Publications
2022
M, Leclercq; A, Ruellas; M, Gurgel; M, Yatabe; J, Bianchi; L, Cevidanes; et al,
Dentalmodelseg: Fully Automated Segmentation of Upper and Lower 3D Intra-Oral Surfaces. Journal Article
In: Semantic Scholar, 2022.
Abstract | Links | BibTeX | Tags: bone segmentation, Deep Learning, dental crown, intra-oral surface, Universal label id
@article{Bianchi2023i,
title = {Dentalmodelseg: Fully Automated Segmentation of Upper and Lower 3D Intra-Oral Surfaces.},
author = {Leclercq M and Ruellas A and Gurgel M and Yatabe M and Bianchi J and Cevidanes L and et al},
url = {https://www.semanticscholar.org/paper/FiboSeg%3A-Fully-automated-segmentation-of-upper-and-Leclercq-Ruellas/7269780afbd9c060e4509465f2b24d7fdbc35924},
year = {2022},
date = {2022-01-01},
journal = {Semantic Scholar},
abstract = {In this paper, we present a deep learning based method for surface segmentation. This technique consists of acquiring 2D views and extracting features from the surface such as the normal vectors. The rendered images are analyzed with a 2D convolutional neural network, such as UNETs. We test our method in a dental application for segmentation of dental crowns. The neural network is trained for the multi-class segmentation, using image labels as ground truth. The segmentation task achieved an average Dice of 0.97, sensitivity of 0.97 and precision of 0.97.},
keywords = {bone segmentation, Deep Learning, dental crown, intra-oral surface, Universal label id},
pubstate = {published},
tppubtype = {article}
}
2018
Oscar, C L; Jonas, B; Dirceu, R; Joao, B N; Bernd, H
Mandible and skull segmentation in cone-beam computed tomography using super-voxels and graph clustering Journal Article
In: The Visual Computer, vol. 35, pp. 1461-1474, 2018.
Abstract | Links | BibTeX | Tags: bone segmentation, Cone-beam computed tomography, graph clustering, mandible, skull, super-voxels
@article{Linares2018,
title = {Mandible and skull segmentation in cone-beam computed tomography using super-voxels and graph clustering},
author = {C L Oscar and B Jonas and R Dirceu and B N Joao and H Bernd },
url = {https://link.springer.com/article/10.1007/s00371-018-1511-0},
doi = {https://doi.org/10.1007/s00371-018-1511-0},
year = {2018},
date = {2018-04-26},
urldate = {2018-04-26},
journal = {The Visual Computer},
volume = {35},
pages = {1461-1474},
abstract = {Cone beam computed tomography (CBCT) is a medical imaging technique employed for diagnosis and treatment of patients with cranio-maxillofacial deformities. CBCT 3D reconstruction and segmentation of bones such as mandible or maxilla are essential procedures in surgical and orthodontic treatments. However, CBCT image processing may be impaired by features such as low contrast, inhomogeneity, noise and artifacts. Besides, values assigned to voxels are relative Hounsfield units unlike traditional computed tomography (CT). Such drawbacks render CBCT segmentation a difficult and time-consuming task, usually performed manually with tools designed for medical image processing. We present an interactive two-stage method for the segmentation of CBCT: (i) we first perform an automatic segmentation of bone structures with super-voxels, allowing a compact graph representation of the 3D data; (ii) next, a user-placed seed process guides a graph partitioning algorithm, splitting the extracted bones into mandible and skull. We have evaluated our segmentation method in three different scenarios and compared the results with ground truth data of the mandible and the skull. Results show that our method produces accurate segmentation and is robust to changes in parameters. We also compared our method with two similar segmentation strategy and showed that it produces more accurate segmentation. Finally, we evaluated our method for CT data of patients with deformed or missing bones and the segmentation was accurate for all data. The segmentation of a typical CBCT takes in average 5 min, which is faster than most techniques currently available.},
keywords = {bone segmentation, Cone-beam computed tomography, graph clustering, mandible, skull, super-voxels},
pubstate = {published},
tppubtype = {article}
}
M, Leclercq; A, Ruellas; M, Gurgel; M, Yatabe; J, Bianchi; L, Cevidanes; et al,
Dentalmodelseg: Fully Automated Segmentation of Upper and Lower 3D Intra-Oral Surfaces. Journal Article
In: Semantic Scholar, 2022.
@article{Bianchi2023i,
title = {Dentalmodelseg: Fully Automated Segmentation of Upper and Lower 3D Intra-Oral Surfaces.},
author = {Leclercq M and Ruellas A and Gurgel M and Yatabe M and Bianchi J and Cevidanes L and et al},
url = {https://www.semanticscholar.org/paper/FiboSeg%3A-Fully-automated-segmentation-of-upper-and-Leclercq-Ruellas/7269780afbd9c060e4509465f2b24d7fdbc35924},
year = {2022},
date = {2022-01-01},
journal = {Semantic Scholar},
abstract = {In this paper, we present a deep learning based method for surface segmentation. This technique consists of acquiring 2D views and extracting features from the surface such as the normal vectors. The rendered images are analyzed with a 2D convolutional neural network, such as UNETs. We test our method in a dental application for segmentation of dental crowns. The neural network is trained for the multi-class segmentation, using image labels as ground truth. The segmentation task achieved an average Dice of 0.97, sensitivity of 0.97 and precision of 0.97.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Oscar, C L; Jonas, B; Dirceu, R; Joao, B N; Bernd, H
Mandible and skull segmentation in cone-beam computed tomography using super-voxels and graph clustering Journal Article
In: The Visual Computer, vol. 35, pp. 1461-1474, 2018.
