Automatic computerized radiographic identification of cephalometric landmarks

The Future of Orthodontics: Deep Learning Technologies

Deep learning has emerged as a revolutionary technical advancement in modern orthodontics, offering novel methods for diagnosis, treatment planning, and outcome prediction. Over the past 25 years, the field of dentistry has widely adopted information technology (IT), resulting in several benefits, including decreased expenses, increased efficiency, decreased need for human expertise, and reduced errors. The transition from preset rules to learning from real-world examples, particularly machine learning (ML) and artificial intelligence (AI), has greatly benefited the organization, analysis, and storage of medical data. Deep learning, a type of AI, enables robots to mimic human neural networks, allowing them to learn and make decisions independently without the need for explicit programming. Its ability to automate cephalometric analysis and enhance diagnosis through 3D imaging has revolutionized orthodontic operations. Deep learning models have the potential to significantly improve treatment outcomes and reduce human errors by accurately identifying anatomical characteristics on radiographs, thereby expediting analytical processes. Additionally, the use of 3D imaging technologies such as cone-beam computed tomography (CBCT) can facilitate precise treatment planning, allowing for comprehensive examinations of craniofacial architecture, tooth movements, and airway dimensions. In today's era of personalized medicine, deep learning's ability to customize treatments for individual patients has propelled the field of orthodontics forward tremendously. However, it is essential to address issues related to data privacy, model interpretability, and ethical considerations before orthodontic practices can use deep learning in an ethical and responsible manner. Modern orthodontics is evolving, thanks to the ability of deep learning to deliver more accurate, effective, and personalized orthodontic treatments, improving patient care as technology develops.

Landmark annotation through feature combinations: a comparative study on cephalometric images with in-depth analysis of model's explainability

OBJECTIVES

The objectives of this study are to explore and evaluate the automation of anatomical landmark localization in cephalometric images using machine learning techniques, with a focus on feature extraction and combinations, contextual analysis, and model interpretability through Shapley Additive exPlanations (SHAP) values.

METHODS

We conducted extensive experimentation on a private dataset of 300 lateral cephalograms to thoroughly study the annotation results obtained using pixel feature descriptors including raw pixel, gradient magnitude, gradient direction, and histogram-oriented gradient (HOG) values. The study includes evaluation and comparison of these feature descriptions calculated at different contexts namely local, pyramid, and global. The feature descriptor obtained using individual combinations is used to discern between landmark and nonlandmark pixels using classification method. Additionally, this study addresses the opacity of LGBM ensemble tree models across landmarks, introducing SHAP values to enhance interpretability.

RESULTS

The performance of feature combinations was assessed using metrics like mean radial error, standard deviation, success detection rate (SDR) (2 mm), and test time. Remarkably, among all the combinations explored, both the HOG and gradient direction operations demonstrated significant performance across all context combinations. At the contextual level, the global texture outperformed the others, although it came with the trade-off of increased test time. The HOG in the local context emerged as the top performer with an SDR of 75.84% compared to others.

CONCLUSIONS

The presented analysis enhances the understanding of the significance of different features and their combinations in the realm of landmark annotation but also paves the way for further exploration of landmark-specific feature combination methods, facilitated by explainability.

AI in Orthodontics: Revolutionizing Diagnostics and Treatment Planning-A Comprehensive Review

The advent of artificial intelligence (AI) in medicine has transformed various medical specialties, including orthodontics. AI has shown promising results in enhancing the accuracy of diagnoses, treatment planning, and predicting treatment outcomes. Its usage in orthodontic practices worldwide has increased with the availability of various AI applications and tools. This review explores the principles of AI, its applications in orthodontics, and its implementation in clinical practice. A comprehensive literature review was conducted, focusing on AI applications in dental diagnostics, cephalometric evaluation, skeletal age determination, temporomandibular joint (TMJ) evaluation, decision making, and patient telemonitoring. Due to study heterogeneity, no meta-analysis was possible. AI has demonstrated high efficacy in all these areas, but variations in performance and the need for manual supervision suggest caution in clinical settings. The complexity and unpredictability of AI algorithms call for cautious implementation and regular manual validation. Continuous AI learning, proper governance, and addressing privacy and ethical concerns are crucial for successful integration into orthodontic practice.

Applications of artificial intelligence in dentomaxillofacial imaging-a systematic review

BACKGROUND

Artificial intelligence (AI) technology has been increasingly developed in oral and maxillofacial imaging. The aim of this systematic review was to assess the applications and performance of the developed algorithms in different dentomaxillofacial imaging modalities.

STUDY DESIGN

A systematic search of PubMed and Scopus databases was performed. The search strategy was set as a combination of the following keywords: "Artificial Intelligence," "Machine Learning," "Deep Learning," "Neural Networks," "Head and Neck Imaging," and "Maxillofacial Imaging." Full-text screening and data extraction were independently conducted by two independent reviewers; any mismatch was resolved by discussion. The risk of bias was assessed by one reviewer and validated by another.

RESULTS

The search returned a total of 3,392 articles. After careful evaluation of the titles, abstracts, and full texts, a total number of 194 articles were included. Most studies focused on AI applications for tooth and implant classification and identification, 3-dimensional cephalometric landmark detection, lesion detection (periapical, jaws, and bone), and osteoporosis detection.

