Prediction of hand‐wrist maturation stages based on cervical vertebrae images using artificial intelligence

Objectives: This study aimed to develop five different supervised machine learning (ML) classifier models using artificial intelligence (AI) techniques and to compare their performance for cervical vertebral maturation (CVM) analysis. A clinical decision support system (CDSS) was developed for more objective results. Methods: A total of 647 digital lateral cephalometric radiographs with visible C2, C3, C4 and C5 vertebrae were chosen. Newly developed software was used for manually labelling the samples, with the integrated CDSS developed by evaluation of 100 radiographs. On each radiograph, 26 points were marked, and the CDSS generated a suggestion according to the points and CVM analysis performed by the human observer. For each sample, 54 features were saved in text format and classified using logistic regression (LR), support vector machine, random forest, artificial neural network (ANN) and decision tree (DT) models. The weighted κ coefficient was used to evaluate the concordance of classification and expert visual evaluation results. Results: Among the CVM stage classifier models, the best result was achieved using the ANN model (κ = 0.926). Among cervical vertebrae morphology classifier models, the best result was achieved using the LR model (κ = 0.968) for the presence of concavity, and the DT model (κ = 0.949) for vertebral body shapes. Conclusions: This study has proposed ML models for CVM assessment on lateral cephalometric radiographs, which can be used for the prediction of cervical vertebrae morphology. Further studies should be done especially of forensic applications of AI models through CVM evaluations.

Download Full-text

Anatomical evaluation of the cervical vertebrae of Wistar rats by means of digital radiographs and its correlation with the maturation stages of human cervical vertebrae

Dental Press Journal of Orthodontics ◽

10.1590/s2176-94512013000400012 ◽

2013 ◽

Vol 18 (4) ◽

pp. 82-88

Author(s):

Roberto Hiroshi Matsui ◽

Julio Cezar de Melo Castilho ◽

Luiz César de Moraes ◽

Mônica Fernandes Gomes ◽

Kurt Faltin Júnior ◽

...

Keyword(s):

Cross Sections ◽

Wistar Rats ◽

Cervical Vertebrae ◽

Pearson Correlation ◽

Bone Age ◽

Skeletal Maturation ◽

Growth Spurt ◽

Digital Radiographs ◽

Maturation Stages ◽

Development Assessment

INTRODUCTION: Biological age is an important parameter for growth and development assessment. It can be evaluated through the observation of radiographic changes in skeletal maturation of cervical vertebrae. OBJECTIVE: This study aims to: a) verify if there is correlation between growth curve and the stages of bone age of animals used in laboratories, by evaluating radiographs of the cervical vertebrae; b) correlate these stages with their correspondents in humans. METHODS: 35 Wistar rats were evaluated for a period of 160 days, starting at day 22nd (weaning), with cross sections for periodic weighing, length measurement and digital radiography. Radiographs of the cervical vertebrae (C2 and C3) were measured by means of a computer program (Radio IMP). Data were submitted to statistical analysis (ANOVA) and Pearson correlation. RESULTS: Growth spurt was characterized by fast increasing in weight and length. Through ANOVA, differences were observed in the cervical measurements between days 22, 97, 127, 157, 187 and 217 (p <0.001). A high correlation was found between increasing in body length and weight, as well as in cervical vertebrae height (r = 0.86). Increments in concavities of vertebrae were also observed, similar to humans. CONCLUSIONS: There is correlation between body growth and maturation of cervical vertebrae in rats. Despite the continuous development of concavities, it was not possible to clearly identify the 5/6 stages as in studies of cervical vertebrae maturation in humans.

