Deep-learning-based segmentation of individual tooth and bone with periodontal ligament interface details for simulation purposes
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Deep-learning-based segmentation of individual tooth and bone with periodontal ligament interface details for simulation purposes. / Xu, Peidi; Gholamalizadeh, Torkan; Moshfeghifar, Faezeh; Darkner, Sune; Erleben, Kenny.
In: IEEE Access, Vol. 11, 2023, p. 102460-102470.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Deep-learning-based segmentation of individual tooth and bone with periodontal ligament interface details for simulation purposes
AU - Xu, Peidi
AU - Gholamalizadeh, Torkan
AU - Moshfeghifar, Faezeh
AU - Darkner, Sune
AU - Erleben, Kenny
N1 - Publisher Copyright: Author
PY - 2023
Y1 - 2023
N2 - The process of constructing precise geometry of human jaws from cone beam computed tomography (CBCT) scans is crucial for building finite element models and treatment planning. Despite the success of deep learning techniques, they struggle to accurately identify delicate features such as thin structures and gaps between the tooth-bone interfaces where periodontal ligament resides, especially when trained on limited data. Therefore, segmented geometries obtained through automated methods still require extensive manual adjustment to achieve a smooth and organic 3D geometry that is suitable for simulations. In this work, we require the model to provide anatomically correct segmentation of teeth and bones which preserves the space for the periodontal ligament layers. To accomplish the task with few accurate labels, we pre-train a modified MultiPlanar UNet as the backbone model using inferior segmentations, i.e., tooth-bone segmentation with no space in the tooth-bone interfaces, and fine-tune the model with a dedicated loss function over accurate delineations that considers the space. We demonstrate that our approach can produce proper tooth-bone segmentations with gap interfaces that are fit for simulations when applied to human jaw CBCT scans. Furthermore, we propose a marker-based watershed segmentation applied on the MultiPlanar UNet probability map to separate individual tooth. This has advantages when the segmentation task is challenged by common artifacts caused by restorative materials or similar intensities in the teeth-teeth interfaces in occurrence of crowded teeth phenomenon. Code and segmentation results are available at https://github.com/diku-dk/AutoJawSegment.
AB - The process of constructing precise geometry of human jaws from cone beam computed tomography (CBCT) scans is crucial for building finite element models and treatment planning. Despite the success of deep learning techniques, they struggle to accurately identify delicate features such as thin structures and gaps between the tooth-bone interfaces where periodontal ligament resides, especially when trained on limited data. Therefore, segmented geometries obtained through automated methods still require extensive manual adjustment to achieve a smooth and organic 3D geometry that is suitable for simulations. In this work, we require the model to provide anatomically correct segmentation of teeth and bones which preserves the space for the periodontal ligament layers. To accomplish the task with few accurate labels, we pre-train a modified MultiPlanar UNet as the backbone model using inferior segmentations, i.e., tooth-bone segmentation with no space in the tooth-bone interfaces, and fine-tune the model with a dedicated loss function over accurate delineations that considers the space. We demonstrate that our approach can produce proper tooth-bone segmentations with gap interfaces that are fit for simulations when applied to human jaw CBCT scans. Furthermore, we propose a marker-based watershed segmentation applied on the MultiPlanar UNet probability map to separate individual tooth. This has advantages when the segmentation task is challenged by common artifacts caused by restorative materials or similar intensities in the teeth-teeth interfaces in occurrence of crowded teeth phenomenon. Code and segmentation results are available at https://github.com/diku-dk/AutoJawSegment.
KW - Bones
KW - cone-beam computed tomography
KW - deep learning
KW - Finite element analysis
KW - finite element modeling
KW - Human factors
KW - human jaws
KW - Image segmentation
KW - instance segmentation
KW - learning with limited data
KW - Ligaments
KW - Pipelines
KW - Semantic segmentation
KW - semantic segmentation
KW - Solid modeling
KW - Three-dimensional displays
KW - transfer learning
KW - Watersheds
U2 - 10.1109/ACCESS.2023.3317512
DO - 10.1109/ACCESS.2023.3317512
M3 - Journal article
AN - SCOPUS:85173009456
VL - 11
SP - 102460
EP - 102470
JO - IEEE Access
JF - IEEE Access
SN - 2169-3536
ER -
ID: 369928148