Automatic Landmark Research Articles

Robust ACO-Based Landmark Matching and Maxillofacial Anomalies Classification

Imagery assessment is an efficient method for detecting craniofacial anomalies. A cephalometric landmark matching approach may help in orthodontic diagnosis, craniofacial growth assessment and treatment planning. Automatic landmark matching and anomalies detection helps face the manual labelling limitations and optimize preoperative planning of maxillofacial surgery. The aim of this study was to develop an accurate Cephalometric Landmark Matching method as well as an automatic system for anatomical anomalies classification. First, the Active Appearance Model (AAM) was used for the matching process. This process was achieved by the Ant Colony Optimization (ACO) algorithm enriched with proximity information. Then, the maxillofacial anomalies were classified using the Support Vector Machine (SVM). The experiments were conducted on X-ray cephalograms of 400 patients where the ground truth was produced by two experts. The frameworks achieved a landmark matching error (LE) of 0.50 ± 1.04 and a successful landmark matching of 89.47% in the 2 mm and 3 mm range and of 100% in the 4 mm range. The classification of anomalies achieved an accuracy of 98.75%. Compared to previous work, the proposed approach is simpler and has a comparable range of acceptable matching cost and anomaly classification. Results have also shown that it outperformed the K-nearest neighbors (KNN) classifier.

Automatic analysis of lateral cephalograms based on high-resolution net

Cephalometric analysis is essential in orthodontic treatment, and it is progressing toward automatic cephalometric analysis. This study aimed to establish a cephalometric landmark detection model on the basis of a high-resolution net and improve the accuracy with high resolution. A total of 2000 lateral cephalograms were collected to construct a dataset, and the number of target landmarks was 51. A high-resolution network model was applied to the landmark detection task. Four models were trained by adjusting different input resolutions to choose the most suitable resolution. A test set consisting of 300 lateral cephalograms was used for evaluation. The model was evaluated from the error size and distribution of each landmark. After 200 epochs of training, a landmark detection model was established. Under different resolutions of the input image, the mean model radial error decreased initially and then increased. At 680 × 920 pixels resolution, the minimum error and the highest detection success rate were obtained. The mean radial error was 1.08 ± 0.87 mm. The detection success rates of 2.0 mm, 2.5 mm, 3.0 mm, and 4.0 mm were 89.00%, 94.00%, 96.33%, and 98.67%, respectively. The mean radial errors of 22 landmarks were<1 mm, and the errors of other landmarks were<2 mm except for the pterion. The error distribution of landmarks followed a certain pattern. An automatic landmark detection model based on a high-resolution net was established to recognize 51 landmarks. The model showed high detection accuracy, which provides a basis for further measurement application.

Artificial intelligence system for automated landmark localization and analysis of cephalometry.

Cephalometric analysis is essential for diagnosis, treatment planning and outcome assessment of orthodontics and orthognathic surgery. Utilizing artificial intelligence (AI) to achieve automated landmark localization has proved feasible and convenient. However, current systems remain insufficient for clinical application, as patients exhibit various malocclusions in cephalograms produced by different manufacturers while limited cephalograms were applied to train AI in these systems. A robust and clinically applicable AI system was proposed for automatic cephalometric analysis. First, 9870 cephalograms taken by different radiography machines with various malocclusions of patients were collected from 20 medical institutions. Then 30 landmarks of all these cephalogram samples were manually annotated to train an AI system, composed of a two-stage convolutional neural network and a software-as-a-service system. Further, more than 100 orthodontists participated to refine the AI-output landmark localizations and retrain this system. The average landmark prediction error of this system was as low as 0.94 ± 0.74 mm and the system achieved an average classification accuracy of 89.33%. An automatic cephalometric analysis system based on convolutional neural network was proposed, which can realize automatic landmark location and cephalometric measurements classification. This system showed promise in improving diagnostic efficiency in clinical circumstances.

