Estimating Cervical Vertebral Maturation with a Lateral Cephalogram Using the Convolutional Neural Network

Kim, Eun-Gyeong; Oh, Il‐Seok; So, Jeong-Eun; Kang, Jeonggyu; Le, Van Nhat Thang; Tak, Min-Kyung; Lee, Daewoo

doi:10.3390/jcm10225400

Cited by 31 publications

(22 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Atici et al used a custom-designed CNN algorithm to classify X-ray images into CVM stages and achieved a testing accuracy of 75.11%. Similarly, Kim et al implemented a custom CNN algorithm for CVM classiőcation and achieved the best accuracy of 62.5% [26]. In medical imaging tasks, one could also propose using pre-trained networks such as ResNet or Xception, although these require large collections of training sets.…”

Section: Discussionmentioning

confidence: 99%

“…The studies extracted the digitized landmarks for the computer-assisted classiőer which require the clinician to identify 19 or 26 digital landmarks on the cervical vertebra. There are also other attempts to develop a fully automated deep learning tool for CVM classiőcation [25,26,27,28]. Note that all previous studies used discrete stages (CS1-CS6) or (CVM I-CVM V), [29,30] for CVM classiőcation and the current discrete classiőcation system is based on human observation.…”

Section: Introduction (10pt Bold)mentioning

confidence: 99%

See 1 more Smart Citation

A Novel Continuous Classification System for the Cervical Vertebrae Maturation (CVM) Stages Using Convolutional Neural Networks

Atici

Elnagar

Allareddy

et al. 2023

Preprint

View full text Add to dashboard Cite

Introduction: We aim to apply deep learning methods to achieve the continuous classification of the Cervical Vertebrae Maturation (CVM) stages and to assess skeletal maturity. We propose a novel two-stage system with a parallel structure network and a sigmoid-based method to generate the continuous-valued cervical vertebrae maturity (CVCVM) parameter. Methods: A total of 1398 Cephalometric radiographs are meticulously annotated and stratified based on their respective Cervical Vertebrae Maturation (CVM) stages, with 1018 images allocated for training and validation, also the remaining 380 collected from 25 patients and labeled by two clinicians for testing. The images are further partitioned according to gender. A two-stage system is devised for the continuous estimation of CVM stages. A parallel-structure neural network called TriPodNet is trained to gauge the likelihood of each class for the maturation stage in the first part of the proposed system. The network is supplied with two different types of input, namely a radiographic X-ray image and chronological age. Probability values of individual classes are generated and mapped onto a continuous stage by two different methods, namely weighted averaging and sigmoid-based regression. The correlation of the estimated Cervical Vertebrae Maturation parameter is assessed using the Pearson correlation coefficient. In order to ascertain the validity of TriPodNet, the Permutation Importancemethod is employed to gauge the impact of each input. Results: TriPodNet is able to achieve a validation accuracy of 81.17% for female subjects and 75.96% for male subjects. During testing, the class probability values of the inputs are determined by TriPodNet, and the continuous estimation parameters are obtained by applying two distinct mapping functions. The sigmoid-based regression method produces an average correlation coefficient value of 0.910 with the first clinician and 0.944 with the second clinician for male patients, while for female patients the values were 0.910 and 0.918 respectively. Conversely, the weighted average method performs less effectively, with average correlation coefficient values of 0.913 and 0.904 for male patients with the first and second clinicians respectively. For female patients, the method produces similar results with an average correlation coefficient value of 0.901 and 0.896 with the first and second clinicians respectively. The Permutation Importance method shows that the image input and the chronological age input collaboratively contribute to the model in producing the accurate output. Conclusion: The proposed method to determine the CVM stages in a continuous stages pattern CVCVM using Convolutional Neural Network (CNN) achieved novel high correlation results compared to true labels and it is more consistent with the gradual growth changes. It is observed to be a unique way to represent skeletal maturity and assess growth.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introduction (10pt Bold)mentioning

confidence: 99%

A Novel Continuous Classification System for the Cervical Vertebrae Maturation (CVM) Stages Using Convolutional Neural Networks

Atici

Elnagar

Allareddy

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We calculated the MAE as average differences between the predicted and groundtruth class labels (0-9 for DELTA PF, 0-11 for Minima S, and 0-12 for MASTER SL). Adjacent accuracy is often used to evaluate ordinal classification algorithms in various research fields; however, it has been described using different terminologies [62], [63]. Adjacent accuracy is similar to the exact accuracy used in nominal classification problems, which allows predictions to adjacent classes within distance to also be correct.…”

