Landmark Positions Research Articles

Application of Artificial Intelligence (AI) in a Cephalometric Analysis: A Narrative Review.

In recent years, the application of artificial intelligence (AI) has become more and more widespread in medicine and dentistry. It may contribute to improved quality of health care as diagnostic methods are getting more accurate and diagnostic errors are rarer in daily medical practice. The aim of this paper was to present data from the literature on the effectiveness of AI in orthodontic diagnostics based on the analysis of lateral cephalometric radiographs. A review of the literature from 2009 to 2023 has been performed using PubMed, Medline, Scopus and Dentistry & Oral Sciences Source databases. The accuracy of determining cephalometric landmarks using widely available commercial AI-based software and advanced AI algorithms was presented and discussed. Most AI algorithms used for the automated positioning of landmarks on cephalometric radiographs had relatively high accuracy. At the same time, the effectiveness of using AI in cephalometry varies depending on the algorithm or the application type, which has to be accounted for during the interpretation of the results. In conclusion, artificial intelligence is a promising tool that facilitates the identification of cephalometric landmarks in everyday clinical practice, may support orthodontic treatment planning for less experienced clinicians and shorten radiological examination in orthodontics. In the future, AI algorithms used for the automated localisation of cephalometric landmarks may be more accurate than manual analysis.

Development of a Human-Robot Interaction System for Industrial Applications

The use of robots is increasing day by day. In this study, it was aimed to develop manufacturing-assistant robot software for small production plants involving non-mass production. The main purpose of this study is to eliminate the difficulty of recruiting an expert robot operator thanks to the developed software and to facilitate the use of robots for non-experts. The developed software consists of three parts: the convolutional neural network (CNN), process selection-trajectory generation, and trajectory regulation modules. Before the operations in these modules are executed, operators record the desired process and the trajectory of the process in the video by hand gestures and index finger. Then recorded video is separated into images. The separated images are classified by the CNN module and the positions of landmarks (joint and fingernail of index finger) were calculated by the same module and using the images. Eight different pre-trained CNN structures were tested in the CNN module, and the best result Xception structure (test loss = 0.0051) was used. The desired process was determined and the trajectory of the process was created with the CNN output data. The connection of the generated trajectory with the object was detected by the trajectory regulation module, and unnecessary trajectory parts were cleaned. Regulated trajectory and desired tasks such as welding or sealing were simulated via an industrial robot in a simulation environment. As a result, an industrial robot could be programmed by non-expert operators for companies whose production line is not standard by using the developed software.

SDMT: Spatial Dependence Multi-Task Transformer Network for 3D Knee MRI Segmentation and Landmark Localization

Knee segmentation and landmark localization from 3D MRI are two significant tasks for diagnosis and treatment of knee diseases. With the development of deep learning, Convolutional Neural Network (CNN) based methods have become the mainstream. However, the existing CNN methods are mostly single-task methods. Due to the complex structure of bone, cartilage and ligament in the knee, it is challenging to complete the segmentation or landmark localization alone. And establishing independent models for all tasks will bring difficulties for surgeon's clinical using. In this paper, a Spatial Dependence Multi-task Transformer (SDMT) network is proposed for 3D knee MRI segmentation and landmark localization. We use a shared encoder for feature extraction, then SDMT utilizes the spatial dependence of segmentation results and landmark position to mutually promote the two tasks. Specifically, SDMT adds spatial encoding to the features, and a task hybrided multi-head attention mechanism is designed, in which the attention heads are divided into the inter-task attention head and the intra-task attention head. The two attention head deal with the spatial dependence between two tasks and correlation within the single task, respectively. Finally, we design a dynamic weight multi-task loss function to balance the training process of two task. The proposed method is validated on our 3D knee MRI multi-task datasets. Dice can reach 83.91% in the segmentation task, and MRE can reach 2.12 mm in the landmark localization task, it is competitive and superior over other state-of-the-art single-task methods.