CONCLUSION

Despite the AI models' limitations, they showed promising results. Further studies are needed to explore specific applications and real-world scenarios before confidently integrating these models into dental practice.

Is automatic cephalometric software using artificial intelligence better than orthodontist experts in landmark identification?

BACKGROUND

To evaluate the techniques used for the automatic digitization of cephalograms using artificial intelligence algorithms, highlighting the strengths and weaknesses of each one and reviewing the percentage of success in localizing each cephalometric point.

METHODS

Lateral cephalograms were digitized and traced by three calibrated senior orthodontic residents with or without artificial intelligence (AI) assistance. The same radiographs of 43 patients were uploaded to AI-based machine learning programs MyOrthoX, Angelalign, and Digident. Image J was used to extract x- and y-coordinates for 32 cephalometric points: 11 soft tissue landmarks and 21 hard tissue landmarks. The mean radical errors (MRE) were assessed radical to the threshold of 1.0 mm,1.5 mm, and 2 mm to compare the successful detection rate (SDR). One-way ANOVA analysis at a significance level of P < .05 was used to compare MRE and SDR. The SPSS (IBM-vs. 27.0) and PRISM (GraphPad-vs.8.0.2) software were used for the data analysis.

RESULTS

Experimental results showed that three methods were able to achieve detection rates greater than 85% using the 2 mm precision threshold, which is the acceptable range in clinical practice. The Angelalign group even achieved a detection rate greater than 78.08% using the 1.0 mm threshold. A marked difference in time was found between the AI-assisted group and the manual group due to heterogeneity in the performance of techniques to detect the same landmark.

CONCLUSIONS

AI assistance may increase efficiency without compromising accuracy with cephalometric tracings in routine clinical practice and research settings.

Artificial Intelligence and Machine Learning for Automated Cephalometric Landmark Identification: A Meta-Analysis Previewed by a Systematic Review

Digital dentistry has become an integral part of our practice today, with artificial intelligence (AI) playing the predominant role. The present systematic review was intended to detect the accuracy of landmarks identified cephalometrically using machine learning and artificial intelligence and compare the same with the manual tracing (MT) group. According to the PRISMA-DTA guidelines, a scoping evaluation of the articles was performed. Electronic databases like Doaj, PubMed, Scopus, Google Scholar, and Embase from January 2001 to November 2022 were searched. Inclusion and exclusion criteria were applied, and 13 articles were studied in detail. Six full-text articles were further excluded (three articles did not provide a comparison between manual tracing and AI for cephalometric landmark detection, and three full-text articles were systematic reviews and meta-analyses). Finally, seven articles were found appropriate to be included in this review. The outcome of this systematic review has led to the conclusion that AI, when employed for cephalometric landmark detection, has shown extremely positive and promising results as compared to manual tracing.

Feature Aggregation and Refinement Network for 2D Anatomical Landmark Detection

Localization of anatomical landmarks is essential for clinical diagnosis, treatment planning, and research. This paper proposes a novel deep network named feature aggregation and refinement network (FARNet) for automatically detecting anatomical landmarks. FARNet employs an encoder-decoder structure architecture. To alleviate the problem of limited training data in the medical domain, we adopt a backbone network pre-trained on natural images as the encoder. The decoder includes a multi-scale feature aggregation module for multi-scale feature fusion and a feature refinement module for high-resolution heatmap regression. Coarse-to-fine supervisions are applied to the two modules to facilitate end-to-end training. We further propose a novel loss function named Exponential Weighted Center loss for accurate heatmap regression, which focuses on the losses from the pixels near landmarks and suppresses the ones from far away. We evaluate FARNet on three publicly available anatomical landmark detection datasets, including cephalometric, hand, and spine radiographs. Our network achieves state-of-the-art performances on all three datasets. Code is available at https://github.com/JuvenileInWind/FARNet .

Learning Cephalometric Landmarks for Diagnostic Features Using Regression Trees

Lateral cephalograms provide important information regarding dental, skeletal, and soft-tissue parameters that are critical for orthodontic diagnosis and treatment planning. Several machine learning methods have previously been used for the automated localization of diagnostically relevant landmarks on lateral cephalograms. In this study, we applied an ensemble of regression trees to solve this problem. We found that despite the limited size of manually labeled images, we can improve the performance of landmark detection by augmenting the training set using a battery of simple image transforms. We further demonstrated the calculation of second-order features encoding the relative locations of landmarks, which are diagnostically more important than individual landmarks.

Cephalometric Analysis in Orthodontics Using Artificial Intelligence-A Comprehensive Review

Artificial intelligence (AI) is a branch of science concerned with developing programs and computers that can gather data, reason about it, and then translate it into intelligent actions. AI is a broad area that includes reasoning, typical linguistic dispensation, machine learning, and planning. In the area of medicine and dentistry, machine learning is currently the most widely used AI application. This narrative review is aimed at giving an outline of cephalometric analysis in orthodontics using AI. Latest algorithms are developing rapidly, and computational resources are increasing, resulting in increased efficiency, accuracy, and reliability. Current techniques for completely automatic identification of cephalometric landmarks have considerably improved efficiency and growth prospects for their regular use. The primary considerations for effective orthodontic treatment are an accurate diagnosis, exceptional treatment planning, and good prognosis estimation. The main objective of the AI technique is to make dentists' work more precise and accurate. AI is increasingly being used in the area of orthodontic treatment. It has been evidenced to be a time-saving and reliable tool in many ways. AI is a promising tool for facilitating cephalometric tracing in routine clinical practice and analyzing large databases for research purposes.

