Personalization of human body models and beyond via image registration

A fast-modeling framework for personalized human body models based on a single image

Finite element human body models (HBMs) are the primary method for predicting human biological responses in vehicle collisions, especially personalized HBMs that allow accounting for diverse populations. Yet, creating personalized HBMs from a single image is a challenging task. This study addresses this challenge by providing a framework for HBM personalization, starting from a single image used to estimate the subject's skin point cloud, the skeletal point cloud, and the relative positions of the skeletons. Personalized HBMs were created by morphing the baseline HBM accounting skin and skeleton point clouds using a point cloud registration-based mesh morphing method. Using this framework, eight personalized HBMs with various biological characteristics (e.g., sex, height, and weight) were created, with comparable element quality to the baseline HBM. The mean geometric errors of the personalized FEMs generated by the framework are less than 7 mm, which was found to be acceptable based on biomechanical response evaluations conducted in this study.

Swin UNETR Segmentation with Automated Geometry Filtering for Biomechanical Modeling of Knee Joint Cartilage

PURPOSE

Simulation studies, such as finite element (FE) modeling, offer insights into knee joint biomechanics, which may not be achieved through experimental methods without direct involvement of patients. While generic FE models have been used to predict tissue biomechanics, they overlook variations in population-specific geometry, loading, and material properties. In contrast, subject-specific models account for these factors, delivering enhanced predictive precision but requiring significant effort and time for development.

METHODS

This study aimed to facilitate subject-specific knee joint FE modeling by integrating an automated cartilage segmentation algorithm using a 3D Swin UNETR. This algorithm provided initial segmentation of knee cartilage, followed by automated geometry filtering to refine surface roughness and continuity. In addition to the standard metrics of image segmentation performance, such as Dice similarity coefficient (DSC) and Hausdorff distance, the method's effectiveness was also assessed in FE simulation. Nine pairs of knee cartilage FE models, using manual and automated segmentation methods, were developed to compare the predicted stress and strain responses during gait.

RESULTS

The automated segmentation achieved high Dice similarity coefficients of 89.4% for femoral and 85.1% for tibial cartilage, with a Hausdorff distance of 2.3 mm between the automated and manual segmentation. Mechanical results including maximum principal stress and strain, fluid pressure, fibril strain, and contact area showed no significant differences between the manual and automated FE models.

CONCLUSION

These findings demonstrate the effectiveness of the proposed automated segmentation method in creating accurate knee joint FE models. The automated models developed in this study have been made publicly accessible to support biomechanical modeling and medical image segmentation studies ( https://data.mendeley.com/datasets/dc832g7j5m/1 ).

Toward systematic finite element reconstructions of accidents involving vulnerable road users

OBJECTIVES

To combat the global fatality rates among vulnerable road users (VRUs), prioritizing research on head injury mechanisms and human tolerance levels in vehicle-to-VRU traffic collisions is imperative. A foundational step for VRU injury prevention is often to create virtual reconstructions of real-world collisions. Thus, efficient and trustworthy reconstruction tools are needed to make use of recent advances in accident data collection routines and Finite Element (FE) human body modeling.

METHODS

In this study, a comprehensive and streamlined reconstruction methodology, starting from a video-recorded accident, has been developed. The workflow, that includes state-of-the-art tools for personalization of human body models (HBMs) and vehicles, was evaluated and demonstrated through 20 real-world VRU collision cases.

RESULTS

The FE models successfully replicated the vehicle damage that was observed in on-scene photographs of the post-impact vehicle, as well as impact kinematics captured in dash cam or surveillance recordings.

CONCLUSIONS

The findings highlight how video evidence can considerably narrow down the number of plausible impact scenarios and raise the credibility of virtual reconstructions of real-world VRU collision events. More importantly, this study demonstrates how, with an efficient and systematic methodology, FE might be feasible also for large-scale VRU accident datasets.

