Characterizing Motor Control of Mastication With Soft Actor-Critic.

The human masticatory system is a complex functional unit characterized by a multitude of skeletal components, muscles, soft tissues, and teeth. Muscle activation dynamics cannot be directly measured on live human subjects due to ethical, safety, and accessibility limitations. Therefore, estimation of muscle activations and their resultant forces is a longstanding and active area of research. Reinforcement learning (RL) is an adaptive learning strategy which is inspired by the behavioral psychology and enables an agent to learn the dynamics of an unknown system via policy-driven explorations. The RL framework is a well-formulated closed-loop system where high capacity neural networks are trained with the feedback mechanism of rewards to learn relatively complex actuation patterns. In this work, we are building on a deep RL algorithm, known as the Soft Actor-Critic, to learn the inverse dynamics of a simulated masticatory system, i.e., learn the activation patterns that drive the jaw to its desired location. The outcome of the proposed training procedure is a parametric neural model which acts as the brain of the biomechanical system. We demonstrate the model's ability to navigate the feasible three-dimensional (3D) envelope of motion with sub-millimeter accuracies. We also introduce a performance analysis platform consisting of a set of quantitative metrics to assess the functionalities of a given simulated masticatory system. This platform assesses the range of motion, metabolic efficiency, the agility of motion, the symmetry of activations, and the accuracy of reaching the desired target positions. We demonstrate how the model learns more metabolically efficient policies by integrating a force regularization term in the RL reward. We also demonstrate the inverse correlation between the metabolic efficiency of the models and their agility and range of motion. The presented masticatory model and the proposed RL training mechanism are valuable tools for the analysis of mastication and other biomechanical systems. We see this framework's potential in facilitating the functional analyses aspects of surgical treatment planning and predicting the rehabilitation performance in post-operative subjects.

Can 3D imaging and digital software increase the ability to predict dental arch form after orthodontic treatment?

INTRODUCTION: This study aimed to evaluate the ability of dental clinicians to predict posttreatment dental arch forms in patients with malocclusion with the aid of 3D imaging and digital software in comparison with a conventional method. METHODS: Pretreatment and posttreatment dental plaster casts of 100 patients (200 maxillary models and 200 mandibular models) were selected. Three orthodontists selected the best-fitted archwires among 5 commercially available preformed nickel-titanium archwires using 2 methods. In the conventional method, they fit the archwires to pretreatment casts, and in the digital method, they fit the scanned wire to a 3D digital model, using Ortho-Aid, a locally developed 3D software, using clinical bracket points as reference for wire fitness. The predicted posttreatment archwire in each method was compared with the best-fit archwire on the actual posttreatment model of each patient in both methods, and the level of agreement was calculated. The interobserver agreement between the 3 orthodontists in each method was evaluated using intraclass correlation coefficient and the Dahlberg formula. RESULTS: Orthodontists predicted the final treatment outcome in 50% of cases using the conventional method and 58% using the digital method. However, the range of method error was significantly higher in the conventional method (0.425-3.853 mm for the conventional vs 0.451-0.584 mm for the digital). CONCLUSIONS: Although the clinicians' ability to predict the final dental arch form after orthodontic treatment and the agreement between clinicians increased by the use of digital equipment, orthodontists can predict the final arch form in about 60% of patients.

Cardiac Phase Detection in Echocardiograms With Densely Gated Recurrent Neural Networks and Global Extrema Loss.

Accurate detection of end-systolic (ES) and end-diastolic (ED) frames in an echocardiographic cine series can be difficult but necessary pre-processing step for the development of automatic systems to measure cardiac parameters. The detection task is challenging due to variations in cardiac anatomy and heart rate often associated with pathological conditions. We formulate this problem as a regression problem and propose several deep learning-based architectures that minimize a novel global extrema structured loss function to localize the ED and ES frames. The proposed architectures integrate convolution neural networks (CNNs)-based image feature extraction model and recurrent neural networks (RNNs) to model temporal dependencies between each frame in a sequence. We explore two CNN architectures: DenseNet and ResNet, and four RNN architectures: long short-term memory, bi-directional LSTM, gated recurrent unit (GRU), and Bi-GRU, and compare the performance of these models. The optimal deep learning model consists of a DenseNet and GRU trained with the proposed loss function. On average, we achieved 0.20 and 1.43 frame mismatch for the ED and ES frames, respectively, which are within reported inter-observer variability for the manual detection of these frames.

Fiducial-based fusion of 3D dental models with magnetic resonance imaging.