Evaluation of the accuracy and reliability of WebCeph – An artificial intelligence-based online software

Objectives:

Landmark identification is of utmost importance in cephalometric analysis but it turns out to be the main source of error. With modern inventions in the field of artificial intelligence (AI), it becomes essential to assess the reliability of computer-automated programs. A greater deal of time can be conserved with fully automated programs such as WebCeph, which uses an AI-based algorithm that performs automated and immediate cephalometric analysis. This study aimed to evaluate the accuracy, reliability, and duration of tracing cephalometric radiographs with WebCeph, an AI-based software in comparison to digital tracing with FACAD and manual tracing. The null hypothesis proposed is that there is no statistically significant difference among the three methods with regard to accuracy of cephalometric analysis.

Material and Methods:

Pre-treatment cephalometric radiographs of 25 patients (14 males and 11 females, mean age of 18 ± 3.2 years) were selected randomly from the dental information archiving software of Saveetha University, Department of Orthodontics, Chennai. Composite analysis with skeletal, dental and soft-tissue parameters was selected and cephalometric analysis was done with all three methods – Manual tracing (Group 1), digital tracing using FACAD (Group 2), and fully automated AI-based software WebCeph (Group 3). The timing for each method of analysis was calculated using a stopwatch in seconds. Values were tabulated in an Excel sheet and statistical analysis including one-way analysis of variance and post hoc Tukey test were performed.

Results:

No statistically significant difference was found between the three methods for cephalometric analysis, P > 0.05. The time taken for measurement using the three different methods was the least while using WebCeph (30.2 ± 6.4 s) and the maximum while manual tracing (472 ± 40.4 s).

Conclusion:

WebCeph is a reliable, faster and practical tool for analyzing cephalometric analysis in comparison to digital tracing using FACAD and manual tracing.

Accuracy of one-step automated orthodontic diagnosis model using a convolutional neural network and lateral cephalogram images with different qualities obtained from nationwide multi-hospitals

Objective

The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals.

Methods

Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradient-weighted class activation mapping (Grad-CAM).

Results

In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis.

Conclusions

Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.

Current applications and development of artificial intelligence for digital dental radiography

In the last few years, artificial intelligence (AI) research has been rapidly developing and emerging in the field of dental and maxillofacial radiology. Dental radiography, which is commonly used in daily practices, provides an incredibly rich resource for AI development and attracted many researchers to develop its application for various purposes. This study reviewed the applicability of AI for dental radiography from the current studies. Online searches on PubMed and IEEE Xplore databases, up to December 2020, and subsequent manual searches were performed. Then, we categorized the application of AI according to similarity of the following purposes: diagnosis of dental caries, periapical pathologies, and periodontal bone loss; cyst and tumor classification; cephalometric analysis; screening of osteoporosis; tooth recognition and forensic odontology; dental implant system recognition; and image quality enhancement. Current development of AI methodology in each aforementioned application were subsequently discussed. Although most of the reviewed studies demonstrated a great potential of AI application for dental radiography, further development is still needed before implementation in clinical routine due to several challenges and limitations, such as lack of datasets size justification and unstandardized reporting format. Considering the current limitations and challenges, future AI research in dental radiography should follow standardized reporting formats in order to align the research designs and enhance the impact of AI development globally.

Automatic recognition of landmarks on digital dental models

Fundamental principle in improving Dental and Orthodontic treatments is the ability to quantitatively assess and cross-compare their outcomes. Such assessments require calculating distances and angles from 3D coordinates of dental landmarks. The costly and repetitive task of hand-labelling dental models hinder studies requiring large sample size to penetrate statistical noise. We have developed techniques and a software implementing these techniques to map out automatically, 3D dental scans. This process is divided into consecutive steps - determining a model's orientation, separating and identifying the individual tooth and finding landmarks on each tooth - described in this paper. The examples to demonstrate the techniques, software and discussions on remaining issues are provided as well. The software is originally designed to automate Modified Huddard Bodemham (MHB) landmarking for assessing cleft lip/palate patients. Currently only MHB landmarks are supported, however it is extendable to any predetermined landmarks. The software, coupled with intra-oral scanning innovation, should supersede the arduous and error prone plaster model and calipers approach to Dental research, and provide a stepping-stone towards automation of routine clinical assessments such as "index of orthodontic treatment need" (IOTN).

Applications of artificial intelligence and machine learning in orthodontics: a scoping review

Introduction

This scoping review aims to provide an overview of the existing evidence on the use of artificial intelligence (AI) and machine learning (ML) in orthodontics, its translation into clinical practice, and what limitations do exist that have precluded their envisioned application.

Methods

A scoping review of the literature was carried out following the PRISMA-ScR guidelines. PubMed was searched until July 2020.

Results

Sixty-two articles fulfilled the inclusion criteria. A total of 43 out of the 62 studies (69.35%) were published this last decade. The majority of these studies were from the USA (11), followed by South Korea (9) and China (7). The number of studies published in non-orthodontic journals (36) was more extensive than in orthodontic journals (26). Artificial Neural Networks (ANNs) were found to be the most commonly utilized AI/ML algorithm (13 studies), followed by Convolutional Neural Networks (CNNs), Support Vector Machine (SVM) (9 studies each), and regression (8 studies). The most commonly studied domains were diagnosis and treatment planning—either broad-based or specific (33), automated anatomic landmark detection and/or analyses (19), assessment of growth and development (4), and evaluation of treatment outcomes (2). The different characteristics and distribution of these studies have been displayed and elucidated upon therein.

