A neural network framework for immediate temperature prediction of surgical hand-held drilling.

BACKGROUND AND OBJECTIVE: Heat generation and associated temperature rise in surgical drilling can cause irreversible tissue damage. It is nearly impossible to provide immediate temperature prediction for a hand-held drilling process since both feed rate and motion vary with time. The objective of this study is to present and test a framework for immediate bone drilling temperature visualization based on a neural network (NN) model and a linear time-invariant (LTI) model. METHODS: In this study, the finite element analysis (FEA) model is used as the ground truth. The NN model is used to predict the location-dependent thermal responses of FEA, while LTI is used to superimpose these responses based on the location history of the heat source. The use of LTI can eliminate the uncertainty of the unlimited possibility in the time domain. To test the framework, two three-dimensional drilling cases are studied, one with a constant drilling feed and straight path and the other with a varying feed and a varying path. RESULTS: The NN model using U-net architecture can achieve the predicted correlation of over 97% with only 1% of the total number of data points. Using the framework with U-net and LTI, both case studies show good agreement in temporal and spatial temperature distributions with the ground truth. The average error near the drilling path is less than 10%. Discrepancies are mainly found near the heat source and the regions near the removed material. CONCLUSIONS: An FEA surrogate model for rapid and accurate prediction of 3D temperature during arbitrary bone drilling is successfully made. The overall error is less than 5% on average in the two case studies. Future improvements include strategies for training data selection and data formating.

Prediction of Bone Healing around Dental Implants in Various Boundary Conditions by Deep Learning Network.

Tissue differentiation varies based on patients' conditions, such as occlusal force and bone properties. Thus, the design of the implants needs to take these conditions into account to improve osseointegration. However, the efficiency of the design procedure is typically not satisfactory and needs to be significantly improved. Thus, a deep learning network (DLN) is proposed in this study. A data-driven DLN consisting of U-net, ANN, and random forest models was implemented. It serves as a surrogate for finite element analysis and the mechano-regulation algorithm. The datasets include the history of tissue differentiation throughout 35 days with various levels of occlusal force and bone properties. The accuracy of day-by-day tissue differentiation prediction in the testing dataset was 82%, and the AUC value of the five tissue phenotypes (fibrous tissue, cartilage, immature bone, mature bone, and resorption) was above 0.86, showing a high prediction accuracy. The proposed DLN model showed the robustness for surrogating the complex, time-dependent calculations. The results can serve as a design guideline for dental implants.

Engineer design process assisted by explainable deep learning network.

Engineering simulation accelerates the development of reliable and repeatable design processes in various domains. However, the computing resource consumption is dramatically raised in the whole development processes. Making the most of these simulation data becomes more and more important in modern industrial product design. In the present study, we proposed a workflow comprised of a series of machine learning algorithms (mainly deep neuron networks) to be an alternative to the numerical simulation. We have applied the workflow to the field of dental implant design process. The process is based on a complex, time-dependent, multi-physical biomechanical theory, known as mechano-regulatory method. It has been used to evaluate the performance of dental implants and to assess the tissue recovery after the oral surgery procedures. We provided a deep learning network (DLN) with calibrated simulation data that came from different simulation conditions with experimental verification. The DLN achieves nearly exact result of simulated bone healing history around implants. The correlation of the predicted essential physical properties of surrounding bones (e.g. strain and fluid velocity) and performance indexes of implants (e.g. bone area and bone-implant contact) were greater than 0.980 and 0.947, respectively. The testing AUC values for the classification of each tissue phenotype were ranging from 0.90 to 0.99. The DLN reduced hours of simulation time to seconds. Moreover, our DLN is explainable via Deep Taylor decomposition, suggesting that the transverse fluid velocity, upper and lower parts of dental implants are the keys that influence bone healing and the distribution of tissue phenotypes the most. Many examples of commercial dental implants with designs which follow these design strategies can be found. This work demonstrates that DLN with proper network design is capable to replace complex, time-dependent, multi-physical models/theories, as well as to reveal the underlying features without prior professional knowledge.

Healing Pattern Analysis for Dental Implants Using the Mechano-Regulatory Tissue Differentiation Model.