Planning and control of the ship curvilinear route

The possibility of applying the traditional navigation parameters used in pilotage (bearing and distance), as well as their sum and difference for planning and controlling the ship curvilinear route in coastal waters is being investigated. Mathematical apparatus is based on the classical navigation methods such as the theory of isolines, the lines of position, the principles of route planning, as well as the approximation of the curvilinear route. The mathematical justification of the circle arcs, ellipse and hyperbola used as the approximation lines of both the ship curvilinear route and the control isolines is given. The methods for estimating the vessel approaching to the point of the beginning and end of the turn and for controlling the ship movement along the planned path by measuring the navigational parameters are proposed. The problems of the physical and mathematical feasibility of the route arising at the junction points of the straight and curvilinear parts of the ship route are recommended to be resolved on the principles of transition curves (clothoids), considering the maneuvering characteristics of the vessel. The main theses of the research are supported by the graphical interpretation while the given expressions are ready for practical application. The formalization of the proposed methods in both automatic navigation systems and autonomous ship control systems will allow the navigator on the bases of the configuration of the relative position of landmarks and the ship curvilinear route to solve the problems of processing relevant navigation information in coastal and congested waters more efficiently in conjunction with the traditional pilotage methods, which is especially important for advanced autonomous navigation.

A store-and-forward cloud-based telemonitoring system for automatic assessing dysarthria evolution in neurological diseases from video-recording analysis

Background and objectives:Patients suffering from neurological diseases may develop dysarthria, a motor speech disorder affecting the execution of speech. Close and quantitative monitoring of dysarthria evolution is crucial for enabling clinicians to promptly implement patients’ management strategies and maximizing effectiveness and efficiency of communication functions in term of restoring, compensating or adjusting. In the clinical assessment of orofacial structures and functions, at rest condition or during speech and non-speech movements, a qualitative evaluation is usually performed, throughout visual observation. Methods:To overcome limitations posed by qualitative assessments, this work presents a store-and-forward self-service telemonitoring system that integrates, within its cloud architecture, a convolutional neural network (CNN) for analyzing video recordings acquired by individuals with dysarthria. This architecture – called facial landmark Mask RCNN – aims at locating facial landmarks as a prior for assessing the orofacial functions related to speech and examining dysarthria evolution in neurological diseases. Results:When tested on the Toronto NeuroFace dataset, a publicly available annotated dataset of video recordings from patients with amyotrophic lateral sclerosis (ALS) and stroke, the proposed CNN achieved a normalized mean error equal to 1.79 on localizing the facial landmarks. We also tested our system in a real-life scenario on 11 bulbar-onset ALS subjects, obtaining promising outcomes in terms of facial landmark position estimation. Discussion and conclusions:This preliminary study represents a relevant step towards the use of remote tools to support clinicians in monitoring the evolution of dysarthria.

Accuracy and clinical validity of automated cephalometric analysis using convolutional neural networks.

This study aimed to assess the error range of cephalometric measurements based on the landmarks detected using cascaded CNNs and determine how horizontal and vertical positional errors of individual landmarks affect lateral cephalometric measurements. In total, 120 lateral cephalograms were obtained consecutively from patients (mean age, 32.5 ± 11.6) who visited the Asan Medical Center, Seoul, Korea, for orthodontic treatment between 2019 and 2021. An automated lateral cephalometric analysis model previously developed from a nationwide multi-centre database was used to digitize the lateral cephalograms. The horizontal and vertical landmark position error attributable to the AI model was defined as the distance between the landmark identified by the human and that identified by the AI model on the x- and y-axes. The differences between the cephalometric measurements based on the landmarks identified by the AI model vs those identified by the human examiner were assessed. The association between the lateral cephalometric measurements and the positioning errors in the landmarks comprising the cephalometric measurement was assessed. The mean difference in the angular and linear measurements based on AI vs human landmark localization was .99 ± 1.05°, and .80 ± .82 mm, respectively. Significant differences between the measurements derived from AI-based and human localization were observed for all cephalometric variables except SNA, pog-Nperp, facial angle, SN-GoGn, FMA, Bjork sum, U1-SN, U1-FH, IMPA, L1-NB (angular) and interincisal angle. The errors in landmark positions, especially those that define reference planes, may significantly affect cephalometric measurements. The possibility of errors generated by automated lateral cephalometric analysis systems should be considered when using such systems for orthodontic diagnoses.

Optimization of Directional Landmark Deployment for Visual Observer on SE(3)

An optimization method is proposed in this paper for novel deployment of given number of directional landmarks (position and orientation) within a given region in the 3-D task space. This new deployment technique is built on the geometric models of both landmarks and the monocular camera. In particular, a new concept of Multiple Coverage Probability (MCP) is defined to characterize the probability of at least <inline-formula><tex-math notation="LaTeX">$\bm n$</tex-math></inline-formula> landmarks being covered simultaneously by a camera at a fixed position. The optimization is conducted with respect to the position and orientation of the given number of landmarks to maximize MCP through globally exploration of the given 3-D space. By adopting the elimination genetic algorithm, the final deployment of landmarks can be obtained, which are then applied to improve the convergent performance of the visual observer on <i>SE</i>(3) as a demonstration example. Both simulation and experimental results are presented to validate the effectiveness of the proposed landmark deployment optimization method.