Download Full-text

Racial and sex differences in timing of the cervical vertebrae maturation stages

American Journal of Orthodontics and Dentofacial Orthopedics ◽

10.1016/j.ajodo.2016.09.019 ◽

2017 ◽

Vol 151 (4) ◽

pp. 744-749 ◽

Cited By ~ 2

Author(s):

Mona A. Montasser ◽

Grace Viana ◽

Carla A. Evans

Keyword(s):

Sex Differences ◽

Cervical Vertebrae ◽

Maturation Stages

Download Full-text

Sectorization of the Axial Image of Cervical Vertebrae, a Heuristic Approach for Automatic Analysis in Artificial Intelligence

Cervical Spine I ◽

10.1007/978-3-7091-8882-8_14 ◽

1987 ◽

pp. 84-87

Author(s):

A. Wackenheim

Keyword(s):

Artificial Intelligence ◽

Cervical Vertebrae ◽

Heuristic Approach ◽

Automatic Analysis ◽

Axial Image

Download Full-text

Cervical Vertebral Body’s Volume as a New Parameter for Predicting the Skeletal Maturation Stages

BioMed Research International ◽

10.1155/2016/8696735 ◽

2016 ◽

Vol 2016 ◽

pp. 1-7 ◽

Cited By ~ 1

Author(s):

Youn-Kyung Choi ◽

Jinmi Kim ◽

Tetsutaro Yamaguchi ◽

Koutaro Maki ◽

Ching-Chang Ko ◽

...

Keyword(s):

Computed Tomography ◽

Regression Analysis ◽

Regression Model ◽

Cone Beam Computed Tomography ◽

Cervical Vertebrae ◽

Skeletal Maturation ◽

Cone Beam ◽

Simple Regression Model ◽

Maturation Stages ◽

Simple Regression

This study aimed to determine the correlation between the volumetric parameters derived from the images of the second, third, and fourth cervical vertebrae by using cone beam computed tomography with skeletal maturation stages and to propose a new formula for predicting skeletal maturation by using regression analysis. We obtained the estimation of skeletal maturation levels from hand-wrist radiographs and volume parameters derived from the second, third, and fourth cervical vertebrae bodies from 102 Japanese patients (54 women and 48 men, 5–18 years of age). We performed Pearson’s correlation coefficient analysis and simple regression analysis. All volume parameters derived from the second, third, and fourth cervical vertebrae exhibited statistically significant correlations (P<0.05). The simple regression model with the greatest R-square indicated the fourth-cervical-vertebra volume as an independent variable with a variance inflation factor less than ten. The explanation power was 81.76%. Volumetric parameters of cervical vertebrae using cone beam computed tomography are useful in regression models. The derived regression model has the potential for clinical application as it enables a simple and quantitative analysis to evaluate skeletal maturation level.

Download Full-text

Assessing The Relationship Between The Cervical Vertebrae Maturation Stages And Permanent Maxillary Canine Calcification Stages - A Retrospective Study

International Journal of Pharmaceutical Research ◽

10.31838/ijpr/2020.12.04.297 ◽

2020 ◽

Vol 12 (04) ◽

Keyword(s):

Retrospective Study ◽

Cervical Vertebrae ◽

Maxillary Canine ◽

Maturation Stages ◽

The Relationship

Download Full-text

Hubungan tingkat maturitas vertebra servikalis dengan panjang mandibulaRelationship between cervical vertebrae maturity and mandibular length

Jurnal Kedokteran Gigi Universitas Padjadjaran ◽

10.24198/jkg.v32i3.28300 ◽

2020 ◽

Vol 32 (3) ◽

pp. 205

Author(s):

Tessa Rebecca Sihombing ◽

Mimi Marina Lubis

Keyword(s):

