Neural network modelling of soft tissue deformation for surgical simulation

Zhang, Jinao; Zhong, Yongmin; Gu, Chengfan

doi:10.1016/j.artmed.2018.11.001

Cited by 32 publications

(15 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Importantly, both machine learning and multiscale modeling complement each other in creating more robust predictive models in the current field of research [126,127]. Recently, several studies have been reported in the literature that have explored the application of AI and machine learning algorithms in the field of thermal therapies [40,[128][129][130][131][132][133][134][135][136]. The integration of machine learning with the coupled models could play a vital role in decision-making processes and the treatment planning stage of such procedures, e.g., by providing a priori information about electrode placement for enhancing treatment efficacy or by the real-time monitoring of the damage to the target tissue and other critical structures.…”

Section: Coupling Framework and Pain Relief Modelsmentioning

confidence: 99%

Domain Heterogeneity in Radiofrequency Therapies for Pain Relief: A Computational Study with Coupled Models

Singh

Melnik

2020

Bioengineering

View full text Add to dashboard Cite

The objective of the current research work is to study the differences between the predicted ablation volume in homogeneous and heterogeneous models of typical radiofrequency (RF) procedures for pain relief. A three-dimensional computational domain comprising of the realistic anatomy of the target tissue was considered in the present study. A comparative analysis was conducted for three different scenarios: (a) a completely homogeneous domain comprising of only muscle tissue, (b) a heterogeneous domain comprising of nerve and muscle tissues, and (c) a heterogeneous domain comprising of bone, nerve and muscle tissues. Finite-element-based simulations were performed to compute the temperature and electrical field distribution during conventional RF procedures for treating pain, and exemplified here for the continuous case. The predicted results reveal that the consideration of heterogeneity within the computational domain results in distorted electric field distribution and leads to a significant reduction in the attained ablation volume during the continuous RF application for pain relief. The findings of this study could provide first-hand quantitative information to clinical practitioners about the impact of such heterogeneities on the efficacy of RF procedures, thereby assisting them in developing standardized optimal protocols for different cases of interest.

show abstract

Section: Coupling Framework and Pain Relief Modelsmentioning

confidence: 99%

Domain Heterogeneity in Radiofrequency Therapies for Pain Relief: A Computational Study with Coupled Models

Singh

Melnik

2020

Bioengineering

View full text Add to dashboard Cite

show abstract

“…The implicit integration is superior to the explicit one for stiff equations. It can achieve the stability of dynamic simulation under large time steps, leading to the improved simulation efficiency [4]. The Wilson − θ is a popular implicit time integration scheme.…”

Section: B Temporal Discretizationmentioning

confidence: 99%

“…However, it is difficult to satisfy these two conflicting requirements [1], [2]. Currently, the existing methods for modelling of soft tissue deformation can be divided into two general classes [3], [4]. One focuses on real-time computational performance.…”

Section: Introductionmentioning

confidence: 99%

Kalman Filter Finite Element Method for Real-Time Soft Tissue Modeling

et al. 2020

Self Cite

View full text Add to dashboard Cite

Soft tissue modelling plays a significant role in surgery simulation as well as surgical procedure planning and training. However, it is a challenging research task to satisfy both physical realism and realtime simulation for soft tissue deformation. The finite element method (FEM) is a representative strategy for modelling of soft tissue deformation with highly physical realism. However, it suffers from expensive computations, unable to meet the requirement of real-time simulation. This paper proposes a novel method by combining FEM with the Kalman filter for real-time and accurate modelling of soft tissue deformation. The novelty of this method is that soft tissue deformation is formulated as a filtering identification process to online estimate soft tissue deformation from local measurement of displacement. To construct the discrete system state equation for filtering estimation, soft tissue deformation is discretised based on elastic theory in the space domain by FEM and is further discretised in the time domain by using the Wilson-θ implicit integration to solve the dynamic equilibrium equation of FEM deformation modelling. Subsequently, a Kalman filter is developed for online estimation and analysis of soft tissue deformation according to local measurement of displacement. Interactive tool-tissue interaction with haptic feedback is also achieved for surgery simulation. The presented method significantly improves the computational performance of the traditional FEM, but still maintains a similar level of accuracy. It not only achieves the real-time performance, but also exhibits the similar deformation behaviours as the traditional FEM and enables the use of large time steps to improve the simulation efficiency.

show abstract

“…While hybrid-twin models aim to perform an error correction on well-established models, aiming to preserve the known physics in the model, while accounting for the ignorance or lack of information [ 10 , 13 ]. Such a trend is now colonizing more research fields and soft materials are not an exception [ 14 , 15 ]. For example, Ref.…”

Section: Introductionmentioning

confidence: 99%

“…For example, Ref. [ 14 ] trained a neural network to simulate later in real-time the response of human soft tissues in a surgical context. In [ 15 ], the authors leverage machine learning techniques along with classical mechanics of materials models to create a hybrid modeling of soft materials.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven GENERIC Modeling of Poroviscoelastic Materials

Ghnatios

Alfaro

González

et al. 2019

Entropy

View full text Add to dashboard Cite

Biphasic soft materials are challenging to model by nature. Ongoing efforts are targeting their effective modeling and simulation. This work uses experimental atomic force nanoindentation of thick hydrogels to identify the indentation forces are a function of the indentation depth. Later on, the atomic force microscopy results are used in a GENERIC general equation for non-equilibrium reversible–irreversible coupling (GENERIC) formalism to identify the best model conserving basic thermodynamic laws. The data-driven GENERIC analysis identifies the material behavior with high fidelity for both data fitting and prediction.

show abstract

Neural network modelling of soft tissue deformation for surgical simulation

Cited by 32 publications

References 50 publications

Domain Heterogeneity in Radiofrequency Therapies for Pain Relief: A Computational Study with Coupled Models

Domain Heterogeneity in Radiofrequency Therapies for Pain Relief: A Computational Study with Coupled Models

Kalman Filter Finite Element Method for Real-Time Soft Tissue Modeling

Data-Driven GENERIC Modeling of Poroviscoelastic Materials

Contact Info

Product

Resources

About