This slight latency could be due to the communications within the hardware and software integration (i.e., Arduino, SeeedStudio CAN Bus Shield, Matlab) and the refresh rate in the projector. This slight latency does not affect the feedback of the force sensor input (i.e., contact force and fingers location) to the surrogate model and the tissue deformation rendering, but it could be improved for a smoother visual projection. When palpating onto the force-sensing platform, a slight latency in the range of 200–500 ms during the visual projections was observed, taking into account the duration of 150 ms our brains take to process visual information. These features can then be added into the surrogate model and ANN training, as well as the abdomen phantom to produce a more authentic visualisation and palpation feedback. Customised tissue abnormalities, such as tumours within the liver tissue with different severity can also be included into the FE models for more advanced training programmes. Even though this model provides a sufficient representation of the abdominal tissue dynamics during palpation for our feasibility study, it would be more realistic to take into account the respiratory cycle in our simulations. In addition, the FE model was extracted from the CT scan at a single respiratory frame. More investigation is required to include these variations into our FE model configurations to provide a more realistic abdominal model for a larger range of palpation training. The FE model of our abdomen was generated by using XCAT software from a single male human body based on the 3D Visible Human Project hence, it does not take into account physiological variations, such as the visceral fat in different human bodies. Performing FE simulations for palpation requires a long run time and high computation, which is not desirable especially when real-time information is needed for immediate training feedback. Therefore, we constructed a new model from CT scans of the human abdomen, allowing us to model different abdominal tissues for different physiological conditions, such as different stages of the respiratory cycle. However, this model has a complex description of abdominal tissues and has been developed for high rate loading hence, it is not suitable for palpation simulation. The Global Human Body Model Consortium (GHBMC) has also developed a full human body model for impact studies in road traffic accidents. For instance, a complete human body model named the total human model for safety (THUMS) model by Toyota Motor Corporation was developed and validated for injury reconstruction and crash analyses, but it lacks details of the abdominal tissues. Several FE human body models have been developed. By using finite element modelling (FEM), we can predict tissue deformation under mechanical loading, such as palpation. This enhanced robotics platform has the potential to be used as a training simulator for trainees to hone their palpation skills.Ĭomputational modelling can be used to produce this important layer of information for the simulator. We also showed that the surrogate model is able to use the experimental input of palpation location and force to provide real-time projections onto the robotics platform. Our results show that our artificial neural network (ANN) surrogate has an accuracy of 92.6%. Our FE simulations took 1.5 h to predict stress distribution for each palpation while this only took a fraction of a second for the surrogate model. We then used artificial neural networks (ANNs) to develop the surrogate model and demonstrated its application in an experimental palpation platform. We performed palpation simulations to produce a large database of stress distribution on the liver edge, an area of interest in most examinations. We first developed a new high-fidelity FE model of the abdomen mechanics from computerized tomography (CT) images. In this work, we proposed an innovative surrogate model of abdomen mechanics by using machine learning (ML) and finite element (FE) modelling to virtually render internal tissue deformation in real time. However, such models are computationally expensive, and thus unable to provide real-time predictions. This can be achieved by using computational models of abdomen mechanics. They provide information about internal organ deformation that can significantly enhance palpation training by giving medical trainees visual insight based on the pressure they apply for palpation. Robotic patients show great potential for helping to improve medical palpation training, as they can provide feedback that cannot be obtained in a real patient.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |