Search

International audience

Skull prediction from the head is a challenging issue toward a cost-effective therapeutic solution for facial disorders. This issue was initially studied in our previous work using full head-to-skull relationship learning. However, the head-skull thickness topology is locally shaped, especially in the face region. Thus, the objective of the present study was to enhance our head-to-skull prediction problem by using local topological features for training and predicting. Head and skull feature points were sampled on 329 head and skull models from computed tomography (CT) images. These feature points were classified into the back and facial topologies. Head-to-skull relations were trained using the partial least square regression (PLSR) models separately in the two topologies. A hyperparameter tuning process was also conducted for selecting optimal parameters for each training model. Thus, a new skull could be generated so that its shape was statistically fitted with the target head. Mean errors of the predicted skulls using the topology-based learning method were better than those using the non-topology-based learning method. After tenfold cross-validation, the mean error was enhanced 36.96% for the skull shapes and 14.17% for the skull models. Mean error in the facial skull region was especially improved with 4.98%. The mean errors were also improved 11.71% and 25.74% in the muscle attachment regions and the back skull regions respectively. Moreover, using the enhanced learning strategy, the errors (mean ± SD) for the best and worst prediction cases are from 1.1994 ± 1.1225 mm (median: 0.9036, coefficient of multiple determination (R

Facial palsy patients or patients with facial transplantation have abnormal facial motion due to altered facial muscle functions and nerve damage. Computer-aided system and physics-based models have been developed to provide objective and quantitative information. However, the predictive capacity of these solutions is still limited to explore the facial motion patterns with emerging properties. The present study aims to couple the reinforcement learning and the finite element modeling for facial motion learning and prediction.A novel modeling workflow for learning facial motion was developed. A physically-based model of the face within the Artisynth modeling platform was used. Information exchange protocol was proposed to link reinforcement learning and rigid multi-bodies dynamics outcomes. Two reinforcement learning algorithms (deep deterministic policy gradient (DDPG) and Twin-delayed DDPG (TD3)) were used and implemented to drive the simulations of symmetry-oriented and smile movements. Numerical outcomes were compared to experimental observations (Bosphorus database) for evaluation and validation purposes.As result, after more than 100 episodes of exploring the environment, the agent starts to learn from previous trials and can find the optimal policy after more than 300 episodes of training. Regarding the symmetry-oriented motion, the muscle excitations predicted by the trained agent help to increase the value of reward from R = -2.06 to R = -0.23, which counts for ∼89% improvement of the symmetry value of the face. For smile-oriented motion, two points at the edge of the mouth move up 0.35 cm, which is within the range of movements estimated from the Bosphorus database (0.4 ± 0.32 cm).The present study explored the muscle excitation patterns by coupling reinforcement learning with a detailed finite element model of the face. We developed, for the first time, a novel coupling scheme to integrate the finite element simulation into the reinforcement learning process for facial motion learning. As perspectives, this present workflow will be applied for facial palsy and facial transplantation patients to guide and optimize the functional rehabilitation program.

Facial expression recognition plays an essential role in human conversation and human-computer interaction. Previous research studies have recognized facial expressions mainly based on 2D image processing requiring sensitive feature engineering and conventional machine learning approaches. The purpose of the present study was to recognize facial expressions by applying a new class of deep learning called geometric deep learning directly on 3D point cloud data. Two databases (Bosphorus and SIAT-3DFE) were used. The Bosphorus database includes sixty-five subjects with seven basic expressions (i.e., anger, disgust, fearness, happiness, sadness, surprise, and neutral). The SIAT-3DFE database has 150 subjects and 4 basic facial expressions (neutral, happiness, sadness, and surprise). First, preprocessing procedures such as face center cropping, data augmentation, and point cloud denoising were applied on 3D face scans. Then, a geometric deep learning model called PointNet++ was applied. A hyperparameter tuning process was performed to find the optimal model parameters. Finally, the developed model was evaluated using the recognition rate and confusion matrix. The facial expression recognition accuracy on the Bosphorus database was 69.01% for 7 expressions and could reach 85.85% when recognizing five specific expressions (anger, disgust, happiness, surprise, and neutral). The recognition rate was 78.70% with the SIAT-3DFE database. The present study suggested that 3D point cloud could be directly processed for facial expression recognition by using geometric deep learning approach. In perspectives, the developed model will be applied for facial palsy patients to guide and optimize the functional rehabilitation program.

