1
|
Kim E, Kuroda Y, Soeda Y, Koizumi S, Yamaguchi T. Validation of Machine Learning Models for Craniofacial Growth Prediction. Diagnostics (Basel) 2023; 13:3369. [PMID: 37958265 PMCID: PMC10647775 DOI: 10.3390/diagnostics13213369] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2023] [Revised: 10/26/2023] [Accepted: 10/31/2023] [Indexed: 11/15/2023] Open
Abstract
This study identified the most accurate model for predicting longitudinal craniofacial growth in a Japanese population using statistical methods and machine learning. Longitudinal lateral cephalometric radiographs were collected from 59 children (27 boys and 32 girls) with no history of orthodontic treatment. Multiple regression analysis, least absolute shrinkage and selection operator, radial basis function network, multilayer perceptron, and gradient-boosted decision tree were used. The independent variables included 26 coordinated values of skeletal landmarks, 13 linear skeletal parameters, and 17 angular skeletal parameters in children ages 6 to 12 years. The dependent variables were the values of the 26 coordinated skeletal landmarks, 13 skeletal linear parameters, and 17 skeletal angular parameters at 13 years of age. The difference between the predicted and actual measured values was calculated using the root-mean-square error. The prediction model for craniofacial growth using the least absolute shrinkage and selection operator had the smallest average error for all values of skeletal landmarks, linear parameters, and angular parameters. The highest prediction accuracies when predicting skeletal linear and angular parameters for 13-year-olds were 97.87% and 94.45%, respectively. This model incorporates several independent variables and is useful for future orthodontic treatment because it can predict individual growth.
Collapse
Affiliation(s)
- Eungyeong Kim
- Department of Orthodontics, School of Dentistry, Kanagawa Dental University, Yokosuka 238-8580, Japan; (S.K.); (T.Y.)
| | | | | | - So Koizumi
- Department of Orthodontics, School of Dentistry, Kanagawa Dental University, Yokosuka 238-8580, Japan; (S.K.); (T.Y.)
| | - Tetsutaro Yamaguchi
- Department of Orthodontics, School of Dentistry, Kanagawa Dental University, Yokosuka 238-8580, Japan; (S.K.); (T.Y.)
| |
Collapse
|
2
|
Patcas R, Keller H, Markic G, Beit P, Eliades T, Cole TJ. Craniofacial growth and SITAR growth curve analysis. Eur J Orthod 2021; 44:325-331. [PMID: 34435635 DOI: 10.1093/ejo/cjab059] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
Abstract
BACKGROUND SITAR (SuperImposition by Translation And Rotation) is a shape invariant growth curve model that effectively summarizes somatic growth in puberty. AIM To apply the SITAR model to longitudinal mandibular growth data to clarify its suitability to facial growth analysis. SUBJECTS AND METHODS 2D-cephalometric data on two mandibular measurements (AP: articulare-pogonion; CP: condylion-pogonion) were selected from the Denver Growth Study, consisting of longitudinal records (age range: 7.9-19.0 years) of females (sample size N: 21; number of radiographs n: 154) and males (N: 18; n: 137). The SITAR mixed effects model estimated, for each measurement and gender separately, a mean growth curve versus chronological age, along with mean age at peak velocity (APV) and peak velocity (PV), plus subject-specific random effects for PV and mean size. The models were also fitted versus Greulich-Pyle bone age. RESULTS In males, mean APV occurred at 14.6 years (AP) and 14.4 years (CP), with mean PV 3.1 mm/year (AP) and 3.3 mm/year (CP). In females, APV occurred at 11.6 years (AP and CP), with mean PV 2.3 mm/year (AP) and 2.4 mm/year (CP). The models explained 95-96 per cent of the cross-sectional variance for males and 92-93 per cent for females. The random effects demonstrated standard deviations (SDs) in size of 5.6 mm for males and 3.9 mm for females, and SDs for PV between 0.3 and 0.5 mm/year. The bone age results were similar. CONCLUSION The SITAR model is a useful tool to analyse epidemiological craniofacial growth based on cephalometric data and provides an array of information on pubertal mandibular growth and its variance in a concise manner.