Conclusion

This scoping review suggests that there has been an exponential increase in the number of studies involving various orthodontic applications of AI and ML. The most commonly studied domains were diagnosis and treatment planning, automated anatomic landmark detection and/or analyses, and growth and development assessment.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40510-021-00361-9.

Comparing intra-observer variation and external variations of a fully automated cephalometric analysis with a cascade convolutional neural net

The quality of cephalometric analysis depends on the accuracy of the delineating landmarks in orthodontic and maxillofacial surgery. Due to the extensive number of landmarks, each analysis costs orthodontists considerable time per patient, leading to fatigue and inter- and intra-observer variabilities. Therefore, we proposed a fully automated cephalometry analysis with a cascade convolutional neural net (CNN). One thousand cephalometric x-ray images (2 k × 3 k) pixel were used. The dataset was split into training, validation, and test sets as 8:1:1. The 43 landmarks from each image were identified by an expert orthodontist. To evaluate intra-observer variabilities, 28 images from the dataset were randomly selected and measured again by the same orthodontist. To improve accuracy, a cascade CNN consisting of two steps was used for transfer learning. In the first step, the regions of interest (ROIs) were predicted by RetinaNet. In the second step, U-Net detected the precise landmarks in the ROIs. The average error of ROI detection alone was 1.55 ± 2.17 mm. The model with the cascade CNN showed an average error of 0.79 ± 0.91 mm (paired t-test, p = 0.0015). The orthodontist’s average error of reproducibility was 0.80 ± 0.79 mm. An accurate and fully automated cephalometric analysis was successfully developed and evaluated.

Learning-based local-to-global landmark annotation for automatic 3D cephalometry

The annotation of three-dimensional (3D) cephalometric landmarks in 3D computerized tomography (CT) has become an essential part of cephalometric analysis, which is used for diagnosis, surgical planning, and treatment evaluation. The automation of 3D landmarking with high-precision remains challenging due to the limited availability of training data and the high computational burden. This paper addresses these challenges by proposing a hierarchical deep-learning method consisting of four stages: 1) a basic landmark annotator for 3D skull pose normalization, 2) a deep-learning-based coarse-to-fine landmark annotator on the midsagittal plane, 3) a low-dimensional representation of the total number of landmarks using variational autoencoder (VAE), and 4) a local-to-global landmark annotator. The implementation of the VAE allows two-dimensional-image-based 3D morphological feature learning and similarity/dissimilarity representation learning of the concatenated vectors of cephalometric landmarks. The proposed method achieves an average 3D point-to-point error of 3.63 mm for 93 cephalometric landmarks using a small number of training CT datasets. Notably, the VAE captures variations of craniofacial structural characteristics.

The use and performance of artificial intelligence applications in dental and maxillofacial radiology: A systematic review

OBJECTIVES

To investigate the current clinical applications and diagnostic performance of artificial intelligence (AI) in dental and maxillofacial radiology (DMFR).

METHODS

Studies using applications related to DMFR to develop or implement AI models were sought by searching five electronic databases and four selected core journals in the field of DMFR. The customized assessment criteria based on QUADAS-2 were adapted for quality analysis of the studies included.

RESULTS

The initial electronic search yielded 1862 titles, and 50 studies were eventually included. Most studies focused on AI applications for an automated localization of cephalometric landmarks, diagnosis of osteoporosis, classification/segmentation of maxillofacial cysts and/or tumors, and identification of periodontitis/periapical disease. The performance of AI models varies among different algorithms.

CONCLUSION

The AI models proposed in the studies included exhibited wide clinical applications in DMFR. Nevertheless, it is still necessary to further verify the reliability and applicability of the AI models prior to transferring these models into clinical practice.

Comparative Evaluation of Conventional and OnyxCeph™ Dental Software Measurements on Cephalometric Radiography

Objective

Cephalometry can be measured with traditionally conventional analysing methods (hand tracing), as well as using computers. Many dental softwares have been developed for this purpose. The reliability of these programs are often compared with the conventional method. The aim of the present study was to compare the conventional method of manual cephalometric analysis with a computerized one, OnyxCeph ™ (Image Instruments, Chemnitz, Germany) dental software.

Methods

Lateral cephalometric radiographs of 150 patients (75 males and 75 females) age range 12-34 were traced by two methods. Conventional method and computerized (OnyxCeph) cephalometric analysis method. 2 maxillar, 3 mandibular, 2 maxillo-mandibular, 3 vertical, 7 dental and 1 soft tissue parameters; 10 angular, 8 linear totally 18 cephalometric parameters were measured. Intra-class correlation coefficients were performed for both methods to assess the reliability of the measurements.

Results

The results 9 of 18 parameters were found statistically significant. They were Cd-A distance, Cd-Gn distance, Go-Me distance, GoGnSN angle, ANS-Me distance, upper incisor-NA distance, lower incisor-NB distance, lower incisor-NB angle, overbite distance.

