|
| Authors and year | Aim | Number of X-rays |
|
| Grau et al., 2001 [49] | Aims to identify the landmarks on lateral cephalogram | 20 |
| Kim et al., 2020 [41] | The objective of this paper was to create a fully automated cephalometric analysis method based on deep learning, as well as a web-based application that did not require high-end equipment. | 2075 |
Kunz, et al., 2020
[19, 29, 48] | The goal of this study was to use a specialized AI technique to compute an automatic cephalometric X-ray analysis. | 1792 |
Ma et al., 2020
[56] | The goal of the research is to build a suitable automatic landmarking method depending on real OMS data to help surgeons save time during cephalometric analysis. | 66 |
Mario et al., 2010
[33] | To provide an analysis of the cephalometric variables, taking into consideration the system’s unspecific, inconstant, and paracomplete data | 120 |
Neelapu et al., 2018
[54] | The study suggested a method for automatically identifying cephalometric landmarks depending on 3D CBCT image data. | 30 |
| Nishimoto et al., 2019 [15] | The objective of this research was to create deep learning based automatic cephalometric analysis technique for a computer using cephalogram pictures found online. | 219 |
Rudolph et al., 1998
[53] | This study’s goal was to create and test a new computer-based technique for automatically detecting cephalometric landmarks. | 14 |
| Rueda and Alcaniz 2006 [50] | The goal of this research is to develop an automated system that uses active appearance models (AAMs) | 83 |
Tanikawa et al., 2010
[25, 52, 55] | The focus of this research was to assess the reliability of the system in recognizing anatomic landmarks and surrounding structures on lateral cephalograms using landmark-specific eligibility criteria. | 65 |
Tanikawa et al., 2010
[25, 52, 55] | To evaluate the system performance that automatically identifies dentoskeletal characteristics on preadolescent children’s cephalograms, and to develop a system to do so. | 859 |
Vučinić et al., 2010
[49] | The objective of this study was to assess an automatic method for cephalogram landmarking that relied on an active appearance model (AAM), which is a statistical method that represents both shape and texture variations in the model’s coverage areas by analyzing the form and grey-level appearance of an interest point. | 60 |
Yu et al., 2020
[42, 47] | Final analytic methods employ a neural network in each process with lateral cephalograms to provide a reliable and accurate skeletal detection algorithm. | 5890 |
| Ed-Dhahraouy et al., 2018 [57] | The purpose of this study was to create a new method for automatically detecting points of reference in 3D cephalometry to overcome some of the limitations of 2D cephalometric analysis. | 5 |
Muraev et al., 2020
[58] | The objective of this study was to create a machine learning technique capable of effectively placing cephalometric positions on frontal cephs and relating it to human accuracy. | 300 |
Park et al., 2019
[4, 42, 43] | The goal of this research was to compare the accuracy and efficiency of two latest deep learning techniques for automatic cephalometric landmark identification. | 1028 |
Hutton et al., 2000
[59] | The goal of this research was to see how precise the active shaped methodology was at locating cephalometric landmarks automatically. | 5 |
Liu et al., 2000
[60] | The goal of this study was to see how precise an edge-based method could make a computerized automatic landmark detection system. | 10 |
Yue et al., 2006
[61] | Aims to analyze all craniofacial anatomical structures. | 200 |
| Wang, C.-W., et al., 2016 | The goal of the research was to look into and relate different techniques for automatically detecting landmarks in cephalometric X-ray images. | 300 |
Hwang et al., 2021
[9, 61] | To compare a conventional cephalometric assessment with a fully automated cephalometric evaluation using the most advanced deep learning method for identifying cephalometric landmarks. | 1983 |
Lee et al., 2020
[43. 66] | The goal of the study was to use Bayesian convolutional neural networks to create a new framework for finding cephalometric landmarks with competence areas (BCNN). | 400 |
Jeon et al., 2021
[64] | The rapid development of artificial intelligence technologies for medical imaging has recently enabled the automatic identification of anatomical landmarks on radiographs. The purpose of this study was to compare the results of an automatic cephalometric analysis using a convolutional neural network with those obtained by a conventional cephalometric approach. | 35 |
Leonardi et al., 2008
[21, 65] | To describe the techniques used for automatic landmarking of cephalograms, highlighting the strengths and weaknesses of each one and reviewing the percentage of success in locating each cephalometric point. | 118 articles |
|