Collapse
Affiliation(s)
- Raphael Patcas
- Clinic of Orthodontics and Pediatric Dentistry, Centre of Dental Medicine, University of Zurich, Switzerland
| | - Heidi Keller
- Clinic of Orthodontics and Pediatric Dentistry, Centre of Dental Medicine, University of Zurich, Switzerland
| | - Goran Markic
- Clinic of Orthodontics and Pediatric Dentistry, Centre of Dental Medicine, University of Zurich, Switzerland
| | - Philipp Beit
- Clinic of Orthodontics and Pediatric Dentistry, Centre of Dental Medicine, University of Zurich, Switzerland
| | - Theodore Eliades
- Clinic of Orthodontics and Pediatric Dentistry, Centre of Dental Medicine, University of Zurich, Switzerland
| | - Tim J Cole
- UCL Great Ormond Street Institute of Child Health, London, UK
| |
Collapse
|
3
|
Chalala C, Ghafari JG. Differentiation between maxillary and malar midface position within the facial profile. PeerJ 2019; 7:e8200. [PMID: 31844585 PMCID: PMC6910109 DOI: 10.7717/peerj.8200] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2019] [Accepted: 11/13/2019] [Indexed: 12/05/2022] Open
Abstract
Aims To define midfacial position differentiating maxillary and zygomatic regions and to evaluate the corresponding cephalometric characteristics discerning midfacial flatness and fullness. Material and Methods A total of 183 pretreatment lateral cephalometric radiographs of non-growing orthodontic patients (age 25.98 ± 8.43 years) screened at our university orthodontic clinic. The lateral cephalographs of the orthodontic patients were stratified in four groups: flat, normal toward flat, normal toward full, full,according to distances from nasion and sella to points J and G (NJ, SJ, NG and SG). J is the midpoint of the distance connecting orbitale to point A, and G the center of the triangle connecting orbit, key ridge and pterygomaxillary fissure. Statistics included the Kendall tau-b test for best associations among measurements. Results All measurements were statistically significantly different between flat and full groups. The highest associations were between NJ and SJ (τb = 0.71; p < 0.001) and NG and SG (τb = 0.70; p < 0.001). Flat midfaces were characterized by canting of the cranial base and palatal plane, hyperdivergent pattern and maxillary retrognathism. The opposite was true for fuller midfaces. Conclusion Midface skeletal location was assessed differentially in the naso-maxillary and malo-zygomatic structures differentially. Craniofacial characteristics were identified according to this stratification, indicating the potential for application in facial diagnosis and need for testing on 3D cone-beam computed tomography images.