Can Fracture Reduction be Attempted Through a 3D-Printed Guide Template Without Maxillomandibular Fixation?

Computer-aided design and manufacturing is widely used in clinical practice. This technology may change existing methods for mandibular fracture management. The purpose of this in-vitro study was to determine if the reduction for mandibular symphysis fracture is performed without maxillomandibular fixation (MMF) using 3-dimensional (3D)-printed template. This was an in-vitro study and had the character of a proof-of-concept study. The study was planned using the existing 20 pairs of intraoral scan and computed tomography data. The mandibular model STL file was created by merging the STL file obtained for the bimaxillary dentitions with the computed tomography DICOM file, and this was set as the original model. In the original model, STL file of fracture model of mandibular symphysis was created using computer-aided design. A template similar to a wafer or an implant guide was manufactured from restoring the own occlusion, and the mandibular fracture model was reduced and fixed using the 3D-printed template and wire, and this was set as the experimental group. The 3D coordinate system error was measured at 6 landmarks and statistically compared using scan data between models of the groups. Reduction techniques with MMF or without MMF using guide template for mandibular fracture model. The 3D coordinate system error (mm). The position of landmarks. The Mann-Whitney U test, student's t-test, and the Kruskal-Wallis test were used to analyze the coordinate errors between the landmarks. A P value of < .05 was considered statistically significant. The 3D error value of the control and experimental group were 1.06±0.63mm (range: 0.11 to 2.92mm) and 0.96±0.48mm (range: 0.2 to 2.95mm), respectively. There was no statistical difference between the control and experimental group. There was a statistically significant difference in the lower 2 and lower 3 landmarks compared to the upper 1 (P=.001 and .000, respectively) before and after the reduction in the experimental group. This study demonstrates that the reduction using a 3D-printed guide template for the mandibular symphysis fracture could be possible even without the MMF.

Evaluating 3D human face reconstruction from a frontal 2D image, focusing on facial regions associated with foetal alcohol syndrome

Foetal alcohol syndrome (FAS) is a preventable condition caused by maternal alcohol consumption during pregnancy. The FAS facial phenotype is an important factor for diagnosis, alongside central nervous system impairments and growth abnormalities. Current methods for analysing the FAS facial phenotype rely on 3D facial image data, obtained from costly and complex surface scanning devices. An alternative is to use 2D images, which are easy to acquire with a digital camera or smart phone. However, 2D images lack the geometric accuracy required for accurate facial shape analysis. Our research offers a solution through the reconstruction of 3D human faces from single or multiple 2D images. We have developed a framework for evaluating 3D human face reconstruction from a single-input 2D image using a 3D face model for potential use in FAS assessment. We first built a generative morphable model of the face from a database of registered 3D face scans with diverse skin tones. Then we applied this model to reconstruct 3D face surfaces from single frontal images using a model-driven sampling algorithm. The accuracy of the predicted 3D face shapes was evaluated in terms of surface reconstruction error and the accuracy of FAS-relevant landmark locations and distances. Results show an average root mean square error of 2.62 mm. Our framework has the potential to estimate 3D landmark positions for parts of the face associated with the FAS facial phenotype. Future work aims to improve on the accuracy and adapt the approach for use in clinical settings. Significance: Our study presents a framework for constructing and evaluating a 3D face model from 2D face scans and evaluating the accuracy of 3D face shape predictions from single images. The results indicate low generalisation error and comparability to other studies. The reconstructions also provide insight into specific regions of the face relevant to FAS diagnosis. The proposed approach presents a potential cost-effective and easily accessible imaging tool for FAS screening, yet its clinical application needs further research.

Automatic Assessment of Lower-Limb Alignment from Computed Tomography.

