Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net

Abstract The quality of cephalometric analysis depends on the accuracy of the delineating landmarks in orthodontic and maxillofacial surgery. Due to the extensive number of landmarks, each analysis costs orthodontists considerable time per patient, leading to fatigue and inter- and intra-observer va...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: In-Hwan Kim, Young-Gon Kim, Sungchul Kim, Jae-Woo Park, Namkug Kim
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/da86601e38c44724a513d0a20be5513c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:da86601e38c44724a513d0a20be5513c
record_format dspace
spelling oai:doaj.org-article:da86601e38c44724a513d0a20be5513c2021-12-02T18:03:31ZComparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net10.1038/s41598-021-87261-42045-2322https://doaj.org/article/da86601e38c44724a513d0a20be5513c2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87261-4https://doaj.org/toc/2045-2322Abstract The quality of cephalometric analysis depends on the accuracy of the delineating landmarks in orthodontic and maxillofacial surgery. Due to the extensive number of landmarks, each analysis costs orthodontists considerable time per patient, leading to fatigue and inter- and intra-observer variabilities. Therefore, we proposed a fully automated cephalometry analysis with a cascade convolutional neural net (CNN). One thousand cephalometric x-ray images (2 k × 3 k) pixel were used. The dataset was split into training, validation, and test sets as 8:1:1. The 43 landmarks from each image were identified by an expert orthodontist. To evaluate intra-observer variabilities, 28 images from the dataset were randomly selected and measured again by the same orthodontist. To improve accuracy, a cascade CNN consisting of two steps was used for transfer learning. In the first step, the regions of interest (ROIs) were predicted by RetinaNet. In the second step, U-Net detected the precise landmarks in the ROIs. The average error of ROI detection alone was 1.55 ± 2.17 mm. The model with the cascade CNN showed an average error of 0.79 ± 0.91 mm (paired t-test, p = 0.0015). The orthodontist’s average error of reproducibility was 0.80 ± 0.79 mm. An accurate and fully automated cephalometric analysis was successfully developed and evaluated.In-Hwan KimYoung-Gon KimSungchul KimJae-Woo ParkNamkug KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
In-Hwan Kim
Young-Gon Kim
Sungchul Kim
Jae-Woo Park
Namkug Kim
Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net
description Abstract The quality of cephalometric analysis depends on the accuracy of the delineating landmarks in orthodontic and maxillofacial surgery. Due to the extensive number of landmarks, each analysis costs orthodontists considerable time per patient, leading to fatigue and inter- and intra-observer variabilities. Therefore, we proposed a fully automated cephalometry analysis with a cascade convolutional neural net (CNN). One thousand cephalometric x-ray images (2 k × 3 k) pixel were used. The dataset was split into training, validation, and test sets as 8:1:1. The 43 landmarks from each image were identified by an expert orthodontist. To evaluate intra-observer variabilities, 28 images from the dataset were randomly selected and measured again by the same orthodontist. To improve accuracy, a cascade CNN consisting of two steps was used for transfer learning. In the first step, the regions of interest (ROIs) were predicted by RetinaNet. In the second step, U-Net detected the precise landmarks in the ROIs. The average error of ROI detection alone was 1.55 ± 2.17 mm. The model with the cascade CNN showed an average error of 0.79 ± 0.91 mm (paired t-test, p = 0.0015). The orthodontist’s average error of reproducibility was 0.80 ± 0.79 mm. An accurate and fully automated cephalometric analysis was successfully developed and evaluated.
format article
author In-Hwan Kim
Young-Gon Kim
Sungchul Kim
Jae-Woo Park
Namkug Kim
author_facet In-Hwan Kim
Young-Gon Kim
Sungchul Kim
Jae-Woo Park
Namkug Kim
author_sort In-Hwan Kim
title Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net
title_short Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net
title_full Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net
title_fullStr Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net
title_full_unstemmed Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net
title_sort comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/da86601e38c44724a513d0a20be5513c
work_keys_str_mv AT inhwankim comparingintraobservervariationandexternalvariationsofafullyautomatedcephalometricanalysiswithacascadeconvolutionalneuralnet
AT younggonkim comparingintraobservervariationandexternalvariationsofafullyautomatedcephalometricanalysiswithacascadeconvolutionalneuralnet
AT sungchulkim comparingintraobservervariationandexternalvariationsofafullyautomatedcephalometricanalysiswithacascadeconvolutionalneuralnet
AT jaewoopark comparingintraobservervariationandexternalvariationsofafullyautomatedcephalometricanalysiswithacascadeconvolutionalneuralnet
AT namkugkim comparingintraobservervariationandexternalvariationsofafullyautomatedcephalometricanalysiswithacascadeconvolutionalneuralnet
_version_ 1718378716858417152