Conclusion

Despite some discrepancies in measured values between hand-tracing cephalometric analysis method and the OnyxCeph cephalometric analysis method, statistical differences were minimal and only Cd-A, Cd-Gn, Go-Me, ANS-Me, GoGnSN° were clinically important for cephalometric analysis OnyxCeph was evaluated as an efficient method to replace conventional method.

Automated identification of cephalometric landmarks: Part 1-Comparisons between the latest deep-learning methods YOLOV3 and SSD

OBJECTIVE

To compare the accuracy and computational efficiency of two of the latest deep-learning algorithms for automatic identification of cephalometric landmarks.

MATERIALS AND METHODS

A total of 1028 cephalometric radiographic images were selected as learning data that trained You-Only-Look-Once version 3 (YOLOv3) and Single Shot Multibox Detector (SSD) methods. The number of target labeling was 80 landmarks. After the deep-learning process, the algorithms were tested using a new test data set composed of 283 images. Accuracy was determined by measuring the point-to-point error and success detection rate and was visualized by drawing scattergrams. The computational time of both algorithms was also recorded.

RESULTS

The YOLOv3 algorithm outperformed SSD in accuracy for 38 of 80 landmarks. The other 42 of 80 landmarks did not show a statistically significant difference between YOLOv3 and SSD. Error plots of YOLOv3 showed not only a smaller error range but also a more isotropic tendency. The mean computational time spent per image was 0.05 seconds and 2.89 seconds for YOLOv3 and SSD, respectively. YOLOv3 showed approximately 5% higher accuracy compared with the top benchmarks in the literature.

CONCLUSIONS

Between the two latest deep-learning methods applied, YOLOv3 seemed to be more promising as a fully automated cephalometric landmark identification system for use in clinical practice.

Evaluation of an online website-based platform for cephalometric analysis

BACKGROUND

The purpose of our study was to assess the reproducibility of linear and angular measurements of cephalogram tracings made with an online website-based platform CephX® vs. tracings made using the FACAD® computer software.

METHODS

Thirty cephalometric radiographs were selected randomly to be used in this study. A total of 16 landmarks and 16 measurements (8 linear and 8 angular) were defined. We used paired t-test to compare mean differences between both methods. Concordance Correlation Coefficient (CCC) and Bland-Altman analyses were used to evaluate reproducibility of measurements. The level of statistical significance was set at P < 0.05.

RESULTS

We did not find a statistically significant mean difference between the two methods except for two angular measurements SNA, FMA and one linear measurement Pg to NB. The highest magnitude of the difference between sample means was 1.9° and 0.78 mm for the angular and linear measurements respectively. The SE value was less than 0.1° for the angular measurements and less than 0.3 mm for the linear measurements. All parameters except POG to NB showed moderate to almost perfect agreement (>0.90).

CONCLUSION

The measurements obtained by both softwares FACAD® and CephX® are reproducible. Although significant differences were detected for some measurements, all differences were not clinically significant.

Automatic 3D cephalometric annotation system using shadowed 2D image-based machine learning

This paper presents a new approach to automatic three-dimensional (3D) cephalometric annotation for diagnosis, surgical planning, and treatment evaluation. There has long been considerable demand for automated cephalometric landmarking, since manual landmarking requires considerable time and experience as well as objectivity and scrupulous error avoidance. Due to the inherent limitation of two-dimensional (2D) cephalometry and the 3D nature of surgical simulation, there is a trend away from current 2D to 3D cephalometry. Deep learning approaches to cephalometric landmarking seem highly promising, but there exist serious difficulties in handling high dimensional 3D CT data, dimension referring to the number of voxels. To address this issue of dimensionality, this paper proposes a shadowed 2D image-based machine learning method which uses multiple shadowed 2D images with various lighting and view directions to capture 3D geometric cues. The proposed method using VGG-net was trained and tested using 2700 shadowed 2D images and corresponding manual landmarkings. Test data evaluation shows that our method achieved an average point-to-point error of 1.5 mm for the seven major landmarks.

Manual tracing versus smartphone application (app) tracing: a comparative study

OBJECTIVE

This study aimed to compare the results of conventional manual cephalometric tracing with those acquired with smartphone application cephalometric tracing.

MATERIALS AND METHODS

The cephalometric radiographs of 55 patients (25 females and 30 males) were traced via the manual and app methods and were subsequently examined with Steiner's analysis. Five skeletal measurements, five dental measurements and two soft tissue measurements were managed based on 21 landmarks. The durations of the performances of the two methods were also compared.

RESULTS

SNA (Sella, Nasion, A point angle) and SNB (Sella, Nasion, B point angle) values for the manual method were statistically lower (p < .001) than those for the app method. The ANB value for the manual method was statistically lower than that of app method. L1-NB (°) and upper lip protrusion values for the manual method were statistically higher than those for the app method. Go-GN/SN, U1-NA (°) and U1-NA (mm) values for manual method were statistically lower than those for the app method. No differences between the two methods were found in the L1-NB (mm), occlusal plane to SN, interincisal angle or lower lip protrusion values.

CONCLUSIONS

Although statistically significant differences were found between the two methods, the cephalometric tracing proceeded faster with the app method than with the manual method.

Assessing the Reliability of Digitalized Cephalometric Analysis in Comparison with Manual Cephalometric Analysis

INTRODUCTION

For more than seven decades orthodontist used cephalometric analysis as one of the main diagnostic tools which can be performed manually or by software. The use of computers in treatment planning is expected to avoid errors and make it less time consuming with effective evaluation and high reproducibility.

