Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016
Objective To apply deep learning to a data set of dental panoramic radiographs to detect the mental foramen for automatic assessment of the mandibular cortical width. Methods Data from the seventh survey of the Tromsø Study (Tromsø7) were used. The data set contained 5197 randomly chosen dental pano...
Published in: | Journal of International Medical Research |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
SAGE
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/28182 https://doi.org/10.1177/03000605221135147 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/28182 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/28182 2024-02-04T10:05:00+01:00 Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016 Edvardsen, Isak Paasche Teterina, Anna Johansen, Thomas Haugland Myhre, Jonas Nordhaug Godtliebsen, Fred Bolstad, Napat Limchaichana 2022-11-22 https://hdl.handle.net/10037/28182 https://doi.org/10.1177/03000605221135147 eng eng SAGE Teterina, A. (2024). Panoramic radiograph analyses for early detection of osteoporosis in the population of Northern Norway. (Doctoral thesis). https://hdl.handle.net/10037/32402 . Journal of International Medical Research Edvardsen, Teterina, Johansen, Myhre, Godtliebsen, Bolstad. Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016. Journal of International Medical Research. 2022;50(11) FRIDAID 2089683 doi:10.1177/03000605221135147 0300-0605 1473-2300 https://hdl.handle.net/10037/28182 Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) openAccess Copyright 2022 The Author(s) https://creativecommons.org/licenses/by-nc/4.0 Journal article Tidsskriftartikkel Peer reviewed publishedVersion 2022 ftunivtroemsoe https://doi.org/10.1177/03000605221135147 2024-01-11T00:08:07Z Objective To apply deep learning to a data set of dental panoramic radiographs to detect the mental foramen for automatic assessment of the mandibular cortical width. Methods Data from the seventh survey of the Tromsø Study (Tromsø7) were used. The data set contained 5197 randomly chosen dental panoramic radiographs. Four pretrained object detectors were tested. We randomly chose 80% of the data for training and 20% for testing. Models were trained using GeForce RTX 2080 Ti with 11 GB GPU memory (NVIDIA Corporation, Santa Clara, CA, USA). Python programming language version 3.7 was used for analysis. Results The EfficientDet-D0 model showed the highest average precision of 0.30. When the threshold to regard a prediction as correct (intersection over union) was set to 0.5, the average precision was 0.79. The RetinaNet model achieved the lowest average precision of 0.23, and the precision was 0.64 when the intersection over union was set to 0.5. The procedure to estimate mandibular cortical width showed acceptable results. Of 100 random images, the algorithm produced an output 93 times, 20 of which were not visually satisfactory. Conclusions EfficientDet-D0 effectively detected the mental foramen. Methods for estimating bone quality are important in radiology and require further development. Article in Journal/Newspaper Tromsø University of Tromsø: Munin Open Research Archive Tromsø Journal of International Medical Research 50 11 030006052211351 |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
description |
Objective To apply deep learning to a data set of dental panoramic radiographs to detect the mental foramen for automatic assessment of the mandibular cortical width. Methods Data from the seventh survey of the Tromsø Study (Tromsø7) were used. The data set contained 5197 randomly chosen dental panoramic radiographs. Four pretrained object detectors were tested. We randomly chose 80% of the data for training and 20% for testing. Models were trained using GeForce RTX 2080 Ti with 11 GB GPU memory (NVIDIA Corporation, Santa Clara, CA, USA). Python programming language version 3.7 was used for analysis. Results The EfficientDet-D0 model showed the highest average precision of 0.30. When the threshold to regard a prediction as correct (intersection over union) was set to 0.5, the average precision was 0.79. The RetinaNet model achieved the lowest average precision of 0.23, and the precision was 0.64 when the intersection over union was set to 0.5. The procedure to estimate mandibular cortical width showed acceptable results. Of 100 random images, the algorithm produced an output 93 times, 20 of which were not visually satisfactory. Conclusions EfficientDet-D0 effectively detected the mental foramen. Methods for estimating bone quality are important in radiology and require further development. |
format |
Article in Journal/Newspaper |
author |
Edvardsen, Isak Paasche Teterina, Anna Johansen, Thomas Haugland Myhre, Jonas Nordhaug Godtliebsen, Fred Bolstad, Napat Limchaichana |
spellingShingle |
Edvardsen, Isak Paasche Teterina, Anna Johansen, Thomas Haugland Myhre, Jonas Nordhaug Godtliebsen, Fred Bolstad, Napat Limchaichana Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016 |
author_facet |
Edvardsen, Isak Paasche Teterina, Anna Johansen, Thomas Haugland Myhre, Jonas Nordhaug Godtliebsen, Fred Bolstad, Napat Limchaichana |
author_sort |
Edvardsen, Isak Paasche |
title |
Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016 |
title_short |
Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016 |
title_full |
Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016 |
title_fullStr |
Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016 |
title_full_unstemmed |
Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016 |
title_sort |
automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the tromsø study (tromsø7) in 2015-2016 |
publisher |
SAGE |
publishDate |
2022 |
url |
https://hdl.handle.net/10037/28182 https://doi.org/10.1177/03000605221135147 |
geographic |
Tromsø |
geographic_facet |
Tromsø |
genre |
Tromsø |
genre_facet |
Tromsø |
op_relation |
Teterina, A. (2024). Panoramic radiograph analyses for early detection of osteoporosis in the population of Northern Norway. (Doctoral thesis). https://hdl.handle.net/10037/32402 . Journal of International Medical Research Edvardsen, Teterina, Johansen, Myhre, Godtliebsen, Bolstad. Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs: the seventh survey of the Tromsø Study (Tromsø7) in 2015-2016. Journal of International Medical Research. 2022;50(11) FRIDAID 2089683 doi:10.1177/03000605221135147 0300-0605 1473-2300 https://hdl.handle.net/10037/28182 |
op_rights |
Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) openAccess Copyright 2022 The Author(s) https://creativecommons.org/licenses/by-nc/4.0 |
op_doi |
https://doi.org/10.1177/03000605221135147 |
container_title |
Journal of International Medical Research |
container_volume |
50 |
container_issue |
11 |
container_start_page |
030006052211351 |
_version_ |
1789973868601933824 |