Preoperative planning of lower-limb realignment surgical procedures necessitates the quantification of alignment parameters by using landmarks placed on medical scans. Conventionally, alignment measurements are performed on 2-dimensional (2D) standing radiographs. To enable fast and accurate 3-dimensional (3D) planning of orthopaedic surgery, automatic calculation of the lower-limb alignment from 3D bone models is required. The goal of this study was to develop, validate, and apply a method that automatically quantifies the parameters defining lower-limb alignment from computed tomographic (CT) scans. CT scans of the lower extremities of 50 subjects were both manually and automatically segmented. Thirty-two manual landmarks were positioned twice on the bone segmentations to assess intraobserver reliability in a subset of 20 subjects. The landmarks were also positioned automatically using a shape-fitting algorithm. The landmarks were then used to calculate 25 angles describing the lower-limb alignment for all 50 subjects. The mean absolute difference (and standard deviation) between repeat measurements using the manual method was 2.01 ± 1.64 mm for the landmark positions and 1.05° ± 1.48° for the landmark angles, whereas the mean absolute difference between the manual and fully automatic methods was 2.17 ± 1.37 mm for the landmark positions and 1.10° ± 1.16° for the landmark angles. The manual method required approximately 60 minutes of manual interaction, compared with 12 minutes of computation time for the fully automatic method. The intraclass correlation coefficient showed good to excellent reliability between the manual and automatic assessments for 23 of 25 angles, and the same was true for the intraobserver reliability in the manual method. The mean for the 50 subjects was within the expected range for 18 of the 25 automatically calculated angles. We developed a method that automatically calculated a comprehensive range of 25 measurements that defined lower-limb alignment in considerably less time, and with differences relative to the manual method that were comparable to the differences between repeated manual assessments. This method could thus be used as an efficient alternative to manual assessment of alignment. Diagnostic Level III . See Instructions for Authors for a complete description of levels of evidence.

A Semi-Automatic Method on a Small Italian Sample for Estimating Sex Based on the Shape of the Crown of the Maxillary Posterior Teeth

Teeth are known to be reliable substrates for human identification and are endowed with significant sexual dimorphism not only in the size but also in the shape of the crowns. In the preliminary phase of our study (already published in 2021), a novel sex estimation method based on dental morphometric geometric (GMA) analysis combined with the artificial neural network (ANN) was developed and validated on a single dental element (first upper premolar) with an accuracy rate of 80%. This study aims to experiment and validate the combination of GMA-ANN on the upper first and second left premolars and the upper left first molar to obtain a reliable classification model based on the sexual dimorphic traits of multiple maxillary teeth of Caucasian Italian adults (115 males and 115 females). A general procrustes superimposition (GPS) and principal component analysis (PCA) were performed to study the shape variance between the sexes and to reduce the data variations. The "set-aside" approach was used to validate the accuracy of the proposed ANN. As the main findings, the proposed method correctly classified 94% of females and 68% of males from the test sample and the overall accuracy gained was 82%, higher than the odontometric methods that similarly consider multiple teeth. The shape variation between male and female premolars represents the best dimorphic feature compared with the first upper molar. Future research could overcome some limitations by considering a larger sample of subjects and experimenting with the use of computer vision for automatic landmark positioning and should verify the present evidence in samples with different ancestry.

Automatic landmark identification in cone-beam computed tomography.

To present and validate an open-source fully automated landmark placement (ALICBCT) tool for cone-beam computed tomography scans. One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position. Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU. The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.

Efficient ear alignment using a two‐stack hourglass network

AbstractEar images have been shown to be a reliable modality for biometric recognition with desirable characteristics, such as high universality, distinctiveness, measurability and permanence. While a considerable amount of research has been directed towards ear recognition techniques, the problem of ear alignment is still under‐explored in the open literature. Nonetheless, accurate alignment of ear images, especially in unconstrained acquisition scenarios, where the ear appearance is expected to vary widely due to pose and view point variations, is critical for the performance of all downstream tasks, including ear recognition. Here, the authors address this problem and present a framework for ear alignment that relies on a two‐step procedure: (i) automatic landmark detection and (ii) fiducial point alignment. For the first (landmark detection) step, the authors implement and train a Two‐Stack Hourglass model (2‐SHGNet) capable of accurately predicting 55 landmarks on diverse ear images captured in uncontrolled conditions. For the second (alignment) step, the authors use the Random Sample Consensus (RANSAC) algorithm to align the estimated landmark/fiducial points with a pre‐defined ear shape (i.e. a collection of average ear landmark positions). The authors evaluate the proposed framework in comprehensive experiments on the AWEx and ITWE datasets and show that the 2‐SHGNet model leads to more accurate landmark predictions than competing state‐of‐the‐art models from the literature. Furthermore, the authors also demonstrate that the alignment step significantly improves recognition accuracy with ear images from unconstrained environments compared to unaligned imagery.

