Enhanced multistage deep learning for diagnosing anterior disc displacement in the temporomandibular joint using MRI.

OBJECTIVES: This study aimed to propose a new method for the automatic diagnosis of anterior disc displacement of the temporomandibular joint (TMJ) using MRI and deep learning. By using a multistage approach, the factors affecting the final result can be easily identified and improved. METHODS: This study introduces a multistage automatic diagnostic technique using deep learning. This process involves segmenting the target from MR images, extracting distance parameters, and classifying the diagnosis into 3 classes. MRI exams of 368 TMJs from 204 patients were evaluated for anterior disc displacement. In the first stage, 5 algorithms were used for the semantic segmentation of the disc and condyle. In the second stage, 54 distance parameters were extracted from the segments. In the third stage, a rule-based decision model was developed to link the parameters with the expert diagnosis results. RESULTS: In the first stage, DeepLabV3+ showed the best result (95% Hausdorff distance, Dice coefficient, and sensitivity of 6.47 ± 7.22, 0.84 ± 0.07, and 0.84 ± 0.09, respectively). This study used the original MRI exams as input without preprocessing and showed high segmentation performance compared with that of previous studies. In the third stage, the combination of SegNet and a random forest model yielded an accuracy of 0.89 ± 0.06. CONCLUSIONS: An algorithm was developed to automatically diagnose TMJ-anterior disc displacement using MRI. Through a multistage approach, this algorithm facilitated the improvement of results and demonstrated high accuracy from more complex inputs. Furthermore, existing radiological knowledge was applied and validated.

Automatic multi-class intertrochanteric femur fracture detection from CT images based on AO/OTA classification using faster R-CNN-BO method.

Intertrochanteric (IT) femur fractures are the most common fractures in elderly people, and they lead to significant morbidity, mortality, and reduced quality of life. The different types of fractures require a careful definition to ensure accurate surgical planning and reduce the operation time, healing time, and number of surgical failures. In this study, a deep learning-based automatic multi-class IT fracture detection model was developed using computed tomography (CT) images and based on the AO/OTA classification method. The original CT image was resized and rearranged according to the fracture location and an unsharp masking filter was applied. A multi-class classification of nine different types of IT fractures and no fracture was performed using the faster regional-convolutional neural network (R-CNN). Bayesian optimization was also implemented to determine the optimal hyperparameter values for the faster R-CNN algorithm. In our proposed model, IT fractures classified into two classes showed an average accuracy of 0.97 ± 0.02, which was 0.90 ± 0.02 when classified into ten classes. Additionally, the detected region of interest from our proposed model showed minimum root mean square error and intersection over union values of 16.34 ± 47.01 pixels and 0.87 ± 0.12, respectively. In the future, our proposed automatic multi-class IT femur fracture detection model could allow clinicians to identify the fracture region and diagnose different types of femur fractures faster and more accurately. This will increase the probability of correct surgical treatment and minimize postoperative complications.

Predicting Complete Ground Reaction Forces and Moments During Gait With Insole Plantar Pressure Information Using a Wavelet Neural Network.

In general, three-dimensional ground reaction forces (GRFs) and ground reaction moments (GRMs) that occur during human gait are measured using a force plate, which are expensive and have spatial limitations. Therefore, we proposed a prediction model for GRFs and GRMs, which only uses plantar pressure information measured from insole pressure sensors with a wavelet neural network (WNN) and principal component analysis-mutual information (PCA-MI). For this, the prediction model estimated GRFs and GRMs with three different gait speeds (slow, normal, and fast groups) and healthy/pathological gait patterns (healthy and adolescent idiopathic scoliosis (AIS) groups). Model performance was validated using correlation coefficients (r) and the normalized root mean square error (NRMSE%) and was compared to the prediction accuracy of the previous methods using the same dataset. As a result, the performance of the GRF and GRM prediction model proposed in this study (slow group: r = 0.840-0.989 and NRMSE% = 10.693-15.894%; normal group: r = 0.847-0.988 and NRMSE% = 10.920-19.216%; fast group: r = 0.823-0.953 and NRMSE% = 12.009-20.182%; healthy group: r = 0.836-0.976 and NRMSE% = 12.920-18.088%; and AIS group: r = 0.917-0.993 and NRMSE% = 7.914-15.671%) was better than that of the prediction models suggested in previous studies for every group and component (p < 0.05 or 0.01). The results indicated that the proposed model has improved performance compared to previous prediction models.

Kinematic evaluation of movement smoothness in golf: relationship between the normalized jerk cost of body joints and the clubhead.