(1) Background: Our aim is to reveal the influence of the geometry designs on biophysical stimuli and healing patterns. The design guidelines for dental implants can then be provided. (2) Methods: A two-dimensional axisymmetric finite element model was developed based on mechano-regulatory algorithm. The history of tissue differentiation around eight selected implants can be predicted. The performance of the implants was evaluated by bone area (BA), bone-implant contact (BIC); (3) Results: The predicted healing patterns have very good agreement with the experimental observation. Many features observed in literature, such as soft tissues covering on the bone-implant interface; crestal bone loss; the location of bone resorption bumps, were reproduced by the model and explained by analyzing the solid and fluid biophysical stimuli and (4) Conclusions: The results suggested the suitable depth, the steeper slope of the upper flanks, and flat roots of healing chambers can improve the bone ingrowth and osseointegration. The mechanism related to solid and fluid biophysical stimuli were revealed. In addition, the model developed here is efficient, accurate and ready to extend to any geometry of dental implants. It has potential to be used as a clinical application for instant prediction/evaluation of the performance of dental implants.

Investigation of Bone Growth in Additive-Manufactured Pedicle Screw Implant by Using Ti-6Al-4V and Bioactive Glass Powder Composite.

In this study, we optimized the geometry and composition of additive-manufactured pedicle screws. Metal powders of titanium-aluminum-vanadium (Ti-6Al-4V) were mixed with reactive glass-ceramic biomaterials of bioactive glass (BG) powders. To optimize the geometry of pedicle screws, we applied a novel numerical approach to proposing the optimal shape of the healing chamber to promote biological healing. We examined the geometry and composition effects of pedicle screw implants on the interfacial autologous bone attachment and bone graft incorporation through in vivo studies. The addition of an optimal amount of BG to Ti-6Al-4V leads to a lower elastic modulus of the ceramic-metal composite material, effectively reducing the stress-shielding effects. Pedicle screw implants with optimal shape design and made of the composite material of Ti-6Al-4V doped with BG fabricated through additive manufacturing exhibit greater osseointegration and a more rapid bone volume fraction during the fracture healing process 120 days after implantation, per in vivo studies.

Novel design of additive manufactured hollow porous implants.

OBJECTIVE: Our aim is to examine the mechanical properties of two types of additive manufactured hollow porous dental implants and 6 and 12-week bone ingrowth after insertion in animals. A 3D numerical model is also developed to show detailed tissue differentiation and to provide design guidelines for implants. METHODS: The two porous and a commercial dental implant were studied by series of in vitro mechanical tests (three-point bending, torsional, screwing torque, and sawbone pull-out tests). They also evaluated by in vivo animal tests (micro-CT analysis) and ex vivo pull-out tests. Moreover, the mechano-regulation algorithm was implemented by the 3D finite element model to predict the history of tissue differentiation around the implants. RESULTS: The results showed that the two porous implants can significantly improve osseointegration after 12-week bone healing. This resulted in good fixation and stability of implants, giving very high maximum pull-out strength 413.1 N and 493.2 N, compared to 245.7 N for the commercial implant. Also, several features were accurately predicted by the mechano-regulation model, such as transversely connected bone formation, and bone resorption occurred in the middle of implants. SIGNIFICANCE: Systematic studies on dental implants with multiple approaches, including new design, mechanical tests, animal tests, and numerical modeling, were performed. Two hollow porous implants significantly improved bone ingrowth compared with commercial implants, while maintaining mechanical strength. Also, the numerical model was verified by animal tests. It improved the efficiency of design and reduce the demand for animal sacrifice.

A Hybrid Model for Predicting Bone Healing around Dental Implants.

BACKGROUND: The effect of the short-term bone healing process is typically neglected in numerical models of bone remodeling for dental implants. In this study, a hybrid two-step algorithm was proposed to enable a more accurate prediction for the performance of dental implants. METHODS: A mechano-regulation algorithm was firstly used to simulate the tissue differentiation around a dental implant during the short-term bone healing. Then, the result was used as the initial state of the bone remodeling model to simulate the long-term healing of the bones. The algorithm was implemented by a 3D finite element model. RESULTS: The current hybrid model reproduced several features which were discovered in the experiments, such as stress shielding effect, high strength bone connective tissue bands, and marginal bone loss. A reasonable location of bone resorptions and the stability of the dental implant is predicted, compared with those predicted by the conventional bone remodeling model. CONCLUSIONS: The hybrid model developed here predicted bone healing processes around dental implants more accurately. It can be used to study bone healing before implantation surgery and assist in the customization of dental implants.