Abstract No. 49 Motion Compensation in 3D MRI-US Fusion Using Fast Deformable Registration: A Feasibility Study for Real-Time Intervention

The heterogeneity of hepatocellular carcinoma may be better seen with magnetic resonance imaging (MRI) compared with CT due to its high soft tissue contrast, providing precise tumor targets during therapy, while ultrasound (US) remains as the imaging modality for real-time guidance. Image fusion methods existing in clinical workflows involve rigid registration only and fail to compensate for liver motion in US. In this work, we present a hybrid deformable fusion method to align pre-interventional 3D MRI and interventional 3D US in real-time. Multimodal pre-interventional MRI (pMRI) and US (pUS) volumes were obtained from 3 human volunteers using a simultaneous MRI-US acquisition system, with an MR-compatible, hands-free US probe. pMRI and pUS volumes were aligned using conventional deformable registration, as it is not time critical. Deep learning (DL)–based registration was used for real-time fusion of pUS to iUS, and consecutive iUS volumes in near real time. The predicted DL deformation fields were used to deform the pMRI to match each US volume. US data with respiration were collected at a temporal resolution of 4.2 volumes/sec. 1600 US volumes from one volunteer was used for DL training. The hybrid deformable registration method was evaluated for pMRI and 20 US volume alignments for each volunteer. Mean Euclidean distance error between expert placed landmarks and predicted positions of landmarks after image alignment were computed. Table 1 shows the mean landmark error (LE) and computation times for the hybrid (HDR) and conventional deformable registration (CDR) method aligning pMRI and 20 US volumes. Feasibility of a multimodal hybrid deformable registration method with clinically acceptable registration accuracy and low latency was shown. The method for motion compensation may improve tumor targeting in interventional procedures including liver ablation.

EKF-SLAM for Quadcopter Using Differential Flatness-Based LQR Control

SLAM (Simultaneous Localization And Mapping) in unmanned aerial vehicles can be an advantageous proposition during dangerous missions where aggressive maneuvers are paramount. This paper proposes to achieve it for a quadcopter using a differential flatness-based linear quadratic regulator while utilizing sensor measurements of an inertial measurement unit and light detection and ranging considering sensors’ constraints, such as a limited sensing range and field of view. Additionally, a strategy to reduce the computational effort of Extended Kalman Filter-based SLAM (EKF-SLAM) is proposed. To validate the performance of the proposed approach, this work considers a quadcopter traversing an 8-shape trajectory for two scenarios of known and unknown landmarks. The estimation errors for the quadcopter states are comparable for both cases. The accuracy of the proposed method is evident from the Root-Mean-Square Errors (RMSE) of 0.04 m, 0.04 m/s, and 0.34 deg for the position, velocity, and attitude estimation of the quadcopter, respectively, including the RMSE of 0.03 m for the landmark position estimation. Lastly, the averaged computational time for each step of EKF-SLAM with respect to the number of landmarks can help to strategically choose the respective number of landmarks for each step to maximize the use of sensor data and improve performance.

The “True Colours” of Golden Loaches (Teleostei: Cobitidae)

Loaches of the genus Sabanejewia are model organisms for many ichthyologic studies focusing on morphological and colour variation. The bright lateral spots—a part of the mimicry of this fish—cause a taxonomic puzzle. Common practice is that morphometric and molecular studies lack habitat assessments of species originating from different environments. In this study, we analysed body shape and colour variation within two species of Sabanejewia in order to reveal whether they are more affected by phylogeny or environmental conditions. The environmental parameters were obtained using satellite mapping tools, body shape using geometric morphometry, and the molecular identification of specimens using an analysis of mitochondrial DNA (sequence of the cytochrome b gene). Generalized linear mixed models were used for the analysis of lateral spot numbers, and principal components analysis to describe the changes in landmark position defined by the permutation tests. Results show a significant impact of the locality elevation and specimen’s sex on the change of the body shape. We identified significant differences in the number of lateral spots, which are considered mimicry variation across an elevation gradient. Morphological differences of Sabanejewia spp. vary with ecological factors along the river continuum.

EYE ASPECT RATIO ADJUSTMENT DETECTION FOR STRONG BLINKING SLEEPINESS BASED ON FACIAL LANDMARKS WITH EYE-BLINK DATASET

&lt;span lang="id"&gt;Blink detection is an important technique in a variety of settings, including facial motion analysis and signal processing. However, automatic blink detection is challenging due to its blink rate. This paper proposes a real-time method for detecting eye blinks in a video series. The method is based on automatic facial landmark detection trained on real-world datasets and demonstrates robustness against various environmental factors, including lighting conditions, facial emotions, and head position. The proposed algorithm calculates the position of facial landmarks, extracts scalar values using the Eye Aspect Ratio (EAR), and characterises eye proximity in each frame. For each video frame, the proposed method calculates the location of the facial landmark and extracts the vertical distance between the eyelids using the position of the facial landmark. Blinks are detected by using the EAR threshold value and recognising the pattern of EAR values in a short temporal window. According to the results from a common data set, it is shown that the proposed approach is more efficient than state-of-the-art techniques.&lt;/span&gt;

Automatic Detection and Measurement of Renal Cysts in Ultrasound Images: A Deep Learning Approach.