A data-mining study on the prediction of head injury in traffic accidents among vulnerable road users with varying body sizes and head anatomical characteristics

Body sizes and head anatomical characteristics play the major role in the head injuries sustained by vulnerable road users (VRU) in traffic accidents. In this study, in order to study the influence mechanism of body sizes and head anatomical characteristics on head injury, we used age, gender, height, and Body Mass Index (BMI) as characteristic parameters to develop the personalized human body multi-rigid body (MB) models and head finite element (FE) models. Next, using simulation calculations, we developed the VRU head injury dataset based on the personalized models. In the dataset, the dependent variables were the degree of head injury and the brain tissue von Mises value, while the independent variables were height, BMI, age, gender, traffic participation status, and vehicle speed. The statistical results of the dataset show that the von Mises value of VRU brain tissue during collision ranges from 4.4 kPa to 46.9 kPa at speeds between 20 and 60 km/h. The effects of anatomical characteristics on head injury include: the risk of a more serious head injury of VRU rises with age; VRU with higher BMIs has less head injury in collision accidents; height has very erratic and nonlinear impacts on the von Mises values of the VRU's brain tissue; and the severity of head injury is not significantly influenced by VRU's gender. Furthermore, we developed the classification prediction models of head injury degree and the regression prediction models of head injury response parameter by applying eight different data mining algorithms to this dataset. The classification prediction models have the best accuracy of 0.89 and the best R2 value of 0.85 for the regression prediction models.

Integration of Swin UNETR and statistical shape modeling for a semi-automated segmentation of the knee and biomechanical modeling of articular cartilage

Simulation studies, such as finite element (FE) modeling, provide insight into knee joint mechanics without patient involvement. Generic FE models mimic the biomechanical behavior of the tissue, but overlook variations in geometry, loading, and material properties of a population. Conversely, subject-specific models include these factors, resulting in enhanced predictive precision, but are laborious and time intensive. The present study aimed to enhance subject-specific knee joint FE modeling by incorporating a semi-automated segmentation algorithm using a 3D Swin UNETR for an initial segmentation of the femur and tibia, followed by a statistical shape model (SSM) adjustment to improve surface roughness and continuity. For comparison, a manual FE model was developed through manual segmentation (i.e., the de-facto standard approach). Both FE models were subjected to gait loading and the predicted mechanical response was compared. The semi-automated segmentation achieved a Dice similarity coefficient (DSC) of over 98% for both the femur and tibia. Hausdorff distance (mm) between the semi-automated and manual segmentation was 1.4 mm. The mechanical results (max principal stress and strain, fluid pressure, fibril strain, and contact area) showed no significant differences between the manual and semi-automated FE models, indicating the effectiveness of the proposed semi-automated segmentation in creating accurate knee joint FE models. We have made our semi-automated models publicly accessible to support and facilitate biomechanical modeling and medical image segmentation efforts ( https://data.mendeley.com/datasets/k5hdc9cz7w/1 ).

Development of personalizable female and male pedestrian SAFER human body models

OBJECTIVES

Vulnerable road users are globally overrepresented as victims of road traffic injuries. Developing biofidelic male and female pedestrian human body models (HBMs) that represent diverse anthropometries is essential to enhance road safety and propose intervention strategies.

METHODS

In this study, 50th percentile male and female pedestrians of the SAFER HBM were developed via a newly developed image registration-based mesh morphing framework. The performance of the HBMs was evaluated by means of a set of cadaver experiments, involving subjects struck laterally by a generic sedan buck.

RESULTS

In simulated whole-body pedestrian collisions, the personalized HBMs effectively replicate trajectories of the head and lower body regions, as well as head kinematics, in lateral impacts. The results also demonstrate the personalization framework's capacity to generate personalized HBMs with reliable mesh quality, ensuring robust simulations.

CONCLUSIONS

The presented pedestrian HBMs and personalization framework provide robust means to reconstruct and evaluate head impacts in pedestrian-to-vehicle collisions thoroughly and accurately.