Clinical feasibility of deep learning-based automatic head CBCT image segmentation and landmark detection in computer-aided surgical simulation for orthognathic surgery

The purpose of this ambispective study was to investigate whether deep learning-based automatic segmentation and landmark detection, the SkullEngine, could be used for orthognathic surgical planning. Sixty-one sets of cone beam computed tomography (CBCT) images were automatically inferred for midface, mandible, upper and lower teeth, and 68 landmarks. The experimental group included automatic segmentation and landmarks, while the control group included manual ones that were previously used to plan orthognathic surgery. The qualitative analysis of segmentation showed that all of the automatic results could be used for computer-aided surgical simulation. Among these, 98.4% of midface, 70.5% of mandible, 98.4% of upper teeth, and 93.4% of lower teeth could be directly used without manual revision. The Dice similarity coefficient was 96% and the average symmetric surface distance was 0.1 mm for all four structures. With SkullEngine, it took 4 minutes to complete the automatic segmentation and an additional 10 minutes for a manual touchup. The results also showed the overall mean difference between the two groups was 2.3 mm for the midface and 2.4 mm for the mandible. In summary, the authors believe that automatic segmentation using SkullEngine is ready for daily practice. However, the accuracy of automatic landmark digitization needs to be improved.

Automatic extraction of upper body landmarks using Rhino and Grasshopper algorithms

The aim of this study is to develop algorithms for automatic landmark extraction on women with various upper body types and body inclinations using the Grasshopper algorithm editor, which enables the user to interact with the 3D modeling interface. First, 15 landmarks were defined based on the morphological features of 3D body surfaces and clothing applications, from which automatic landmark extraction algorithms were developed. To verify the accuracy of the algorithms on various body shapes, this study determined criteria for key body shape factors (BMI, neck slope, upper body slope, and shoulder slope) that influence each landmark position, classified them into body shape groups and sorted the scan samples for each body type using the 6th SizeKorea database. The statistical differences between the scan-derived measurements and the SizeKorea measurements were compared, with an allowable tolerance of ISO 20685. In the case of landmarks with significant differences, the algorithm was modified. It was found that the algorithms were successfully applied to various upper body shapes, which improved the reliability and accuracy of the algorithm.

A semi-supervised learning approach for automated 3D cephalometric landmark identification using computed tomography.

Identification of 3D cephalometric landmarks that serve as proxy to the shape of human skull is the fundamental step in cephalometric analysis. Since manual landmarking from 3D computed tomography (CT) images is a cumbersome task even for the trained experts, automatic 3D landmark detection system is in a great need. Recently, automatic landmarking of 2D cephalograms using deep learning (DL) has achieved great success, but 3D landmarking for more than 80 landmarks has not yet reached a satisfactory level, because of the factors hindering machine learning such as the high dimensionality of the input data and limited amount of training data due to the ethical restrictions on the use of medical data. This paper presents a semi-supervised DL method for 3D landmarking that takes advantage of anonymized landmark dataset with paired CT data being removed. The proposed method first detects a small number of easy-to-find reference landmarks, then uses them to provide a rough estimation of the all landmarks by utilizing the low dimensional representation learned by variational autoencoder (VAE). The anonymized landmark dataset is used for training the VAE. Finally, coarse-to-fine detection is applied to the small bounding box provided by rough estimation, using separate strategies suitable for the mandible and the cranium. For mandibular landmarks, patch-based 3D CNN is applied to the segmented image of the mandible (separated from the maxilla), in order to capture 3D morphological features of mandible associated with the landmarks. We detect 6 landmarks around the condyle all at once rather than one by one, because they are closely related to each other. For cranial landmarks, we again use the VAE-based latent representation for more accurate annotation. In our experiment, the proposed method achieved a mean detection error of 2.88 mm for 90 landmarks using only 15 paired training data.

