Verification of Convolutional Neural Network Cephalometric Landmark Identification
Introduction: The mass-harvesting of digitized medical data has prompted their use as a clinical and research tool. The purpose of this study was to compare the accuracy and reliability of artificial intelligence derived cephalometric landmark identification with that of human observers. Methods: Te...
Published in: | Applied Sciences |
---|---|
Main Authors: | , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/app122412784 |
id |
ftmdpi:oai:mdpi.com:/2076-3417/12/24/12784/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2076-3417/12/24/12784/ 2023-08-20T04:09:05+02:00 Verification of Convolutional Neural Network Cephalometric Landmark Identification Moshe Davidovitch Tatiana Sella-Tunis Liat Abramovicz Shoshana Reiter Shlomo Matalon Nir Shpack agris 2022-12-13 application/pdf https://doi.org/10.3390/app122412784 EN eng Multidisciplinary Digital Publishing Institute Applied Dentistry and Oral Sciences https://dx.doi.org/10.3390/app122412784 https://creativecommons.org/licenses/by/4.0/ Applied Sciences; Volume 12; Issue 24; Pages: 12784 artificial intelligence convolutional neural networks lateral cephalometric radiographs diagnostics Text 2022 ftmdpi https://doi.org/10.3390/app122412784 2023-08-01T07:46:44Z Introduction: The mass-harvesting of digitized medical data has prompted their use as a clinical and research tool. The purpose of this study was to compare the accuracy and reliability of artificial intelligence derived cephalometric landmark identification with that of human observers. Methods: Ten pre-treatment digital lateral cephalometric radiographs were randomly selected from a university post-graduate clinic. The x- and y-coordinates of 21 (i.e., 42 points) hard and soft tissue landmarks were identified by 6 specialists, 19 residents, 4 imaging technicians, and a commercially available convolutional neural network artificial intelligence platform (CephX, Orca Dental, Hertzylia, Israel). Wilcoxon, Spearman and Bartlett tests were performed to compare agreement of human and AI landmark identification. Results: Six x- or y-coordinates (14.28%) were found to be statistically different, with only one being outside the 2 mm range of acceptable error, and with 97.6% of coordinates found to be within this range. Conclusions: The use of convolutional neural network artificial intelligence as a tool for cephalometric landmark identification was found to be highly accurate and can serve as an aid in orthodontic diagnosis. Text Orca MDPI Open Access Publishing Applied Sciences 12 24 12784 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
artificial intelligence convolutional neural networks lateral cephalometric radiographs diagnostics |
spellingShingle |
artificial intelligence convolutional neural networks lateral cephalometric radiographs diagnostics Moshe Davidovitch Tatiana Sella-Tunis Liat Abramovicz Shoshana Reiter Shlomo Matalon Nir Shpack Verification of Convolutional Neural Network Cephalometric Landmark Identification |
topic_facet |
artificial intelligence convolutional neural networks lateral cephalometric radiographs diagnostics |
description |
Introduction: The mass-harvesting of digitized medical data has prompted their use as a clinical and research tool. The purpose of this study was to compare the accuracy and reliability of artificial intelligence derived cephalometric landmark identification with that of human observers. Methods: Ten pre-treatment digital lateral cephalometric radiographs were randomly selected from a university post-graduate clinic. The x- and y-coordinates of 21 (i.e., 42 points) hard and soft tissue landmarks were identified by 6 specialists, 19 residents, 4 imaging technicians, and a commercially available convolutional neural network artificial intelligence platform (CephX, Orca Dental, Hertzylia, Israel). Wilcoxon, Spearman and Bartlett tests were performed to compare agreement of human and AI landmark identification. Results: Six x- or y-coordinates (14.28%) were found to be statistically different, with only one being outside the 2 mm range of acceptable error, and with 97.6% of coordinates found to be within this range. Conclusions: The use of convolutional neural network artificial intelligence as a tool for cephalometric landmark identification was found to be highly accurate and can serve as an aid in orthodontic diagnosis. |
format |
Text |
author |
Moshe Davidovitch Tatiana Sella-Tunis Liat Abramovicz Shoshana Reiter Shlomo Matalon Nir Shpack |
author_facet |
Moshe Davidovitch Tatiana Sella-Tunis Liat Abramovicz Shoshana Reiter Shlomo Matalon Nir Shpack |
author_sort |
Moshe Davidovitch |
title |
Verification of Convolutional Neural Network Cephalometric Landmark Identification |
title_short |
Verification of Convolutional Neural Network Cephalometric Landmark Identification |
title_full |
Verification of Convolutional Neural Network Cephalometric Landmark Identification |
title_fullStr |
Verification of Convolutional Neural Network Cephalometric Landmark Identification |
title_full_unstemmed |
Verification of Convolutional Neural Network Cephalometric Landmark Identification |
title_sort |
verification of convolutional neural network cephalometric landmark identification |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2022 |
url |
https://doi.org/10.3390/app122412784 |
op_coverage |
agris |
genre |
Orca |
genre_facet |
Orca |
op_source |
Applied Sciences; Volume 12; Issue 24; Pages: 12784 |
op_relation |
Applied Dentistry and Oral Sciences https://dx.doi.org/10.3390/app122412784 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/app122412784 |
container_title |
Applied Sciences |
container_volume |
12 |
container_issue |
24 |
container_start_page |
12784 |
_version_ |
1774721800375107584 |