AIM

This study was done to evaluate and compare the accuracy and reliability of cephalometric measurements between computerized method of direct digital radiographs and conventional tracing.

MATERIALS AND METHODS

Digital and conventional hand tracing cephalometric analysis of 50 patients were done. Thirty anatomical landmarks were defined on each radiograph by a single investi-gator, 5 skeletal analysis (Steiner, Wits, Tweeds, McNamara, Rakosi Jarabaks) and 28 variables were calculated.

RESULTS

The variables showed consistency between the two methods except for 1-NA, Y-axis and interincisal angle measurements which were higher in manual tracing and higher facial axis angle in digital tracing.

CONCLUSION

Most of the commonly used measurements were accurate except some measurements between the digital tracing with FACAD^® and manual methods. The advantages of digital imaging such as enhancement, transmission, archiving and low radiation dosages makes it to be preferred over conventional method in daily use.

An evaluation of the reproducibility of landmark identification in traditional versus computer-assisted digital cephalometric analysis system

Objective

To determine the reliability of Computer Assisted Digital Cephalometric Analysis System (CADCAS) in terms of landmark identification on the values of cephalometric measurements in comparison with those obtained from original radiographs.

Materials and Methods

The study material consisted of Twenty five lateral cephalograms selected randomly, 16 cephalometric points together with 10 angular and 5 linear cephalometric measurements. The landmarks were manually picked on the tracing & the measurements of X &Y axis done with reference grid. The same tracing was digitized & image loaded in the software (ViewBox 3.1.1) was checked for the magnification (metal ruler) & distortion. The second part of the study compared manual and the CADCAS since the landmarks were manually digitized on screen as against the manually picked ones on the tracing paper. The x and y-coordinates for 16 landmarks were measured, mean and standard deviation calculated, linear and angular measurements compared.

Statistical Analysis

A paired t-test was done to calculate the statistical significance of the differences. Intraclass reliability coefficient (signifying reproducibility) of the variable was recorded. The observations were tabulated and analysis was done using the paired t test at a P value <0.05.

Results

Out of 47 variables looked for, 21 showed statistical significance. Direct digitization onscreen (CADCAS) was the quickest and least tedious method. CADCAS was unreliable with linear measurements involving bilateral structures such as Gonion & Articulare.

Conclusions

Both the methods are equally reliable and reproducible. The intra-class reliability coefficient of all variables differed only slightly, which is not clinically significant.

Accuracy of computerized automatic identification of cephalometric landmarks by a designed software

OBJECTIVES

The purpose of this study was to design software for localization of cephalometric landmarks and to evaluate its accuracy in finding landmarks.

METHODS

40 digital cephalometric radiographs were randomly selected. 16 landmarks which were important in most cephalometric analyses were chosen to be identified. Three expert orthodontists manually identified landmarks twice. The mean of two measurements of each landmark was defined as the baseline landmark. The computer was then able to compare the automatic system's estimate of a landmark with the baseline landmark. The software was designed using Delphi and Matlab programming languages. The techniques were template matching, edge enhancement and some accessory techniques.

RESULTS

The total mean error between manually identified and automatically identified landmarks was 2.59 mm. 12.5% of landmarks had mean errors less than 1 mm. 43.75% of landmarks had mean errors less than 2 mm. The mean errors of all landmarks except the anterior nasal spine were less than 4 mm.

CONCLUSIONS

This software had significant accuracy for localization of cephalometric landmarks and could be used in future applications. It seems that the accuracy obtained with the software which was developed in this study is better than previous automated systems that have used model-based and knowledge-based approaches.

A comparison of hand-tracing and cephalometric analysis computer programs with and without advanced features--accuracy and time demands

The aim of this study was to evaluate the basic and advanced features of five different cephalometric analysis computer programs. The level of measurement agreement with hand-tracing and time demands was examined. The material consisted of 30 digital lateral radiographic images. Twenty-three measurements were calculated by one operator both manually and using five different cephalometric analysis software programs. Intraclass correlation coefficient (ICC) was used to detect differences in measurement agreement between hand-tracing and basic features as well as between hand-tracing and advanced features. Coefficient of variation (CV) was used to assess intra-user error and a Student's t-test to determine time differences. Of the 23 measurements tested for each procedure, one [(Ii to NB (mm)] showed better agreement with hand-tracing when the advanced features were used, 20 showed good agreement with hand-tracing for both basic and advanced features, while two (AB on FOP and Ii to A/Pog) showed poor intra-user reproducibility. Hand-tracing took a significantly longer time (P < 0.001) than both the basic and advanced features. The advanced features took a significantly longer time (P < 0.001) than the basic features. Both basic and advanced features showed good measurement agreement with the hand-tracing technique. The use of the basic features minimizes the time requirements for analysis. A computerized tracing technique, which consists of either basic or advanced feature, can be regarded as less time consuming and equally reliable to hand-tracing as far as cephalometric measurements are concerned.