Comparative landmark detection on stops of dysarthric speech

Dysarthria is a disease of motor speech that affects millions of individuals. This impairment induces wrongly pronounced phonemes, variable speech amplitude, low articulation, etc resulting in poor intelligibility. Significant time instants known as landmarks are detected for modifications in the distorted dysarthric speech. The difficulty in accurately locating the regions for modification in an automated fashion is one of the most predominant challenges. Hence it is important to detect the landmarks accurately and modifications have to be carried out for the segment of interest based on estimates. This work aims at identifying the stop consonants in dysarthric speech accurately, in particular, closure onset and burst onset landmarks for stops and, also comparing landmark detection by automatic and manual procedures to improve the intelligibility of dysarthric speech. Automatic landmark detection by using energy derivatives gives more accurate landmark detection than Manual landmark detection. Praat software and Speechmark toolbox are used to detect landmarks.

Automatic landmark detection and mapping for 2D/3D registration with BoneNet

The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations.

Review of online X-ray diagnostic services based on artificial neural networks in dentistry

Aim. This review is devoted to the analysis of available on-line services and programs using artificial neural networks (ANNs) in dentistry, especially for cephalometric analysis.Materials and methods. We searched for scientific publications in the information and analytical databases PubMed, Google Scholar and eLibrary using combinations of the following keywords: artificial intelligence, deep learning, computer vision, neural network, dentistry, orthodontics, cephalometry, cephalometric analysis. 1612 articles were analyzed, of which 23 publications were included in our review.Results. Deep machine learning based on ANN has been successfully used in various branches of medicine as an analytical tool for processing various data. ANNs are especially successfully used for image recognition in radiology and histology. In dentistry, computer vision is used to diagnose diseases of the maxillofacial region, plan surgical treatment, including dental implantation, as well as for cephalometric analysis for the needs of orthodontists and maxillofacial surgeons.Conclusion. Currently, there are many programs and on-line services for cephalometric analysis. However, only 7 of them use ANNs for automatic landmarking and image analysis. Also, there is not enough data to evaluate the accuracy of their work and convenience.

Diagnose Alzheimer's disease by combining 3D discrete wavelet transform and 3D moment invariants

The early stage of Alzheimer's disease (AD) is called mild cognitive impairment (MCI). According to the final progression of the disease, it can be divided into progressive MCI (pMCI) and stable MCI (sMCI). Clinical treatment shows that early treatment of MCI stage can effectively delay the progression of the disease and even complete recovery. Therefore, accurate diagnosis of AD and its early stage play an important guiding role in the treatment and delay of AD progression. Previous studies have shown that the data of different modalities of AD can reflect different pathological changes. Therefore, the accuracy of combining multi-modality data to classify AD is better than that of using single-modality to classify AD. Based on this, an AD diagnosis method is proposed based on 3D discrete wavelet transform (3D-DWT) and 3D moment invariants (3D-MIs) features from multi-modalities images. First, automatic anatomical landmark (AAL) atlas is used to identify the brain regions of interest (ROIs) from magnetic resonance image (MRI) and positron emission tomography (PET). Next, for each ROI, the 3D-DWT and 3D-MIs extract methods are used to extract features. Finally, a deep neural network with stacked autoencoders (SAE) is trained to detect AD. The experimental results show that, compared with the state-of-the-art AD/MCI classification algorithms based on multi-modality features, this method can significantly improve the classification performance of pMCI and sMCI classification tasks, which has an important guiding role in the early diagnosis of AD.

Comparison between a human judge and automatic landmark identification on digital models

Accurate landmark identification is a prerequisite for accurate and reliable biomedical image analysis. Orthodontic study models are valuable tools for diagnosis, treatment planning, and maintaining complete records. The purpose of this study was to evaluate the reliability and validity of a software program (Align Technology, Inc) as a tool for automatic landmark location. Using digital intraoral scans of 10 dental arches, 4 calibrated human judges independently located cusp tips and interproximal contacts. The same landmarks were automatically identified by the software. Intraclass correlation coefficient (Cronbach α), absolute mean errors, and regression analysis were calculated. In addition, Bland-Altman 95% confidence limits were also applied to the data to graphically display agreement on landmark identification between the human judges and the software. The intraclass correlation coefficient between the software and the human judges' average for the x-, y-, and z-coordinates for all landmarks was excellent, at 1.0, 1.0, and 0.98, respectively. The regression analysis and Bland-Altman plots show no systematic errors for agreement on landmark identification between the human judges and the software. Landmark location was nearly identical between the software and the human judges, making the methods interchangeable.

