Automatic landmark annotation in 3D surface scans of skulls: Methodological proposal and reliability study

Bermejo, Enrique; Taniguchi, Kei; Ogawa, Yoshinori; Martos, Rubén; Valsecchi, Andrea; Mesejo, Pablo; Ibáñez, Óscar; Imaizumi, Kazunori

doi:10.1016/j.cmpb.2021.106380

Cited by 24 publications

(26 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Both yielded promising results for deep learning (DL)-based methods, which outperformed previously proposed knowledge-based, atlas-based, or shallow learning-based methods. DL methods published in the past few years can localize 3D cephalometric landmarks with great accuracy, often under the 2-mm threshold of clinical acceptability (Lee et al 2019;Torosdagli et al 2019;Lang et al 2020;Ma et al 2020;Yun et al 2020;Zhang et al 2020;Bermejo et al 2021;Chen et al 2021;Kang et al 2021;Liu et al 2021;Chen et al 2022). The studies showing the best results usually formulate landmark detection as a regression problem, using landmark heatmap regression methods (Zhang et al 2020;Chen et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Automatic 3-Dimensional Cephalometric Landmarking via Deep Learning

et al. 2022

View full text Add to dashboard Cite

The increasing use of 3-dimensional (3D) imaging by orthodontists and maxillofacial surgeons to assess complex dentofacial deformities and plan orthognathic surgeries implies a critical need for 3D cephalometric analysis. Although promising methods were suggested to localize 3D landmarks automatically, concerns about robustness and generalizability restrain their clinical use. Consequently, highly trained operators remain needed to perform manual landmarking. In this retrospective diagnostic study, we aimed to train and evaluate a deep learning (DL) pipeline based on SpatialConfiguration-Net for automatic localization of 3D cephalometric landmarks on computed tomography (CT) scans. A retrospective sample of consecutive presurgical CT scans was randomly distributed between a training/validation set ( n = 160) and a test set ( n = 38). The reference data consisted of 33 landmarks, manually localized once by 1 operator( n = 178) or twice by 3 operators ( n = 20, test set only). After inference on the test set, 1 CT scan showed “very low” confidence level predictions; we excluded it from the overall analysis but still assessed and discussed the corresponding results. The model performance was evaluated by comparing the predictions with the reference data; the outcome set included localization accuracy, cephalometric measurements, and comparison to manual landmarking reproducibility. On the hold-out test set, the mean localization error was 1.0 ± 1.3 mm, while success detection rates for 2.0, 2.5, and 3.0 mm were 90.4%, 93.6%, and 95.4%, respectively. Mean errors were −0.3 ± 1.3° and −0.1 ± 0.7 mm for angular and linear measurements, respectively. When compared to manual reproducibility, the measurements were within the Bland–Altman 95% limits of agreement for 91.9% and 71.8% of skeletal and dentoalveolar variables, respectively. To conclude, while our DL method still requires improvement, it provided highly accurate 3D landmark localization on a challenging test set, with a reliability for skeletal evaluation on par with what clinicians obtain.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic 3-Dimensional Cephalometric Landmarking via Deep Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This procedure can potentially be improved by other novel methods or deep learning methods in terms of precision and efficiency. [37][38][39] Fourth, the slice resolution of CT image in this study was limited to 5 mm due to clinical protocol. A finer thickness (<3 mm) will result in better registration accuracy, where the improvement is marginal with 1 mm according to previous reports.…”

Section: Discussionmentioning

confidence: 99%

The application of multiple metrics in deformable image registration for target volume delineation of breast tumor bed