Section: A Experiments Environmentmentioning

confidence: 99%

Deep Learning and Computer Vision Techniques for Automated Total Hip Arthroplasty Planning on 2-D Radiographs

Kim

Yoon

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

Preoperative planning is mandatory for successful total hip arthroplasty (THA). In planning, the operating surgeon should decide the best type and size of THA components for the patient. However, most digital templating software only simulates acetate templating by overlaying the shape of the prosthesis components on a radiograph; the selection and positioning of the prostheses are performed manually depending on the operator's experience. Determining the optimal type and size of THA components is a repetitive and time-consuming task for digital and acetate templating. This study proposes a novel approach to automatically select and position THA components that are most suitable for the patient's bone anatomy. The approach consists of two phases: segmenting a hip anteroposterior (AP) radiographic image into five predefined anatomical regions using a fully convolutional neural network, and estimating the optimal sizes and positions of THA components using deep learning and computer vision technology. The experiments demonstrated that the accuracy of acetabular and femoral component size prediction within one size error was 78.9% and 70.9%, respectively. Compared with meta-analysis results from previous studies, our results are close to human level. An automated digital templating prototype system was developed using our research results and tested in a clinical setting to evaluate field adaptability. These processes are introduced in this study.INDEX TERMS Artificial intelligence (AI), automated 2-D templating, hip joint segmentation, implant size estimation, prostheses recommendation, total hip arthroplasty (THA)

show abstract

“…Machine learning (ML), uses algorithms to predict the unseen data based on the learnings obtained from intrinsic statistical patterns and structures in data [14, 15]. Deep learning (DL) refers to network architectures with more than one hidden layer that are capable of analyzing complex data structures such as images [14, 16].…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning (DL) refers to network architectures with more than one hidden layer that are capable of analyzing complex data structures such as images [14, 16]. DL models require less expert knowledge compared to classical ML methods as they can learn features that adapt to the input data [15].…”

Section: Introductionmentioning

confidence: 99%

Application of deep learning to classify skeletal growth phase on 3D radiographs

Ameli

Lagravère

Lai

2023

Preprint

View full text Add to dashboard Cite

Cervical vertebral maturation (CVM) is widely used to evaluate growth potential in the field of orthodontics. The aim of this study is to develop an artificial intelligence (AI) algorithm to automatically predict the CVM stages in terms of growth phases using the cone-beam computed tomographic (CBCT) images. A total of 30,016 slices obtained from 56 patients with the age range of 7-16 years were included in the dataset. After cropping the region of interest (ROI), a convolutional neural network (CNN) was built to classify the slices based on the presence of a good vision of vertebrae for classification of the growth stages. The output was used to train another model capable of categorizing the slices into phases of growth, which were defined as Phase I (prepubertal, CVM stages 1 and 2), phase II (circumpubertal, CVM stage 3), and phase III (postpubertal, CVM stages 4, 5, and 6). After training the model, 88 unused images belonging to 3 phases were used to evaluate the performance of the model using multi-class classification metrics. The average classification accuracy of the first and second CNN-based deep learning models were 96.06% and 95.79%, respectively on the validation dataset. The multi-class classification metrics applied to the new testing dataset also showed an overall accuracy of 84% for predicting the growth phase. Moreover, phase I ranked the highest accuracy in terms of F1 score (87%), followed by phase II (83%), and phase III (80%) on new images. Our proposed models could automatically detect the C2-C4 vertebrae required for CVM staging and accurately classify slices into 3 growth phases without the need for annotating the shape and configuration of vertebrae. This will result in developing a fully automatic and less complex system with reasonable performance, comparable to expert practitioners.

show abstract

Estimating Cervical Vertebral Maturation with a Lateral Cephalogram Using the Convolutional Neural Network

Cited by 31 publications

References 30 publications

A Novel Continuous Classification System for the Cervical Vertebrae Maturation (CVM) Stages Using Convolutional Neural Networks

A Novel Continuous Classification System for the Cervical Vertebrae Maturation (CVM) Stages Using Convolutional Neural Networks

Deep Learning and Computer Vision Techniques for Automated Total Hip Arthroplasty Planning on 2-D Radiographs

Application of deep learning to classify skeletal growth phase on 3D radiographs

Contact Info

Product

Resources

About