Automatic landmark identification for surgical 3d-navigation- A proposed method for marker-free dental surgical navigation systems.

This paper proposes a conceptual method to calculate the pose of a stereo-vision camera relative to an artificial mandible without additional markers. The general method for marker-free navigation has four steps: 1) parallel image acquisition by a stereo-vision camera, 2) automatic identification of 2d point pairs (landmark pairs) in a left and a right image, 3) calculation of related 3d points in the joint camera coordinate system and 4) matching of 3d points generated to a preoperative 3d model (i.e.,CT data based). To identify and compare landmarks in the acquired stereo images, well-known algorithms for landmark detection, description and matching were compared within the developed approach. Finally, the BRISK algorithm (Leutenegger S, Chli M, Siegwart RY. BRISK: Binary Robust invariant scalable keypoints. Proceedings of the IEEE International Conference on Computer Vision; 2011: 2548-2555) was used. The proposed method was implemented in MATLAB® and validated in vitro with one artificial mandible. The accuracy evaluation of the camera positions calculated resulted in an average deviation error of 1.45mm±0.76mm to the real camera displacement. This value was calculated using only stereo images with over 100 reconstructed landmark pairs each. This provides the basis for marker-free navigation.

Performance of a Convolutional Neural Network- Based Artificial Intelligence Algorithm for Automatic Cephalometric Landmark Detection.

The aim of this study is to develop an artificial intelligence model to detect cephalometric landmark automatically en- abling the automatic analysis of cephalometric radiographs which have a very important place in dental practice and is used routinely in the diagnosis and treatment of dental and skeletal disorders. In this study, 1620 lateral cephalograms were obtained and 21 landmarks were included. The coordinates of all landmarks in the 1620 films were obtained to establish a labeled data set: 1360 were used as a training set, 140 as a validation set, and 180 as a testing set. A convolutional neural network-based artificial intelligence algorithm for automatic cephalometric landmark detection was developed. Mean radial error and success detection rate within the range of 2 mm, 2.5 mm, 3 mm, and 4 mm were used to eval- uate the performance of the model. Presented artificial intelligence system (CranioCatch, Eskişehir, Turkey) could detect 21 anatomic landmarks in a lateral ceph- alometric radiograph. The highest success detection rate scores of 2 mm, 2.5 mm, 3 mm, and 4 mm were obtained from the sella point as 98.3, 99.4, 99.4, and 99.4, respectively. The mean radial error ± standard deviation value of the sella point was found as 0.616 ± 0.43. The lowest success detection rate scores of 2 mm, 2.5 mm, 3 mm, and 4 mm were obtained from the Gonion point as 48.3, 62.8, 73.9, and 87.2, respectively. The mean radial error ± standard deviation value of Gonion point was found as 8.304 ± 2.98. Although the success of the automatic landmark detection using the developed artificial intelligence model was not in- sufficient for clinical use, artificial intelligence-based cephalometric analysis systems seem promising to cephalometric analysis which provides a basis for diagnosis, treatment planning, and following-up in clinical orthodontics practice.

Automatic 3D Cranial Landmark Positioning based on Surface Curvature Feature using Machine Learning