Xie

Song

et al. 2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

Background and purpose For postoperative breast cancer patients, deformable image registration (DIR) is challenged due to the large deformations and non‐correspondence caused by tumor resection and clip insertion. To deal with it, three metrics (fiducial‐, region‐, and intensity‐based) were jointly used in DIR algorithm for improved accuracy. Materials and methods Three types of metrics were combined to form a single‐objective function in DIR algorithm. Fiducial‐based metric was used to minimize the distance between the corresponding point sets of two images. Region‐based metric was used to improve the overlap between the corresponding areas of two images. Intensity‐based metric was used to maximize the correlation between the corresponding voxel intensities of two images. The two CT images, one before surgery and the other after surgery, were acquired from the same patient in the same radiotherapy treatment position. Twenty patients who underwent breast‐conserving surgery and postoperative radiotherapy were enrolled in this study. Results For target registration error, the difference between the proposed and the conventional registration methods was statistically significant for soft tissue (2.06 vs. 7.82, p = 0.00024 < 0.05) and body boundary (3.70 vs. 6.93, p = 0.021 < 0.05). For visual assessment, the proposed method achieved better matching result for soft tissue and body boundary. Conclusions Comparing to the conventional method, the registration accuracy of the proposed method was significantly improved. This method provided a feasible way for target volume delineation of tumor bed in postoperative radiotherapy of breast cancer patients.

show abstract

“…Both yielded promising results for deep learning (DL) based methods, which outperformed previously proposed knowledge-based, atlas-based or shallow learning-based methods. DL methods published in the last few years can localize 3D cephalometric landmarks with great accuracy, often under the 2-mm threshold of clinical acceptability (Lee et al 2019; O’Neil et al 2019; Torosdagli et al 2019; Lang et al 2020; Ma et al 2020; Yun et al 2020; Zhang et al 2020; Bermejo et al 2021; Chen et al 2021; Kang et al 2021; Liu et al 2021; Chen et al 2022). The studies showing the best results usually formulate landmark detection as a regression problem, using landmark heatmap regression methods (Zhang et al 2020; Chen et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Automatic Three-Dimensional Cephalometric Landmarking via Deep Learning

Dot

Schouman

Chang

et al. 2022

Preprint

View full text Add to dashboard Cite

The increasing use of three-dimensional (3D) imaging by orthodontists and maxillofacial surgeons to assess complex dentofacial deformities and plan orthognathic surgeries implies a critical need for 3D cephalometric analysis. Although promising methods were suggested to localize 3D landmarks automatically, concerns about robustness and generalizability restrain their clinical use. Consequently, highly trained operators remain needed to perform tedious manual landmarking. In this study, we aimed to train and evaluate a deep learning (DL) pipeline based on SpatialConfiguration-Net for automatic localization of 3D cephalometric landmarks on computed tomography (CT) scans. A retrospective sample of consecutive presurgical CT scans was randomly distributed between a training/validation set (n = 160) and a test set (n = 38). The reference data consisted in 33 landmarks, manually localized once by 1 operator (n = 178) or twice by 3 operators (n = 20, test set only). After inference on the test set, one CT scan showed "very low" confidence level predictions; we excluded it from the overall analysis but still assessed and discussed the corresponding results. The model performance was evaluated by comparing the predictions with the reference data; the outcome set included localization accuracy, cephalometric measurements and comparison to manual landmarking reproducibility. On the hold-out test set, the mean localization error was 1.0 ± 1.3mm, while success detection rates for 2.0, 2.5 and 3.0mm were 90.4%, 93.6% and 95.4%, respectively. Mean errors were -0.3 ± 1.3° and -0.1 ± 0.7mm for angular and linear measurements, respectively. When compared to manual reproducibility, the measurements were within the Bland-Altman 95% limits of agreement for 91.9% and 71.8% of skeletal and dentoalveolar variables, respectively. To conclude, while our DL method still requires improvement, it provided highly accurate 3D landmark localization on a challenging test set, with a reliability for skeletal evaluation on par with what clinicians obtain.

show abstract

Automatic landmark annotation in 3D surface scans of skulls: Methodological proposal and reliability study

Cited by 24 publications

References 38 publications

Automatic 3-Dimensional Cephalometric Landmarking via Deep Learning

Automatic 3-Dimensional Cephalometric Landmarking via Deep Learning

The application of multiple metrics in deformable image registration for target volume delineation of breast tumor bed

Automatic Three-Dimensional Cephalometric Landmarking via Deep Learning

Contact Info

Product

Resources

About