Collapse
Affiliation(s)
- Chimène Chalala
- Departments of Orthodontics and Dentofacial Orthopedics, Lebanese University and American University of Beirut, Beirut, Lebanon
| | - Joseph G. Ghafari
- Division of Orthodontics and Dentofacial Orthopedics, American University of Beirut, Beirut, Lebanon
| |
Collapse
|
4
|
CEPHALOMETRIC STUDIES OF UKRAINIAN BOYS AND GIRLS WITH ORTHOGNATHIC BITE BY THE METHOD OF R. M. RICKETTS. WORLD OF MEDICINE AND BIOLOGY 2018. [DOI: 10.26724/2079-8334-2018-2-64-88-93] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
5
|
Oyonarte R, Hurtado M, Castro MV. Evolution of ANB and SN-GoGn angles during craniofacial growth: A retrospective longitudinal study. APOS TRENDS IN ORTHODONTICS 2016. [DOI: 10.4103/2321-1407.194796] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
Abstract
ObjectiveThe aim of this study is to describe the evolution of the ANB and SN-GoGn angles throughout development, in a longitudinal sample of Caucasian patients.Materials and MethodsHistorical cephalometric records from North American individuals available at the American Association of Orthodontists Foundation Craniofacial Legacy Growth Collection website were used to carry out an exploratory longitudinal study. Lateral cephalometric radiographs of orthodontically untreated males and females were included. Individuals with three or more longitudinal cephalometric records at pre- and post-pubertal stages, with at least one postpubertal radiograph available in vertebral cervical maturation stage (cervical vertebral maturation) 5 or 6, were selected. Seventy-one individuals met the inclusion criteria. ANB, SNA, SNB, and SN-GoGn angles were measured. Individuals were classified according to the latest postpubertal ANB angle available and grouped by CVM. Descriptive statistics were obtained for the cephalometric variables, and differences between genders were analyzed.ResultsForty-five individuals were classified as skeletal Class I at the end of growth, 17 as Class II, and 9 as Class III. ANB values decrease as growth occurs in every group (average ANB decrease between the stages CVM 1 and 6: Class I - 1.5°, Class II - 0.7°, and Class III - 3.1°). For SN-GoGn angle, a constant reduction was observed as skeletal maturation increased (Average SN-GoGn decrease between the stages CVM 1 and 6: Class I - 4°, Class II - 2.5°, and Class III - 4.9°).ConclusionsANB and SN-GoGn angles decrease during growth. The magnitude varies depending on individual sagittal characteristics, Class III individuals displaying the greatest reduction, and Class II individuals the least.
Collapse
Affiliation(s)
- Rodrigo Oyonarte
- Department of Orthodontics, Faculty of Odontology, Universidad de los Andes, Chile
| | - Mónica Hurtado
- Private Practice in General Dentistry, Universidad de los Andes, Santiago, Chile
| | - M. Valeria Castro
- Resident, Graduate Orthodontic Program, Department of Orthodontics, Universidad de los Andes, Santiago, Chile
| |
Collapse
|
6
|
Nahhas RW, Valiathan M, Sherwood RJ. Variation in timing, duration, intensity, and direction of adolescent growth in the mandible, maxilla, and cranial base: the Fels longitudinal study. Anat Rec (Hoboken) 2014; 297:1195-207. [PMID: 24737730 DOI: 10.1002/ar.22918] [Citation(s) in RCA: 35] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2013] [Revised: 02/21/2014] [Accepted: 02/25/2014] [Indexed: 11/12/2022]
Abstract
There is considerable individual variation in the timing, duration, and intensity of growth that occurs in the craniofacial complex during childhood and adolescence. The purpose of this article is to describe the extent of this variation between traits and between individuals within the Fels Longitudinal Study (FLS). Polynomial multilevel models were used to estimate the ages of onset, peak velocity, and cessation of adolescent growth, the time between these ages, the amount of growth between these ages, and peak velocity. This was done at both the group and individual levels for standard cephalometric measurements of the lengths of the mandible, maxilla, and cranial base, the gonial angle, and the saddle angle. Data are from 293 untreated boys and girls age 4-24 years in the FLS. The timing of the adolescent growth spurt was, in general, not significantly different between the mandible and the maxilla, with each having an earlier age of onset, later age of peak velocity, and later age of cessation of growth as compared to the cranial base length. Compared to lengths, angles had in general later ages of onset, peak velocity, and cessation of growth. Accurate characterization of the ontogenetic trajectories of the traits in the craniofacial complex is critical for both clinicians seeking to optimize treatment timing and anatomists interested in examining heterochrony.
