Cargando…
Investigation of the best effective fold of data augmentation for training deep learning models for recognition of contiguity between mandibular third molar and inferior alveolar canal on panoramic radiographs
OBJECTIVES: This study aimed to train deep learning models for recognition of contiguity between the mandibular third molar (M3M) and inferior alveolar canal using panoramic radiographs and to investigate the best effective fold of data augmentation. MATERIALS AND METHODS: The total of 1800 M3M crop...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer Berlin Heidelberg
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10329615/ https://www.ncbi.nlm.nih.gov/pubmed/37043029 http://dx.doi.org/10.1007/s00784-023-04992-6 |
_version_ | 1785070056858714112 |
---|---|
author | Papasratorn, Dhanaporn Pornprasertsuk-Damrongsri, Suchaya Yuma, Suraphong Weerawanich, Warangkana |
author_facet | Papasratorn, Dhanaporn Pornprasertsuk-Damrongsri, Suchaya Yuma, Suraphong Weerawanich, Warangkana |
author_sort | Papasratorn, Dhanaporn |
collection | PubMed |
description | OBJECTIVES: This study aimed to train deep learning models for recognition of contiguity between the mandibular third molar (M3M) and inferior alveolar canal using panoramic radiographs and to investigate the best effective fold of data augmentation. MATERIALS AND METHODS: The total of 1800 M3M cropped images were classified evenly into contact and no-contact. The contact group was confirmed with CBCT images. The models were trained from three pretrained models: AlexNet, VGG-16, and GoogLeNet. Each pretrained model was trained with the original cropped panoramic radiographs. Then the training images were increased fivefold, tenfold, 15-fold, and 20-fold using data augmentation to train additional models. The area under the receiver operating characteristic curve (AUC) of the 15 models were evaluated. RESULTS: All models recognized contiguity with AUC from 0.951 to 0.996. Ten-fold augmentation showed the highest AUC in all pretrained models; however, no significant difference with other folds were found. VGG-16 showed the best performance among pretrained models trained at the same fold of augmentation. Data augmentation provided statistically significant improvement in performance of AlexNet and GoogLeNet models, while VGG-16 remained unchanged. CONCLUSIONS: Based on our images, all models performed efficiently with high AUC, particularly VGG-16. Ten-fold augmentation showed the highest AUC by all pretrained models. VGG-16 showed promising potential when training with only original images. CLINICAL RELEVANCE: Ten-fold augmentation may help improve deep learning models’ performances. The variety of original data and the accuracy of labels are essential to train a high-performance model. |
format | Online Article Text |
id | pubmed-10329615 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Springer Berlin Heidelberg |
record_format | MEDLINE/PubMed |
spelling | pubmed-103296152023-07-10 Investigation of the best effective fold of data augmentation for training deep learning models for recognition of contiguity between mandibular third molar and inferior alveolar canal on panoramic radiographs Papasratorn, Dhanaporn Pornprasertsuk-Damrongsri, Suchaya Yuma, Suraphong Weerawanich, Warangkana Clin Oral Investig Research OBJECTIVES: This study aimed to train deep learning models for recognition of contiguity between the mandibular third molar (M3M) and inferior alveolar canal using panoramic radiographs and to investigate the best effective fold of data augmentation. MATERIALS AND METHODS: The total of 1800 M3M cropped images were classified evenly into contact and no-contact. The contact group was confirmed with CBCT images. The models were trained from three pretrained models: AlexNet, VGG-16, and GoogLeNet. Each pretrained model was trained with the original cropped panoramic radiographs. Then the training images were increased fivefold, tenfold, 15-fold, and 20-fold using data augmentation to train additional models. The area under the receiver operating characteristic curve (AUC) of the 15 models were evaluated. RESULTS: All models recognized contiguity with AUC from 0.951 to 0.996. Ten-fold augmentation showed the highest AUC in all pretrained models; however, no significant difference with other folds were found. VGG-16 showed the best performance among pretrained models trained at the same fold of augmentation. Data augmentation provided statistically significant improvement in performance of AlexNet and GoogLeNet models, while VGG-16 remained unchanged. CONCLUSIONS: Based on our images, all models performed efficiently with high AUC, particularly VGG-16. Ten-fold augmentation showed the highest AUC by all pretrained models. VGG-16 showed promising potential when training with only original images. CLINICAL RELEVANCE: Ten-fold augmentation may help improve deep learning models’ performances. The variety of original data and the accuracy of labels are essential to train a high-performance model. Springer Berlin Heidelberg 2023-04-12 2023 /pmc/articles/PMC10329615/ /pubmed/37043029 http://dx.doi.org/10.1007/s00784-023-04992-6 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Research Papasratorn, Dhanaporn Pornprasertsuk-Damrongsri, Suchaya Yuma, Suraphong Weerawanich, Warangkana Investigation of the best effective fold of data augmentation for training deep learning models for recognition of contiguity between mandibular third molar and inferior alveolar canal on panoramic radiographs |
title | Investigation of the best effective fold of data augmentation for training deep learning models for recognition of contiguity between mandibular third molar and inferior alveolar canal on panoramic radiographs |
title_full | Investigation of the best effective fold of data augmentation for training deep learning models for recognition of contiguity between mandibular third molar and inferior alveolar canal on panoramic radiographs |
title_fullStr | Investigation of the best effective fold of data augmentation for training deep learning models for recognition of contiguity between mandibular third molar and inferior alveolar canal on panoramic radiographs |
title_full_unstemmed | Investigation of the best effective fold of data augmentation for training deep learning models for recognition of contiguity between mandibular third molar and inferior alveolar canal on panoramic radiographs |
title_short | Investigation of the best effective fold of data augmentation for training deep learning models for recognition of contiguity between mandibular third molar and inferior alveolar canal on panoramic radiographs |
title_sort | investigation of the best effective fold of data augmentation for training deep learning models for recognition of contiguity between mandibular third molar and inferior alveolar canal on panoramic radiographs |
topic | Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10329615/ https://www.ncbi.nlm.nih.gov/pubmed/37043029 http://dx.doi.org/10.1007/s00784-023-04992-6 |
work_keys_str_mv | AT papasratorndhanaporn investigationofthebesteffectivefoldofdataaugmentationfortrainingdeeplearningmodelsforrecognitionofcontiguitybetweenmandibularthirdmolarandinferioralveolarcanalonpanoramicradiographs AT pornprasertsukdamrongsrisuchaya investigationofthebesteffectivefoldofdataaugmentationfortrainingdeeplearningmodelsforrecognitionofcontiguitybetweenmandibularthirdmolarandinferioralveolarcanalonpanoramicradiographs AT yumasuraphong investigationofthebesteffectivefoldofdataaugmentationfortrainingdeeplearningmodelsforrecognitionofcontiguitybetweenmandibularthirdmolarandinferioralveolarcanalonpanoramicradiographs AT weerawanichwarangkana investigationofthebesteffectivefoldofdataaugmentationfortrainingdeeplearningmodelsforrecognitionofcontiguitybetweenmandibularthirdmolarandinferioralveolarcanalonpanoramicradiographs |