Estudo comparativo das análises cefalométricas manual e computadorizada

OBJETIVO: realizar uma análise comparativa dos traçados manual e computadorizado utilizando um software específico, com a finalidade de definir os resultados inter e intra-avaliadores. MÉTODOS: foi utilizada uma amostra composta por 50 radiografias cefalométricas em norma lateral, sendo todas padronizadas, contendo pacientes de ambos os gêneros e de várias faixas etárias. A análise das radiografias foi realizada por dois avaliadores, os quais realizaram os traçados manuais e computadorizados das 50 radiografias. Para compor as medições, foram selecionadas medidas angulares e lineares, que posteriormente foram submetidas ao teste estatístico de Mann-Whitney, com o objetivo de comparar os resultados entre os dois tipos de traçados inter e intra-avaliadores. RESULTADOS E CONCLUSÕES: conclui-se que pode ser aumentada a confiança nos traçados cefalométricos computadorizados, haja vista que as discrepâncias encontradas entre as medidas dos traçados cefalométricos manual e computadorizado inter e intra-avaliadores, em sua maioria, não foram estatisticamente significativas.

Automatic landmarking of cephalograms using active appearance models

There have been many attempts to further improve and automate cephalometric analysis in order to increase accuracy, reduce errors due to subjectivity, and to provide more efficient use of clinicians' time. The aim of this research was to evaluate an automated system for landmarking of cephalograms based on the use of an active appearance model (AAM) that contains a statistical model of shape and grey-level appearance of an object of interest and represents both shape and texture variations of the region covered by the model. Multi-resolution implementation was used, in which the AAM iterate to convergence at each level before projecting the current solution to the next level of the model. The AAM system was trained using 60 randomly selected, hand-annotated digital cephalograms of subjects between 7.2 and 25.6 years of age, and tested with a leave-five-out method that enabled testing not only of the accuracy of the AAM system but also the accuracy of each AAM. Differences between methods were examined using the non-parametric Wilcoxon signed rank test. An average accuracy of 1.68 mm was obtained, with 61 per cent of landmarks detected within 2 mm and 95 per cent of landmarks detected within 5 mm precision. A noticeable increase in overall precision and detection of low-contrast cephalometric landmarks was achieved compared with other automated systems. These results suggest that the AAM approach can adequately represent the average shape and texture variations of craniofacial structures on digital radiographs. As such it can successfully be implemented for automatic localization of cephalometric landmarks.

Automated cephalometry: system performance reliability using landmark-dependent criteria

OBJECTIVE

The purpose of the present study was to evaluate reliability of a system that performs automatic recognition of anatomic landmarks and adjacent structures on lateral cephalograms using landmark-dependent criteria unique to each landmark.

MATERIALS AND METHODS

To evaluate the reliability of the system, the system was used to examine 65 lateral cephalograms. The area of each system-identified anatomic structure surrounding the landmark and the position of each system-identified landmark were compared with norms using confidence ellipses with alpha = .01, which were derived from the scattergrams of 100 estimates obtained according to the method reported by Baumrind and Frantz. When the system-identified area overlapped with the norm area, anatomic structure recognition was considered successful. In addition, when the system-identified point was located within the norm area, landmark identification was considered successful. Based on these judgment criteria, success rates were calculated for all landmarks.

RESULTS

The system successfully identified all specified anatomic structures in all the images and determined the positions of the landmarks with a mean success rate of 88% (range, 77%- 100%).

CONCLUSION

With the incorporation of the rational assessment criteria provided by confidence ellipses, the proposed system was confirmed to be reliable.

Method selection in craniofacial measurements: advantages and disadvantages of 3D digitization method

AIM

Treatment of the craniofacial malformations is a primary goal of cranio-maxillo-facial surgeons. Surgical treatment of these malformations requires accurate data. Accuracy of measurement should be a priority of scientists to prevent statistical errors and therefore to promote the comparison of the results obtained from various research groups. In the present study, we aimed to compare three different measurement techniques, which were used frequently in craniofacial measurements.

METHODS

A total number of 35 female and 35 male volunteer adults were included to the study. Two-dimensional (2D) photogrammetry, three-dimensional (3D) digitization and manual anthropometry methods were used for the present study. Measurements were obtained from the ear, eye, nose and face.

RESULTS

By comparing three methods, our findings revealed that 3D digitization method is an easy, robust, and sensitive method to obtain the data.

CONCLUSIONS

We think that 3D digitization method is accurate, and it can be applied to both clinical practice and research. Advantages and disadvantages of three methods are discussed with the relevant literature.

An evaluation of cellular neural networks for the automatic identification of cephalometric landmarks on digital images

Several efforts have been made to completely automate cephalometric analysis by automatic landmark search. However, accuracy obtained was worse than manual identification in every study. The analogue-to-digital conversion of X-ray has been claimed to be the main problem. Therefore the aim of this investigation was to evaluate the accuracy of the Cellular Neural Networks approach for automatic location of cephalometric landmarks on softcopy of direct digital cephalometric X-rays. Forty-one, direct-digital lateral cephalometric radiographs were obtained by a Siemens Orthophos DS Ceph and were used in this study and 10 landmarks (N, A Point, Ba, Po, Pt, B Point, Pg, PM, UIE, LIE) were the object of automatic landmark identification. The mean errors and standard deviations from the best estimate of cephalometric points were calculated for each landmark. Differences in the mean errors of automatic and manual landmarking were compared with a 1-way analysis of variance. The analyses indicated that the differences were very small, and they were found at most within 0.59 mm. Furthermore, only few of these differences were statistically significant, but differences were so small to be in most instances clinically meaningless. Therefore the use of X-ray files with respect to scanned X-ray improved landmark accuracy of automatic detection. Investigations on softcopy of digital cephalometric X-rays, to search more landmarks in order to enable a complete automatic cephalometric analysis, are strongly encouraged.

