Publications
2023
M, Gillot; F, Miranda; B, Baquero; A, Ruellas; M, Gurgel; N, Al Turkestani; et al,
Automatic landmark identification in cone‐beam computed tomography. Journal Article
In: Orthod Craniofac Res, vol. 26, iss. 4, pp. 560-567, 2023.
Abstract | Links | BibTeX | Tags: anatomic landmarks, fiducial markers, machine learning
@article{Bianchi2023c,
title = {Automatic landmark identification in cone‐beam computed tomography. },
author = {Gillot M and Miranda F and Baquero B and Ruellas A and Gurgel M and Al Turkestani N and et al},
url = {https://pubmed.ncbi.nlm.nih.gov/36811276/},
doi = {10.1111/ocr.12642},
year = {2023},
date = {2023-11-26},
journal = {Orthod Craniofac Res},
volume = {26},
issue = {4},
pages = {560-567},
abstract = {Objective: To present and validate an open-source fully automated landmark placement (ALICBCT) tool for cone-beam computed tomography scans.
Materials and methods: One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position.
Results: Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU.
Conclusion: The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.},
keywords = {anatomic landmarks, fiducial markers, machine learning},
pubstate = {published},
tppubtype = {article}
}
Objective: To present and validate an open-source fully automated landmark placement (ALICBCT) tool for cone-beam computed tomography scans.
Materials and methods: One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position.
Results: Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU.
Conclusion: The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.
Materials and methods: One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position.
Results: Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU.
Conclusion: The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.
M, Gillot; F, Miranda; B, Baquero; A, Ruellas; M, Gurgel; N, Al Turkestani; et al,
Automatic landmark identification in cone‐beam computed tomography. Journal Article
In: Orthod Craniofac Res, vol. 26, iss. 4, pp. 560-567, 2023.
@article{Bianchi2023c,
title = {Automatic landmark identification in cone‐beam computed tomography. },
author = {Gillot M and Miranda F and Baquero B and Ruellas A and Gurgel M and Al Turkestani N and et al},
url = {https://pubmed.ncbi.nlm.nih.gov/36811276/},
doi = {10.1111/ocr.12642},
year = {2023},
date = {2023-11-26},
journal = {Orthod Craniofac Res},
volume = {26},
issue = {4},
pages = {560-567},
abstract = {Objective: To present and validate an open-source fully automated landmark placement (ALICBCT) tool for cone-beam computed tomography scans.
Materials and methods: One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position.
Results: Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU.
Conclusion: The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Objective: To present and validate an open-source fully automated landmark placement (ALICBCT) tool for cone-beam computed tomography scans.
Materials and methods: One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position.
Results: Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU.
Conclusion: The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.
Materials and methods: One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position.
Results: Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU.
Conclusion: The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.
2023 |
M, Gillot; F, Miranda; B, Baquero; A, Ruellas; M, Gurgel; N, Al Turkestani; et al,: Automatic landmark identification in cone‐beam computed tomography. . In: Orthod Craniofac Res, vol. 26, iss. 4, pp. 560-567, 2023. (Type: Journal Article | Abstract | Links | BibTeX | Tags: anatomic landmarks, fiducial markers, machine learning)@article{Bianchi2023c, Objective: To present and validate an open-source fully automated landmark placement (ALICBCT) tool for cone-beam computed tomography scans. Materials and methods: One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position. Results: Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU. Conclusion: The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision. |