@article{Linares2018,
title = {Mandible and skull segmentation in cone-beam computed tomography using super-voxels and graph clustering},
author = {C L Oscar and B Jonas and R Dirceu and B N Joao and H Bernd },
url = {https://link.springer.com/article/10.1007/s00371-018-1511-0},
doi = {https://doi.org/10.1007/s00371-018-1511-0},
year = {2018},
date = {2018-04-26},
urldate = {2018-04-26},
journal = {The Visual Computer},
volume = {35},
pages = {1461-1474},
abstract = {Cone beam computed tomography (CBCT) is a medical imaging technique employed for diagnosis and treatment of patients with cranio-maxillofacial deformities. CBCT 3D reconstruction and segmentation of bones such as mandible or maxilla are essential procedures in surgical and orthodontic treatments. However, CBCT image processing may be impaired by features such as low contrast, inhomogeneity, noise and artifacts. Besides, values assigned to voxels are relative Hounsfield units unlike traditional computed tomography (CT). Such drawbacks render CBCT segmentation a difficult and time-consuming task, usually performed manually with tools designed for medical image processing. We present an interactive two-stage method for the segmentation of CBCT: (i) we first perform an automatic segmentation of bone structures with super-voxels, allowing a compact graph representation of the 3D data; (ii) next, a user-placed seed process guides a graph partitioning algorithm, splitting the extracted bones into mandible and skull. We have evaluated our segmentation method in three different scenarios and compared the results with ground truth data of the mandible and the skull. Results show that our method produces accurate segmentation and is robust to changes in parameters. We also compared our method with two similar segmentation strategy and showed that it produces more accurate segmentation. Finally, we evaluated our method for CT data of patients with deformed or missing bones and the segmentation was accurate for all data. The segmentation of a typical CBCT takes in average 5 min, which is faster than most techniques currently available.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2022 |
M, Leclercq; A, Ruellas; M, Gurgel; M, Yatabe; J, Bianchi; L, Cevidanes; et al,: Dentalmodelseg: Fully Automated Segmentation of Upper and Lower 3D Intra-Oral Surfaces.. In: Semantic Scholar, 2022. (Type: Journal Article | Abstract | Links | BibTeX | Tags: bone segmentation, Deep Learning, dental crown, intra-oral surface, Universal label id)@article{Bianchi2023i, In this paper, we present a deep learning based method for surface segmentation. This technique consists of acquiring 2D views and extracting features from the surface such as the normal vectors. The rendered images are analyzed with a 2D convolutional neural network, such as UNETs. We test our method in a dental application for segmentation of dental crowns. The neural network is trained for the multi-class segmentation, using image labels as ground truth. The segmentation task achieved an average Dice of 0.97, sensitivity of 0.97 and precision of 0.97. |
2018 |
Oscar, C L; Jonas, B; Dirceu, R; Joao, B N; Bernd, H: Mandible and skull segmentation in cone-beam computed tomography using super-voxels and graph clustering. In: The Visual Computer, vol. 35, pp. 1461-1474, 2018. (Type: Journal Article | Abstract | Links | BibTeX | Tags: bone segmentation, Cone-beam computed tomography, graph clustering, mandible, skull, super-voxels)@article{Linares2018, Cone beam computed tomography (CBCT) is a medical imaging technique employed for diagnosis and treatment of patients with cranio-maxillofacial deformities. CBCT 3D reconstruction and segmentation of bones such as mandible or maxilla are essential procedures in surgical and orthodontic treatments. However, CBCT image processing may be impaired by features such as low contrast, inhomogeneity, noise and artifacts. Besides, values assigned to voxels are relative Hounsfield units unlike traditional computed tomography (CT). Such drawbacks render CBCT segmentation a difficult and time-consuming task, usually performed manually with tools designed for medical image processing. We present an interactive two-stage method for the segmentation of CBCT: (i) we first perform an automatic segmentation of bone structures with super-voxels, allowing a compact graph representation of the 3D data; (ii) next, a user-placed seed process guides a graph partitioning algorithm, splitting the extracted bones into mandible and skull. We have evaluated our segmentation method in three different scenarios and compared the results with ground truth data of the mandible and the skull. Results show that our method produces accurate segmentation and is robust to changes in parameters. We also compared our method with two similar segmentation strategy and showed that it produces more accurate segmentation. Finally, we evaluated our method for CT data of patients with deformed or missing bones and the segmentation was accurate for all data. The segmentation of a typical CBCT takes in average 5 min, which is faster than most techniques currently available. |