Accuracy and reliability of automatic three-dimensional cephalometric landmarking
| Autor: | M. Arbotto, Gauthier Dot, Thomas Schouman, Frédéric Rafflenbeul, Philippe Rouch, Laurent Gajny |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Cephalometric analysis
Cone beam computed tomography 3D Imagery Cephalometry Orthodontics Automatization 03 medical and health sciences 0302 clinical medicine Imaging Three-Dimensional Robustness (computer science) Maxillo Facial Medicine Humans Reliability (statistics) Landmark business.industry Deep learning Reproducibility of Results Pattern recognition 030206 dentistry Cone-Beam Computed Tomography Otorhinolaryngology Sample size determination 030220 oncology & carcinogenesis Sciences du vivant Surgery Systematic Review Tomography Artificial intelligence Oral Surgery Anatomic Landmarks business Algorithms |
| Zdroj: | International journal of oral and maxillofacial surgery. 49(10) |
| ISSN: | 1399-0020 |
| Popis: | The aim of this systematic review was to assess the accuracy and reliability of automatic landmarking for cephalometric analysis of three-dimensional craniofacial images. We searched for studies that reported results of automatic landmarking and/or measurements of human head computed tomography or cone beam computed tomography scans in MEDLINE, Embase and Web of Science until March 2019. Two authors independently screened articles for eligibility. Risk of bias and applicability concerns for each included study were assessed using the QUADAS-2 tool. Eleven studies with test dataset sample sizes ranging from 18 to 77 images were included. They used knowledge-, atlas- or learning-based algorithms to landmark two to 33 points of cephalometric interest. Ten studies measured mean localization errors between manually and automatically detected landmarks. Depending on the studies and the landmarks, mean errors ranged from 5 mm. The two best-performing algorithms used a deep learning method and reported mean errors |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect