Cargando…

Detection of Abnormal Changes on the Dorsal Tongue Surface Using Deep Learning

Background and Objective: The tongue mucosa often changes due to various local and systemic diseases or conditions. This study aimed to investigate whether deep learning can help detect abnormal regions on the dorsal tongue surface in patients and healthy adults. Materials and Methods: The study col...

Descripción completa

Detalles Bibliográficos
Autores principales: Song, Ho-Jun, Park, Yeong-Joon, Jeong, Hie-Yong, Kim, Byung-Gook, Kim, Jae-Hyung, Im, Yeong-Gwan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10385577/
https://www.ncbi.nlm.nih.gov/pubmed/37512104
http://dx.doi.org/10.3390/medicina59071293
_version_ 1785081442178433024
author Song, Ho-Jun
Park, Yeong-Joon
Jeong, Hie-Yong
Kim, Byung-Gook
Kim, Jae-Hyung
Im, Yeong-Gwan
author_facet Song, Ho-Jun
Park, Yeong-Joon
Jeong, Hie-Yong
Kim, Byung-Gook
Kim, Jae-Hyung
Im, Yeong-Gwan
author_sort Song, Ho-Jun
collection PubMed
description Background and Objective: The tongue mucosa often changes due to various local and systemic diseases or conditions. This study aimed to investigate whether deep learning can help detect abnormal regions on the dorsal tongue surface in patients and healthy adults. Materials and Methods: The study collected 175 clinical photographic images of the dorsal tongue surface, which were divided into 7782 cropped images classified into normal, abnormal, and non-tongue regions and trained using the VGG16 deep learning model. The 80 photographic images of the entire dorsal tongue surface were used for the segmentation of abnormal regions using point mapping segmentation. Results: The F1-scores of the abnormal and normal classes were 0.960 (precision: 0.935, recall: 0.986) and 0.968 (precision: 0.987, recall: 0.950), respectively, in the prediction of the VGG16 model. As a result of evaluation using point mapping segmentation, the average F1-scores were 0.727 (precision: 0.717, recall: 0.737) and 0.645 (precision: 0.650, recall: 0.641), the average intersection of union was 0.695 and 0.590, and the average precision was 0.940 and 0.890, respectively, for abnormal and normal classes. Conclusions: The deep learning algorithm used in this study can accurately determine abnormal areas on the dorsal tongue surface, which can assist in diagnosing specific diseases or conditions of the tongue mucosa.
format Online
Article
Text
id pubmed-10385577
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-103855772023-07-30 Detection of Abnormal Changes on the Dorsal Tongue Surface Using Deep Learning Song, Ho-Jun Park, Yeong-Joon Jeong, Hie-Yong Kim, Byung-Gook Kim, Jae-Hyung Im, Yeong-Gwan Medicina (Kaunas) Article Background and Objective: The tongue mucosa often changes due to various local and systemic diseases or conditions. This study aimed to investigate whether deep learning can help detect abnormal regions on the dorsal tongue surface in patients and healthy adults. Materials and Methods: The study collected 175 clinical photographic images of the dorsal tongue surface, which were divided into 7782 cropped images classified into normal, abnormal, and non-tongue regions and trained using the VGG16 deep learning model. The 80 photographic images of the entire dorsal tongue surface were used for the segmentation of abnormal regions using point mapping segmentation. Results: The F1-scores of the abnormal and normal classes were 0.960 (precision: 0.935, recall: 0.986) and 0.968 (precision: 0.987, recall: 0.950), respectively, in the prediction of the VGG16 model. As a result of evaluation using point mapping segmentation, the average F1-scores were 0.727 (precision: 0.717, recall: 0.737) and 0.645 (precision: 0.650, recall: 0.641), the average intersection of union was 0.695 and 0.590, and the average precision was 0.940 and 0.890, respectively, for abnormal and normal classes. Conclusions: The deep learning algorithm used in this study can accurately determine abnormal areas on the dorsal tongue surface, which can assist in diagnosing specific diseases or conditions of the tongue mucosa. MDPI 2023-07-13 /pmc/articles/PMC10385577/ /pubmed/37512104 http://dx.doi.org/10.3390/medicina59071293 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Song, Ho-Jun
Park, Yeong-Joon
Jeong, Hie-Yong
Kim, Byung-Gook
Kim, Jae-Hyung
Im, Yeong-Gwan
Detection of Abnormal Changes on the Dorsal Tongue Surface Using Deep Learning
title Detection of Abnormal Changes on the Dorsal Tongue Surface Using Deep Learning
title_full Detection of Abnormal Changes on the Dorsal Tongue Surface Using Deep Learning
title_fullStr Detection of Abnormal Changes on the Dorsal Tongue Surface Using Deep Learning
title_full_unstemmed Detection of Abnormal Changes on the Dorsal Tongue Surface Using Deep Learning
title_short Detection of Abnormal Changes on the Dorsal Tongue Surface Using Deep Learning
title_sort detection of abnormal changes on the dorsal tongue surface using deep learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10385577/
https://www.ncbi.nlm.nih.gov/pubmed/37512104
http://dx.doi.org/10.3390/medicina59071293
work_keys_str_mv AT songhojun detectionofabnormalchangesonthedorsaltonguesurfaceusingdeeplearning
AT parkyeongjoon detectionofabnormalchangesonthedorsaltonguesurfaceusingdeeplearning
AT jeonghieyong detectionofabnormalchangesonthedorsaltonguesurfaceusingdeeplearning
AT kimbyunggook detectionofabnormalchangesonthedorsaltonguesurfaceusingdeeplearning
AT kimjaehyung detectionofabnormalchangesonthedorsaltonguesurfaceusingdeeplearning
AT imyeonggwan detectionofabnormalchangesonthedorsaltonguesurfaceusingdeeplearning