Cranial anthropometric reference points (landmarks) play an important role in craniofacial reconstruction and identification. Knowledge to detect the position of landmarks is critical. This work aims to locate landmarks automatically. Landmarks positioning using Surface Curvature Feature (SCF) is inspired by conventional methods of finding landmarks based on morphometrical features. Each cranial landmark has a unique shape. With the appropriate 3D descriptors, the computer can draw associations between shapes and landmarks using machine learning. The challenge in classification and detection in three-dimensional space is to determine the model and data representation. Using three-dimensional raw data in machine learning is a serious volumetric issue. This work uses the Surface Curvature Feature as a three-dimensional descriptor. It extracts the local surface curvature shape into a projection sequential value (depth). A machine learning method is developed to determine the position of landmarks based on local surface shape characteristics. Classification is carried out from the top-n prediction probabilities for each landmark class, from a set of predictions, then filtered to get pinpoint accuracy. The landmark prediction points are hypothetically clustered in a particular area, so a cluster-based filter is appropriate to isolate them. The learning model successfully detected the landmarks, with the average distance between the prediction points and the ground truth being 0.0326 normalized units. The cluster-based filter is implemented to increase accuracy compared to the ground truth. Thus, SCF is suitable as a 3D descriptor of cranial landmarks.

Automated landmark identification on cone-beam computed tomography: Accuracy and reliability.

To evaluate the accuracy and reliability of a fully automated landmark identification (ALI) system as a tool for automatic landmark location compared with human judges. A total of 100 cone-beam computed tomography (CBCT) images were collected. After the calibration procedure, two human judges identified 53 landmarks in the x, y, and z coordinate planes on CBCTs using Checkpoint Software (Stratovan Corporation, Davis, Calif). The ground truth was created by averaging landmark coordinates identified by two human judges for each landmark. To evaluate the accuracy of ALI, the mean absolute error (mm) at the x, y, and z coordinates and mean error distance (mm) between the human landmark identification and the ALI were determined, and a successful detection rate was calculated. Overall, the ALI system was as successful at landmarking as the human judges. The ALI's mean absolute error for all coordinates was 1.57 mm on average. Across all three coordinate planes, 94% of the landmarks had a mean absolute error of less than 3 mm. The mean error distance for all 53 landmarks was 3.19 ± 2.6 mm. When applied to 53 landmarks on 100 CBCTs, the ALI system showed a 75% success rate in detecting landmarks within a 4-mm error distance range. Overall, ALI showed clinically acceptable mean error distances except for a few landmarks. The ALI was more precise than humans when identifying landmarks on the same image at different times. This study demonstrates the promise of ALI in aiding orthodontists with landmark identifications on CBCTs.

A lightweight keypoint matching framework for insect wing morphometric landmark detection

Geometric morphometrics has become an important approach in insect morphology studies because it capitalizes on advanced quantitative methods to analyze shape. Shape could be digitized as a set of landmarks from specimen images. However, the existing tools mostly require manual landmark digitization, and previous works on automatic landmark detection methods do not focus on implementation for end-users. Motivated by that, we propose a novel approach for automatic landmark detection, based on visual features of landmarks and keypoint matching techniques. While still archiving comparable accuracy to that of the state-of-the-art method, our framework requires less initial annotated data to build prediction model and runs faster. It is lightweight also in terms of implementation, in which a four-step workflow is provided with user-friendly graphical interfaces to produce correct landmark coordinates both by model prediction and manual correction. The utility iMorph is freely available at https://github.com/ha-usth/InsectWingLandmark, currently supporting Windows, MacOS, and Linux.

Anthropometric Landmarking for Diagnosis of Cranial Deformities: Validation of an Automatic Approach and Comparison with Intra- and Interobserver Variability.

Shape analysis of infant's heads is crucial to diagnose cranial deformities and evaluate head growth. Currently available 3D imaging systems can be used to create 3D head models, promoting the clinical practice for head evaluation. However, manual analysis of 3D shapes is difficult and operator-dependent, causing inaccuracies in the analysis. This study aims to validate an automatic landmark detection method for head shape analysis. The detection results were compared with manual analysis in three levels: (1) distance error of landmarks; (2) accuracy of standard cranial measurements, namely cephalic ratio (CR), cranial vault asymmetry index (CVAI), and overall symmetry ratio (OSR); and (3) accuracy of the final diagnosis of cranial deformities. For each level, the intra- and interobserver variability was also studied by comparing manual landmark settings. High landmark detection accuracy was achieved by the method in 166 head models. A very strong agreement with manual analysis for the cranial measurements was also obtained, with intraclass correlation coefficients of 0.997, 0.961, and 0.771 for the CR, CVAI, and OSR. 91% agreement with manual analysis was achieved in the diagnosis of cranial deformities. Considering its high accuracy and reliability in different evaluation levels, the method showed to be feasible for use in clinical practice for head shape analysis.

