ID | 62257 |
FullText URL | |
Author |
Sukegawa, Shintaro
Dentistry and Pharmaceutical Sciences, Department of Oral Pathology and Medicine, Okayama University Graduate School of Medicine
ORCID
Kaken ID
publons
Yoshii, Kazumasa
Department of Intelligence Science and Engineering, Graduate School of Natural Science and Technology, Gifu University
Hara, Takeshi
Department of Intelligence Science and Engineering, Graduate School of Natural Science and Technology, Gifu University
Matsuyama, Tamamo
Department of Oral and Maxillofacial Surgery, Kagawa Prefectural Central Hospital
Yamashita, Katsusuke
Polytechnic Center Kagawa
Nakano, Keisuke
Dentistry and Pharmaceutical Sciences, Department of Oral Pathology and Medicine, Okayama University Graduate School of Medicine
ORCID
Kaken ID
publons
researchmap
Takabatake, Kiyofumi
Dentistry and Pharmaceutical Sciences, Department of Oral Pathology and Medicine, Okayama University Graduate School of Medicine
Kaken ID
publons
researchmap
Kawai, Hotaka
Dentistry and Pharmaceutical Sciences, Department of Oral Pathology and Medicine, Okayama University Graduate School of Medicine
Nagatsuka, Hitoshi
Dentistry and Pharmaceutical Sciences, Department of Oral Pathology and Medicine, Okayama University Graduate School of Medicine
Kaken ID
publons
researchmap
Furuki, Yoshihiko
Department of Oral and Maxillofacial Surgery, Kagawa Prefectural Central Hospital
|
Abstract | It is necessary to accurately identify dental implant brands and the stage of treatment to ensure efficient care. Thus, the purpose of this study was to use multi-task deep learning to investigate a classifier that categorizes implant brands and treatment stages from dental panoramic radiographic images. For objective labeling, 9767 dental implant images of 12 implant brands and treatment stages were obtained from the digital panoramic radiographs of patients who underwent procedures at Kagawa Prefectural Central Hospital, Japan, between 2005 and 2020. Five deep convolutional neural network (CNN) models (ResNet18, 34, 50, 101 and 152) were evaluated. The accuracy, precision, recall, specificity, F1 score, and area under the curve score were calculated for each CNN. We also compared the multi-task and single-task accuracies of brand classification and implant treatment stage classification. Our analysis revealed that the larger the number of parameters and the deeper the network, the better the performance for both classifications. Multi-tasking significantly improved brand classification on all performance indicators, except recall, and significantly improved all metrics in treatment phase classification. Using CNNs conferred high validity in the classification of dental implant brands and treatment stages. Furthermore, multi-task learning facilitated analysis accuracy.
|
Keywords | multi-task learning
deep learning
artificial intelligence
dental implant
classification
|
Published Date | 2021-05-30
|
Publication Title |
Biomolecules
|
Volume | volume11
|
Issue | issue6
|
Publisher | MDPI
|
Start Page | 815
|
ISSN | 2218-273X
|
Content Type |
Journal Article
|
language |
English
|
OAI-PMH Set |
岡山大学
|
Copyright Holders | © 2021 by the authors.
|
File Version | publisher
|
PubMed ID | |
NAID | |
DOI | |
Web of Science KeyUT | |
Related Url | isVersionOf https://doi.org/10.3390/biom11060815
|
License | https://creativecommons.org/licenses/by/4.0/
|