PURPOSE: Magnetic resonance imaging (MRI) is widely used in study of maxillofacial structures. While MRI is the modality of choice for soft tissues, it fails to capture hard tissues such as bone and teeth. Virtual dental models, acquired by optical 3D scanners, are becoming more accessible for dental practice and are starting to replace the conventional dental impressions. The goal of this research is to fuse the high-resolution 3D dental models with MRI to enhance the value of imaging for applications where detailed analysis of maxillofacial structures are needed such as patient examination, surgical planning, and modeling. METHODS: A subject-specific dental attachment was digitally designed and 3D printed based on the subject's face width and dental anatomy. The attachment contained 19 semi-ellipsoidal concavities in predetermined positions where oil-based ellipsoidal fiducial markers were later placed. The MRI was acquired while the subject bit on the dental attachment. The spatial position of the center of mass of each fiducial in the resultant MR Image was calculated by averaging its voxels' spatial coordinates. The rigid transformation to fuse dental models to MRI was calculated based on the least squares mapping of corresponding fiducials and solved via singular-value decomposition. RESULTS: The target registration error (TRE) of the proposed fusion process, calculated in a leave-one-fiducial-out fashion, was estimated at 0.49 mm. The results suggest that 6-9 fiducials suffice to achieve a TRE of equal to half the MRI voxel size. CONCLUSION: Ellipsoidal oil-based fiducials produce distinguishable intensities in MRI and can be used as registration fiducials. The achieved accuracy of the proposed approach is sufficient to leverage the merged 3D dental models with the MRI data for a finer analysis of the maxillofacial structures where complete geometry models are needed.

Minimizing fiducial localization error using sphere-based registration in jaw tracking.

Some of the jaw tracking methods may be limited in terms of their accuracy or clinical applicability. This article introduces the sphere-based registration method to minimize the fiducial (reference landmark) localization error (FLE) in tracking and coregistration of physical and virtual dental models, to enable an effective clinical analysis of the patient's masticatory functions. In this method, spheres (registration fiducials) are placed on the corresponding polygonal concavities of the physical and virtual dental models based on the geometrical principle that establishes a unique spatial position for a sphere inside an infinite trihedron. The experiments in this study were implemented using an optical system which tracked active tracking markers connected to the upper and lower dental casts. The accuracy of the tracking workflow was confirmed in vitro, based on comparing virtually calculated interocclusal regions of close proximity against the physical interocclusal impressions. The target registration error of the tracking was estimated based on the leave-one-sphere-out method to be the sum of the error of the sensors, i.e., the FLE was negligible. Moreover, based on a user study, the FLE of the proposed method was confirmed to be 5 and 10 times smaller than the FLE of conventional fiducial selections on the physical and virtual models, respectively. The proposed tracking method is non-invasive and appears to be sufficiently accurate. To conclude, the proposed registration and tracking principles can be extended to track any biomedical and non-biomedical geometries that contain polygonal concavities.

Correlation of Vitamin D status and orthodontic-induced external apical root resorption.

BACKGROUND: Adequate Vitamin D is essential for dental and skeletal health in children and adult. The purpose of this study was to assess the correlation of serum Vitamin D level with external-induced apical root resorption (EARR) following fixed orthodontic treatment. MATERIALS AND METHODS: In this cross-sectional study, the prevalence of Vitamin D deficiency (defined by25-hydroxyvitamin-D) was determined in 34 patients (23.5% male; age range 12-23 years; mean age 16.63 ± 2.84) treated with fixed orthodontic treatment. Root resorption of four maxillary incisors was measured using before and after periapical radiographs (136 measured teeth) by means of a design-to-purpose software to optimize data collection. Teeth with a maximum percentage of root resorption (%EARR) were indicated as representative root resorption for each patient. A multiple linear regression model and Pearson correlation coefficient were used to assess the association of Vitamin D status and observed EARR. P < 0.05 was considered statistically significant. RESULTS: The Pearson coefficient between these two variables was determined about 0.15 (P = 0.38). Regression analysis revealed that Vitamin D status of the patients demonstrated no significant statistical correlation with EARR, after adjustment of confounding variables using linear regression model (P > 0.05). CONCLUSION: This study suggests that Vitamin D level is not among the clinical variables that are potential contributors for EARR. The prevalence of Vitamin D deficiency does not differ in patients with higher EARR. These data suggest the possibility that Vitamin D insufficiency may not contribute to the development of more apical root resorption although this remains to be confirmed by further longitudinal cohort studies.

Automatic Quality Assessment of Echocardiograms Using Convolutional Neural Networks: Feasibility on the Apical Four-Chamber View.

Echocardiography (echo) is a skilled technical procedure that depends on the experience of the operator. The aim of this paper is to reduce user variability in data acquisition by automatically computing a score of echo quality for operator feedback. To do this, a deep convolutional neural network model, trained on a large set of samples, was developed for scoring apical four-chamber (A4C) echo. In this paper, 6,916 end-systolic echo images were manually studied by an expert cardiologist and were assigned a score between 0 (not acceptable) and 5 (excellent). The images were divided into two independent training-validation and test sets. The network architecture and its parameters were based on the stochastic approach of the particle swarm optimization on the training-validation data. The mean absolute error between the scores from the ultimately trained model and the expert's manual scores was 0.71 ± 0.58. The reported error was comparable to the measured intra-rater reliability. The learned features of the network were visually interpretable and could be mapped to the anatomy of the heart in the A4C echo, giving confidence in the training result. The computation time for the proposed network architecture, running on a graphics processing unit, was less than 10 ms per frame, sufficient for real-time deployment. The proposed approach has the potential to facilitate the widespread use of echo at the point-of-care and enable early and timely diagnosis and treatment. Finally, the approach did not use any specific assumptions about the A4C echo, so it could be generalizable to other standard echo views.