Automatic cephalometric analysis

OBJECTIVE

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.

MATERIALS AND METHODS

The literature survey was performed by searching the Medline, the Institute of Electrical and Electronics Engineers, and the ISI Web of Science Citation Index databases. The survey covered the period from January 1966 to August 2006. Abstracts that appeared to fulfill the initial selection criteria were selected by consensus. The original articles were then retrieved. Their references were also hand-searched for possible missing articles. The search strategy resulted in 118 articles of which eight met the inclusion criteria. Many articles were rejected for different reasons; among these, the most frequent was that results of accuracy for automatic landmark recognition were presented as a percentage of success.

RESULTS

A marked difference in results was found between the included studies consisting of heterogeneity in the performance of techniques to detect the same landmark. All in all, hybrid approaches detected cephalometric points with a higher accuracy in contrast to the results for the same points obtained by the model-based, image filtering plus knowledge-based landmark search and "soft-computing" approaches.

CONCLUSIONS

The systems described in the literature are not accurate enough to allow their use for clinical purposes. Errors in landmark detection were greater than those expected with manual tracing and, therefore, the scientific evidence supporting the use of automatic landmarking is low.

An image representation algorithm compatible with neural-associative-processor-based hardware recognition systems

A robust image representation algorithm compatible with the VLSI-matching-engine-based image recognition system has been developed. The spatial distributions of four-principal-direction edges in a 64 /spl times/ 64-pels gray scale image are coded to form a 64-dimension feature vector. Since the 2D edge information is reduced to a feature vector by projecting edge flags to the principal directions, it is named the projected principal-edge distribution (PPED) representation. The PPED vectors very well preserve the human perception of similarity among images in the vector space, while achieving a substantial dimensionality reduction in the image data. The PPED algorithm has been applied to medical radiograph analysis, which was taken as a test vehicle for algorithm optimization. The robust nature of the PPED representation has been confirmed by the recognition results comparable to the diagnosis by experts having several years of experience in a university hospital. Dedicated digital VLSI circuits have been developed for PPED vector generation in order to expedite the processing. A test hardware recognition system was constructed using the vector generation circuits, where the analog neural associative processor chip developed in a separate project was employed as a vector-matching engine. As a result, a successful medical radiograph analysis has been experimentally demonstrated using the hardware system. Feasibility of a very low-power operation of the system has been also demonstrated.

Automated 2-D cephalometric analysis on X-ray images by a model-based approach

Craniofacial landmark localization and anatomical structure tracing on cephalograms are two important ways to obtain the cephalometric analysis. In order to computerize them in parallel, a model-based approach is proposed to locate 262 craniofacial feature points, including 90 landmarks and 172 auxiliary points. In model training, 12 landmarks are selected as reference points and used to divide every training shape to 10 regions according to the anatomical knowledge; principle components analysis is employed to characterize the region shape variations and the statistical grey profile of every feature point. Locating feature points on an input image is a two-stage procedure. First, we identify the reference landmarks by image processing and pattern matching techniques, so that the shape partition is performed on the input image. Then, for each region, its feature points are located by a modified active shape model. All craniofacial anatomical structures can be traced out by connecting the located points with subdivision curves according to the prior knowledge. Users are permitted to modify the results interactively in many different ways. Experimental results show the advantage and reliability of the proposed method.

Image processing for craniofacial landmark identification and measurement: a review of photogrammetry and cephalometry

Facial surface anthropometry and cephalometry have been used for many years for the diagnosis of malformations, surgical planning and evaluation, and growth studies. These disciplines rely on the identification of craniofacial landmarks. Methods for 3D reconstruction of landmarks have been introduced, as have image processing algorithms for the automation of landmark extraction. This paper reviews facial surface anthropometry and cephalometry with reference to the image processing algorithms that have been applied and their effectiveness.

Landmark identification on direct digital versus film-based cephalometric radiographs: a human skull study

The purpose of this study was to investigate differences in landmark identification on vertically scanned, direct digital and conventional (18 x 24 cm) cephalometric radiographs. Eight observers, all orthodontists or postgraduate orthodontic students, recorded 6 landmarks twice on 3 digital and 3 conventional cephalograms obtained from 3 human skulls in a standardized fashion. Digital images were displayed on a 15.1-in TFT monitor in 3:1 mode (20 x 26 cm). Recordings were transferred into standardized coordinate systems and evaluated separately for each coordinate. After correcting for magnification, precision was assessed with Maloney-Rastogi tests, and intraobserver and interobserver reproducibility was calculated from squared differences. Effective magnification was larger for the digital images (x, 13%; y, 12%). Significantly different (P <.05) precision was found for nasion (N), posterior nasal spine (PNS), sella (S), supraspinale (A), and orbitale (Or), but average differences were entirely below 1 mm. Interobserver and intraobserver reproducibility did not differ significantly between the 2 image modes. Squared differences were largest for PNS and Or in both modalities. Our results indicate comparable errors in landmark recording for both evaluated machines. However, these results must be considered in the context of the specific display conditions for digital images, because no general standard exists for this purpose.