Ultrasonography is widely used for diagnosis of diseases in internal organs because it is nonradioactive, noninvasive, real-time, and inexpensive. In ultrasonography, a set of measurement markers is placed at two points to measure organs and tumors, then the position and size of the target finding are measured on this basis. Among the measurement targets of abdominal ultrasonography, renal cysts occur in 20-50% of the population regardless of age. Therefore, the frequency of measurement of renal cysts in ultrasound images is high, and the effect of automating measurement would be high as well. The aim of this study was to develop a deep learning model that can automatically detect renal cysts in ultrasound images and predict the appropriate position of a pair of salient anatomical landmarks to measure their size. The deep learning model adopted fine-tuned YOLOv5 for detection of renal cysts and fine-tuned UNet++ for prediction of saliency maps, representing the position of salient landmarks. Ultrasound images were input to YOLOv5, and images cropped inside the bounding box and detected from the input image by YOLOv5 were input to UNet++. For comparison with human performance, three sonographers manually placed salient landmarks on 100 unseen items of the test data. These salient landmark positions annotated by a board-certified radiologist were used as the ground truth. We then evaluated and compared the accuracy of the sonographers and the deep learning model. Their performances were evaluated using precision-recall metrics and the measurement error. The evaluation results show that the precision and recall of our deep learning model for detection of renal cysts are comparable to standard radiologists; the positions of the salient landmarks were predicted with an accuracy close to that of the radiologists, and in a shorter time.

An automatic facial landmarking for children with rare diseases.

Two to three thousand syndromes modify facial features: their screening requires the eye of an expert in dysmorphology. A widely used tool in shape characterization is geometric morphometrics based on landmarks, which are precise and reproducible anatomical points. Landmark positioning is user dependent and time consuming. Many automatic landmarking tools are currently available but do not work for children, because they have mainly been trained using photographic databases of healthy adults. Here, we developed a method for building an automatic landmarking pipeline for frontal and lateral facial photographs as well as photographs of external ears. We evaluated the algorithm on patients diagnosed with Treacher Collins (TC) syndrome as it is the most frequent mandibulofacial dysostosis in humans and is clinically recognizable although highly variable in severity. We extracted photographs from the photographic database of the maxillofacial surgery and plastic surgery department of Hôpital Necker-Enfants Malades in Paris, France with the diagnosis of TC syndrome. The control group was built from children admitted for craniofacial trauma or skin lesions. After testing two methods of object detection by bounding boxes, a Haar Cascade-based tool and a Faster Region-based Convolutional Neural Network (Faster R-CNN)-based tool, we evaluated three different automatic annotation algorithms: the patch-based active appearance model (AAM), the holistic AAM, and the constrained local model (CLM). The final error corresponding to the distance between the points placed by automatic annotation and those placed by manual annotation was reported. We included, respectively, 1664, 2044, and 1375 manually annotated frontal, profile, and ear photographs. Object recognition was optimized with the Faster R-CNN-based detector. The best annotation model was the patch-based AAM (p < 0.001 for frontal faces, p=0.082 for profile faces and p < 0.001 for ears). This automatic annotation model resulted in the same classification performance as manually annotated data. Pretraining on public photographs did not improve the performance of the model. We defined a pipeline to create automatic annotation models adapted to faces with congenital anomalies, an essential prerequisite for research in dysmorphology.

A Review on Eye Aspect Ratio Technique

One of the most common factors that contributes to the deaths and injuries caused by road accidents is drowsiness. It can also affect the performance of a driver. Detecting eye blinks is an essential part of various driver safety applications. The rapid pace of blinking makes it incredibly challenging to detect eye blinks automatically. This paper presents a method that can be used to identify eye blinks captured by a camera. The suggested method takes into account the facial landmarks for each frame and then takes the distance between the eyes from these landmarks. The proposed technique calculates the positions of the facial landmarks, uses the Eye Aspect Ratio (EAR) to extract a single scalar quantity, and determines the eye closeness in each frame.