Automated ascending aorta delineation from ECG-gated computed tomography images.

The instrumental role of comprehensive geometrical quantification in contemporary, effective descriptions of aortic growth and disease is well established. General or specific purpose algorithms are being developed to provide automatic landmark detection and high accuracy measurements. In the present study, an objective method for automated delineation of the ascending aorta is introduced, based on geometrical properties of the aortic wall. In the proximal ascending aorta, the method identifies the sinotubular junction by tracing the mean surface curvature transition region from the origins of the coronary arteries to the location where the aorta acquires its tubular shape. In the distal ascending aorta, the brachiocephalic artery origin is defined by a split centreline cross section within the brachiocephalic artery-aortic arch bifurcation region. The method's accuracy of detection was quantified against the manual border identification performed by two experienced observers on 3D aortic reconstructions of 44 computed tomography examinations. Median (method, observer) distance and inclination measurements ranged from 0.89 [1.02] mm and 4.66 [5.07]°, respectively, in the proximal border, to 2.18 [2.39] mm and 7.13 [4.77]° in the distal. Accuracy of border detection was found to be high compared to interobserver variability and relevant automatic and manual methodology results previously reported in literature. Delineation of the ascending aorta on a three-dimensional aortic reconstruction with automated identification of the sinotubular junction (proximal border) and of the origin of the brachiocephalic artery (distal border).

Adjusting eye aspect ratio for strong eye blink detection based on facial landmarks.

Blink detection is an important technique in a variety of settings, including facial movement analysis and signal processing. However, automatic blink detection is very challenging because of the blink rate. This research work proposed a real-time method for detecting eye blinks in a video series. Automatic facial landmarks detectors are trained on a real-world dataset and demonstrate exceptional resilience to a wide range of environmental factors, including lighting conditions, face emotions, and head position. For each video frame, the proposed method calculates the facial landmark locations and extracts the vertical distance between the eyelids using the facial landmark positions. Our results show that the recognizable landmarks are sufficiently accurate to determine the degree of eye-opening and closing consistently. The proposed algorithm estimates the facial landmark positions, extracts a single scalar quantity by using Modified Eye Aspect Ratio (Modified EAR) and characterizing the eye closeness in each frame. Finally, blinks are detected by the Modified EAR threshold value and detecting eye blinks as a pattern of EAR values in a short temporal window. According to the results from a typical data set, it is seen that the suggested approach is more efficient than the state-of-the-art technique.

Bone anatomical landmark localization with cascaded spatial configuration network

Accurate localization of bone anatomical landmarks in medical images is of great significance for decision-making in surgical plans and orthopedic surgery visual navigation systems development. However, due to the high dimensionality and large size of medical images, current automatic anatomical landmarks detection methods still have issues in terms of accuracy, robustness, and efficiency. To improve the accuracy of bone anatomical landmark detection in medical images, a new network model with a two-step strategy (coarse localizing and fine localizing) was proposed in this study. By combining fully convolutional neural networks and the heatmap regression model, a cascaded spatial configuration network was designed to combine the global and local features of 3D image features and localize anatomical landmarks stepwise. The model was evaluated with a collected knee CT image dataset and a published spine CT image dataset. The results were compared to existing state-of-the-art models. The proposed method outperformed other models with an average error of 1.31 mm for knee landmarks and 5.31 mm for the localization of spine landmarks. The outlier rates at error radius 3 mm, 5 mm, and 7 mm are also smaller compared with other models, indicating good robustness of the model. Our proposed method provides a new neural network model with reasonably good accuracy and robustness with a limited computational cost for landmark localization tasks.