Human motion during walking provides biometric information which can be utilized to quantify the similarity between two persons or identify a person. The purpose of this study was to develop a method for identifying a person using their walking motion when another walking motion under different conditions is given. This type of situation occurs frequently in forensic gait science. Twenty-eight subjects were asked to walk in a gait laboratory, and the positions of their joints were tracked using a three-dimensional motion capture system. The subjects repeated their walking motion both without a weight and with a tote bag weighing a total of 5% of their body weight in their right hand. The positions of 17 anatomical landmarks during two cycles of a gait trial were generated to form a gait vector. We developed two different linear transformation methods to determine the functional relationship between the normal gait vectors and the tote-bag gait vectors from the collected gait data, one using linear transformations and the other using partial least squares regression. These methods were validated by predicting the tote-bag gait vector given a normal gait vector of a person, accomplished by calculating the Euclidean distance between the predicted vector to the measured tote-bag gait vector of the same person. The mean values of the prediction scores for the two methods were 96.4 and 95.0, respectively. This study demonstrated the potential for identifying a person based on their walking motion, even under different walking conditions.

ObjectivesThe objective of this study was to quantify the relative movement between the articular surfaces in the tibiotalar and subtalar joints during normal walking in asymptomatic individuals.Methods3D movement data of the ankle joint complex were acquired from 18 subjects using a biplanar fluoroscopic system and 3D-to-2D registration of bone models obtained from CT images. Surface relative velocity vectors (SRVVs) of the articular surfaces of the tibiotalar and subtalar joints were calculated. The relative movement of the articulating surfaces was quantified as the mean relative speed (RS) and synchronization index (SIENT) of the SRVVs.ResultsSIENTand mean RS data showed that the tibiotalar joint exhibited translational movement throughout the stance, with a mean SIENTof 0.54 (sd 0.21). The mean RS of the tibiotalar joint during the 0% to 20% post heel-strike phase was 36.0 mm/s (sd 14.2), which was higher than for the rest of the stance period. The subtalar joint had a mean SIENTvalue of 0.43 (sd 0.21) during the stance phase and exhibited a greater degree of rotational movement than the tibiotalar joint. The mean relative speeds of the subtalar joint in early (0% to 10%) and late (80% to 90%) stance were 23.9 mm/s (sd 11.3) and 25.1 mm/s (sd 9.5), respectively, which were significantly higher than the mean RS during mid-stance (10% to 80%).ConclusionThe tibiotalar and subtalar joints exhibited significant translational and rotational movement in the initial stance, whereas only the subtalar joint exhibited significant rotational movement during the late stance. The relative movement on the articular surfaces provided deeper insight into the interactions between articular surfaces, which are unobtainable using the joint coordinate system. Cite this article: C-B. Phan, D-P. Nguyen, K. M. Lee, S. Koo. Relative movement on the articular surfaces of the tibiotalar and subtalar joints during walking. Bone Joint Res 2018;7:501–507. DOI: 10.1302/2046-3758.78.BJR-2018-0014.R1.

Eighty-five species belonging to 46 genera of Ostracoda were recovered from 169 samples in three sediment cores (VN, NB, and GA) from the Red River delta plain, northeastern Vietnam. From a Q-mode cluster analysis, we recognized three biofacies (Biofacies A, B, and C). Biofacies B is subdivided into Biofacies BI and BII. The environment of Biofacies A is interpreted as open marine, those of Biofacies BI and BII as marine to brackish water and brackish water, respectively, and that of Biofacies C as oligohaline to mesohaline brackish water. The Holocene sediments consist of estuarine sediments deposited under relatively high sea levels following transgression, deposited during 11–8.5 cal kyr BP, overlain by deltaic sediments deposited under relatively low sea levels following regression, and the ostracod assemblages reflect these changes. The estuarine sediments of the early Holocene transgression are characterized by ostracod Biofacies BI. An erosional surface marks an abrupt change to the shelf environment, accompanied by sediment starvation. The interval around this surface, identified as the maximum flooding surface, is characterized by ostracod Biofacies A. During the subsequent delta progradation, the sedimentary environment changed from a prodelta to delta front, and then to a delta plain, and the corresponding ostracod assemblages changed from Biofacies A to BI, BII, and then C in ascending order. Taken together, our results show that the temporal changes in ostracod assemblages since 10 cal kyr BP are closely related to the evolution of the Red River delta system and can serve as good indicators of paleoenvironmental changes.