Orthodontic Treatment ◽

Cervical Vertebrae ◽

Maturity Level ◽

Lateral Cephalogram ◽

Cross Sectional ◽

Mandibular Growth ◽

Strong Conclusion ◽

Maturation Stages ◽

Cervical Vertebral Maturation ◽

The Relationship

Pendahuluan: Beberapa tahun terakhir, hubungan antara cervical vertebral maturation (CVM) dengan pertumbuhan mandibula yang dinilai melalui panjang mandibula mendapat perhatian. Pemahaman mengenai pertumbuhan dan perkembangan kraniofasial pasien sangat penting dalam membantu menegakkan diagnosis, merencanakan perawatan, dan keberhasilan perawatan ortodonti. Waktu perawatan ortodonti berhubungan dengan keparahan dan tipe maloklusi yang dikaitkan dengan tingkat maturitas pasien. Tujuan penelitian ini adalah untuk menganalisis hubungan tingkat maturitas vertebra servikalis dengan panjang mandibula. Metode: Jenis penelitian analitik dengan rancangan cross sectional. Sampel penelitian menggunakan 100 foto sefalogram lateral pasien usia 8-18 tahun dengan Klas I skeletal. Kualitas foto sefalogram lateral baik dan berasal dari laboratorium yang sama. Pengumpulan data dilakukan dengan menganalisis tingkat maturitas vertebra servikalis dan mengukur panjang mandibula pada sefalogram lateral. Uji statistik yang digunakan ANOVA dan Kruskal-Wallis, analisis korelasi menggunakan Pearson. Hasil: Terdapat perbedaan yang bermakna pada panjang mandibula laki-laki dan perempuan, dengan nilai p=0,009. Panjang mandibula pada laki-laki lebih besar dibandingkan perempuan. Peningkatan panjang mandibula tertinggi pada laki-laki terjadi dari cervical vertebrae maturation stages (CVMS) 3 ke CVMS 4 sebesar 8,19±5,79 mm dan pada perempuan terjadi dari CVMS 3 ke CVMS 4 sebesar 6,38±4,51 mm. Hubungan yang paling erat adalah pada tahap CVMS 3 ke CVMS 4 sebesar 0,858 yang bersifat kuat. Simpulan: Terdapat hubungan antara tingkat maturitas vertebra servikalis dengan panjang mandibula, pada setiap tingkat maturitas vertebra servikalis terjadi peningkatan panjang mandibula. Hal ini menunjukkan bahwa pertumbuhan mandibula sejalan dengan maturitas vertebra servikalis.Kata kunci: Maturitas, vertebra servikalis, panjang mandibula. ABSTRACTIntroduction: In recent years, the relationship between cervical vertebral maturation (CVM) and mandibular growth assessed by mandibular length has received attention. Understanding the patient’s craniofacial growth and development is very important in helping make the diagnosis, planning treatment, and the success of orthodontic treatment. The orthodontic treatment timing was related to the severity and type of malocclusion associated with the patient’s maturity level. This study was aimed to analyse the relationship between cervical vertebrae maturity level and mandibular length. Methods: This was an analytic study with a cross-sectional design. The study sample used 100 lateral cephalogram photos of patients aged 8-18 years with skeletal Class I. The quality of the lateral cephalogram images was good and came from the same laboratory. Data collection was carried out by analysing the cervical vertebrae’s maturity level and measuring the mandibular length on the lateral cephalogram. The statistical test used was ANOVA and Kruskal-Wallis, and the correlation analysis used was Pearson. Results: There were significant differences in the male and female mandibular length, with the p-value = 0.009. The mandibular length in male was higher than in the female. The highest increase in the male mandibular length occurred from cervical vertebrae maturation stages (CVMS) 3 to CVMS 4 by 8.19 ± 5.79 mm, and in women occurred from CVMS 3 to CVMS 4 by 6.38 ± 4.51 mm. The closest relationship was at the CVMS 3 to CVMS 4 stage of 0.858, which was categorised as strong. Conclusion: There is a relationship between the maturity level of the cervical vertebrae and the mandibular length. At each maturity level of the cervical vertebrae, there is an increase in the mandibular length. These results suggest that the mandibular growth is in line with the maturity of the cervical vertebrae.Keywords: Maturity, cervical vertebrae, mandibular length.

Download Full-text