Collapse
Affiliation(s)
- Ramzi W Nahhas
- Division of Morphological Sciences and Biostatistics, Lifespan Health Research Center, Department of Community Health, Boonshoft School of Medicine, Wright State University, Dayton, Ohio
| | | | | |
Collapse
|
7
|
Buschang PH, Jacob HB, Demirjian A. Female adolescent craniofacial growth spurts: real or fiction? Eur J Orthod 2013; 35:819-25. [PMID: 23359460 DOI: 10.1093/ejo/cjs094] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022]
Abstract
The purpose of the study is to determine whether the various aspects of the craniofacial complex exhibit female adolescent growth spurts. Multilevel polynomial models were used to estimate the growth curves of a mixed-longitudinal sample of 111 untreated females 10-15 years of age. To evaluate the horizontal and vertical movements of the individual landmarks relative to stable structures, the tracings were superimposed on the natural reference structures in the anterior cranial base. The horizontal and vertical growth changes of four landmarks and the changes of three traditional linear measurements were evaluated. Posterior nasal spine (PNS) moved posteriorly at a constant rate of approximately 0.12mm/year. Five measures showed changes in growth velocity (i.e. quadratic growth curves) but not adolescent growth spurts, including the anterior movements of anterior nasal spine (ANS) and pogonion (Pg), the inferior movements of gonion (Go), and the increases in ANS-PNS and condylion to pogonion (Co-Pg). Five measurements, including the inferior movements of ANS, PNS and Pg, the posterior movements of Go, and the increases of Go-Pg exhibited adolescent growth spurts. Peak growth velocities were attained between 11.4 and 12.8 years of age, approximately 0.7-1.4 years earlier in the maxilla than mandible. While the vertical aspects of craniofacial growth exhibit distinct female adolescent growth spurts, with peak rates occurring earlier in the maxilla than mandible, most horizontal aspects of craniofacial growth do not exhibit an adolescent spurt.
Collapse
Affiliation(s)
- Peter H Buschang
- * Orthodontic Department, Baylor College of Dentistry, Texas A&M Health Science Center, Dallas, USA and
| | | | | |
Collapse
|
8
|
Vertical craniofacial growth changes in French-Canadians between 10 and 15 years of age. Am J Orthod Dentofacial Orthop 2011; 139:797-805. [PMID: 21640887 DOI: 10.1016/j.ajodo.2010.02.032] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2009] [Revised: 02/01/2010] [Accepted: 02/01/2010] [Indexed: 11/21/2022]
Abstract
INTRODUCTION Because of limited available reference data, this study described the vertical growth changes that occur in untreated adolescents 10 to 15 years of age and evaluated the validity of measurements commonly used to classify patients' vertical growth tendencies. METHODS The sample consisted of 228 subjects (119 boys, 109 girls) between 10 and 15 years of age with normal occlusions or malocclusions who had lateral cephalograms (n = 1303) taken annually. Based on 6 landmarks, 3 angles (PPA, MPA, PP/MPA) and 2 proportions (PFH:AFH and UFH:LFH) were calculated. To reduce errors, each subject's growth curve was estimated by using multilevel modeling procedures, and the estimated values were analyzed. RESULTS Growth changes between 10 and 15 years for each of the 5 measurements followed relatively simple (linear or quadratic) polynomial models. On average, PPA and PFH:AFH increased, and MPA and PP/MPA decreased. The UFH:LFH ratio increased during the first few years and then decreased. MPA, PP/MPA, and PFH:AFH showed moderately high intercorrelations; PPA displayed moderate to moderately low correlations with UFH:LFH; UFH:LFH showed a moderate correlation with PP/MPA. Approximately 75% to 86% of the subjects classified as hyperdivergent or hypodivergent at 10 years maintained their classification. Subjects classified as hyperdivergent at 15 years of age showed significantly greater growth changes than did those classified within normal limits, who, in turn, showed greater changes than did the hypodivergent subjects. CONCLUSIONS Measurements typically used to classify vertical growth tendencies changed significantly during adolescence, with boys generally showing greater changes than girls. Although MPA, PFH:AFH, and PP/MPA measured the same phenotypic attribute, PPA and UFH:LFH were relatively independent of the other 3 measurements. Most subjects maintained their vertical facial types, but some worsened, and others improved.
Collapse
|