y Tecnológica de Colombia |
| record_format | ojs |
| spelling | oai:oai.revistas.uptc.edu.co:article-118462021-07-13T02:22:08Z Use of Convolutional Neural Networks in Smartphones for the Identification of Oral Diseases Using a Small Dataset Uso de redes neuronales convolucionales en teléfonos inteligentes para la identificación de enfermedades bucales empleando un pequeño conjunto de datos Quintero-Rojas, Jormany González, Jesús David dentistry medical technology preventive medicine artificial intelligence machine learning oral diagnosis oral disease identification smartphone odontología tecnología médica medicina preventiva inteligencia artificial aprendizaje automático diagnóstico bucal identificación de enfermedades bucales teléfonos inteligentes Image recognition and processing is a suitable tool in systems using machine learning methods. The addition of smartphones as complementary tools in the health area for diagnosis is a fact nowadays due to the advantages they present. Following the trend of providing tools for diagnosis, this research aimed to develop a prototype mobile application for the identification of oral lesions, including potentially malignant lesions, based on convolutional neural networks, as early detection of indications of possible types of cancer in the oral cavity. A mobile application was developed for the Android operating system that implemented the TensorFlow library and the Mobilenet V2 convolutional neural network model. The training of the model was performed by transfer learning with a database of 500 images distributed in five classes for recognition (Leukoplakia, Herpes Simplex Virus Type 1, Aphthous stomatitis, Nicotinic stomatitis, and No lesion). The 80% of the images were used for training and 20% for validation. It was obtained that the application presented at least 80% precision in the recognition of four class. The f1-score and area under curve metrics were used to evaluate performance. The developed mobile application presented an acceptable performance with metrics higher than 75% for the recognition of three lesions, on the other hand, it yielded an unfavorable performance lower than 70% for identifying nicotinic stomatitis cases with the chosen dataset. El reconocimiento y procesamiento de imágenes es una herramienta adecuada en los sistemas que usan métodos de aprendizaje automático. La adición de teléfonos inteligentes como herramientas complementarias en el área de la salud para el diagnóstico es un hecho hoy en día por las ventajas que presentan. Siguiendo la tendencia de proporcionar herramientas para el diagnóstico, esta investigación tuvo como objetivo desarrollar una aplicación móvil prototipo para la identificación de lesiones bucales, incluyendo lesiones potencialmente malignas, basado en redes neuronales convolucionales, como la detección temprana de indicios de posibles tipos de cáncer en la cavidad bucal. Se desarrolló una aplicación móvil para el sistema operativo Android que implementó la librería de TensorFlow y el modelo de redes neuronales convolucionales Mobilenet V2. El entrenamiento del modelo se realizó por transferencia de aprendizaje con una base de datos de 500 imágenes distribuidas en cinco clases para el reconocimiento (Leucoplasia, Herpes Simple Virus Tipo 1, Estomatitis aftosa, Estomatitis nicotínica y Sin lesión). Se utilizó el 80% de las imágenes para el entrenamiento y el 20% para la validación. Se obtuvo que la aplicación presentó al menos 80% de exactitud en el reconocimiento de cuatro clases. Se usaron las métricas de f1-valor y área bajo la curva para evaluar el desempeño. La aplicación móvil desarrollada presentó un comportamiento aceptable con métricas mayores al 75% para el reconocimiento de tres lesiones, por otro lado, arrojó un desempeño desfavorable menor al 70% para identificar los casos de estomatitis nicotínica con el conjunto de datos elegido. Universidad Pedagógica y Tecnológica de Colombia 2021-02-07 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf application/pdf application/xml https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11846 10.19053/01211129.v30.n55.2021.11846 Revista Facultad de Ingeniería; Vol. 30 No. 55 (2021): January-March 2021 (Continuous Publication); e11846 Revista Facultad de Ingeniería; Vol. 30 Núm. 55 (2021): Enero-Marzo 2021 (Publicación Continua); e11846 2357-5328 0121-1129 eng spa https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11846/10233 https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11846/10234 https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11846/10785 Copyright (c) 2021 Jormany Quintero-Rojas, M.Sc., Jesús David González |
| spellingShingle | dentistry medical technology preventive medicine artificial intelligence machine learning oral diagnosis oral disease identification smartphone odontología tecnología médica medicina preventiva inteligencia artificial aprendizaje automático diagnóstico bucal identificación de enfermedades bucales teléfonos inteligentes Quintero-Rojas, Jormany González, Jesús David Use of Convolutional Neural Networks in Smartphones for the Identification of Oral Diseases Using a Small Dataset |
| title | Use of Convolutional Neural Networks in Smartphones for the Identification of Oral Diseases Using a Small Dataset |
| title_alt | Uso de redes neuronales convolucionales en teléfonos inteligentes para la identificación de enfermedades bucales empleando un pequeño conjunto de datos |
| title_full | Use of Convolutional Neural Networks in Smartphones for the Identification of Oral Diseases Using a Small Dataset |
| title_fullStr | Use of Convolutional Neural Networks in Smartphones for the Identification of Oral Diseases Using a Small Dataset |
| title_full_unstemmed | Use of Convolutional Neural Networks in Smartphones for the Identification of Oral Diseases Using a Small Dataset |
| title_short | Use of Convolutional Neural Networks in Smartphones for the Identification of Oral Diseases Using a Small Dataset |
| title_sort | use of convolutional neural networks in smartphones for the identification of oral diseases using a small dataset |
| topic | dentistry medical technology preventive medicine artificial intelligence machine learning oral diagnosis oral disease identification smartphone odontología tecnología médica medicina preventiva inteligencia artificial aprendizaje automático diagnóstico bucal identificación de enfermedades bucales teléfonos inteligentes |
| topic_facet | dentistry medical technology preventive medicine artificial intelligence machine learning oral diagnosis oral disease identification smartphone odontología tecnología médica medicina preventiva inteligencia artificial aprendizaje automático diagnóstico bucal identificación de enfermedades bucales teléfonos inteligentes |
| url | https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11846 |
| work_keys_str_mv | AT quinterorojasjormany useofconvolutionalneuralnetworksinsmartphonesfortheidentificationoforaldiseasesusingasmalldataset AT gonzalezjesusdavid useofconvolutionalneuralnetworksinsmartphonesfortheidentificationoforaldiseasesusingasmalldataset AT quinterorojasjormany usoderedesneuronalesconvolucionalesentelefonosinteligentesparalaidentificaciondeenfermedadesbucalesempleandounpequenoconjuntodedatos AT gonzalezjesusdavid usoderedesneuronalesconvolucionalesentelefonosinteligentesparalaidentificaciondeenfermedadesbucalesempleandounpequenoconjuntodedatos |