BACKGROUND: When the human body is introduced to a new motion or movement, it learns the placement of different body parts, sequential muscle control, and coordination between muscles to achieve necessary positions, and it hones this new skill over time and repetition. Previous studies have demonstrated definite differences in the smoothness of body movements with different levels of training, i.e., amateurs compared with professionals. Therefore, we tested the hypothesis that skilled golfers swing a driver with a smoother motion than do unskilled golfers. In addition, the relationship between the smoothness of body joints and that of the clubhead was evaluated to provide further insight into the mechanism of smooth golf swing. METHODS: Two subject groups (skilled and unskilled) participated in the experiment. The skilled group comprised 20 male professional golfers registered with the Korea Professional Golf Association, and the unskilled group comprised 19 amateur golfers who enjoy golf as a hobby. Six infrared cameras (VICON460 system) were used to record the 3D trajectories of markers attached to the clubhead and body segments, and the resulting data was evaluated with kinematic analysis. A physical quantity called jerk was calculated to investigate differences in smoothness during downswing between the two study groups. RESULTS: The hypothesis that skilled golfers swing a driver with a smoother motion than do unskilled golfers was supported. The normalized jerk of the clubhead of skilled golfers was lower than that of unskilled golfers in the anterior/posterior, medial/lateral, and proximal/distal directions. Most human joints, especially in the lower body, had statistically significant lower normalized jerk values in the skilled group. In addition, the normalized jerk of the skilled group's lower body joints had a distinct positive correlation with the normalized jerk of the clubhead with r = 0.657 (p < 0.01). CONCLUSIONS: The result of this study showed that skilled golfers have smoother swings than unskilled golfers during the downswing and revealed that the smoothness of a clubhead trajectory is related more to the smoothness of the lower body joints than that of the upper body joints. These findings can be used to understand the mechanisms behind smooth golf swings and, eventually, to improve golf performance.

Clinical Application of an Augmented Reality Navigation System for Transforaminal Epidural Injection: A Randomized Controlled Trial.

Objectives: Augmented reality (AR) navigation systems are emerging to simplify and enhance the precision of medical procedures. Lumbosacral transforaminal epidural injection is a commonly performed procedure for the treatment and diagnosis of radiculopathy. Accurate needle placement while avoiding critical structures remains a challenge. For this purpose, we conducted a randomized controlled trial for our augmented reality navigation system. Methods: This randomized controlled study involved 28 patients, split between a traditional C-arm guided group (control) and an AR navigation guided group (AR-NAVI), to compare procedure efficiency and radiation exposure. The AR-NAVI group used a real-time tracking system displaying spinal structure and needle position on an AR head-mounted display. The procedural time and C-arm usage (radiation exposure) were measured. Results: All patients underwent successful procedures without complications. The AR-NAVI group demonstrated significantly reduced times and C-arm usage for needle entry to the target point (58.57 ± 33.31 vs. 124.91 ± 41.14, p < 0.001 and 3.79 ± 1.97 vs. 8.86 ± 3.94, p < 0.001). Conclusions: The use of the AR navigation system significantly improved procedure efficiency and safety by reducing time and radiation exposure, suggesting a promising direction for future enhancements and validation.

Variational autoencoder-based estimation of chronological age and changes in morphological features of teeth.

This study led to the development of a variational autoencoder (VAE) for estimating the chronological age of subjects using feature values extracted from their teeth. Further, it determined how given teeth images affected the estimation accuracy. The developed VAE was trained with the first molar and canine tooth images, and a parallel VAE structure was further constructed to extract common features shared by the two types of teeth more effectively. The encoder of the VAE was combined with a regression model to estimate the age. To determine which parts of the tooth images were more or less important when estimating age, a method of visualizing the obtained regression coefficient using the decoder of the VAE was developed. The developed age estimation model was trained using data from 910 individuals aged 10-79. This model showed a median absolute error (MAE) of 6.99 years, demonstrating its ability to estimate age accurately. Furthermore, this method of visualizing the influence of particular parts of tooth images on the accuracy of age estimation using a decoder is expected to provide novel insights for future research on explainable artificial intelligence.

Improving the ground reaction force prediction accuracy using one-axis plantar pressure: Expansion of input variable for neural network.

In this study, we describe a method to predict 6-axis ground reaction forces based solely on plantar pressure (PP) data obtained from insole type measurement devices free of space limitations. Because only vertical force is calculable from PP data, a wavelet neural network derived from a non-linear mapping function was used to obtain 3-axis ground reaction force in medial-lateral (GRFML), anterior-posterior (GRFAP) and vertical (GRFV) and 3-axis ground reaction moment in sagittal (GRFS), frontal (GRFF) and transverse (GRFT) data for the remaining axes and planes. As the prediction performance of nonlinear models depends strongly on input variables, in this study, three input variables - accumulated PP with respect to time, center of pressure (COP) pattern, and measurements of the opposite foot, which are calculable only with a PP device - were considered in order to improve prediction performance. To conduct this study, the golf swing motions of 80 subjects were characterized as unilateral movement and GRF patterns as functions of individual characteristics. The prediction model was verified with 5-fold cross-validation utilizing the measured values of two force plates. As a result, prediction model (correlation coefficient, r=0.73-0.97) utilized accumulated PP and PP data of the opposite foot and showed the highest prediction accuracy in left-foot GRFV, GRMF, GRMT and right-foot GRFAP, GRFML, GRMF, GRMT. Likewise, another prediction model (r=0.83-0.98) utilized accumulated PP and COP patterns as input and showed the best accuracy in left-foot GRFAP, GRFML, GRMS and right-foot GRFV, GRMS. New methods based on the findings of the present study are expected to help resolve problems such as spatial limitation and limited analyzable motions in existing GRF measurement processes.