Prediction of load in a long bone using an artificial neural network prediction algorithm

Mouloodi, Saeed; Rahmanpanah, Hadi; Burvill, Colin; Davies, Helen M.S.

doi:10.1016/j.jmbbm.2019.103527

Cited by 22 publications

(8 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When R approaches 1, it means significant liner relationship between the predicted results and real results. When R approached 0, it indicates nonsignificant relationship between the predicted results and real results (Mouloodi, Rahmanpanah, Burvill, & Davies, 2020). The ANN model build in this study shows favorable R values which indicates good performance of the model in prediction.…”

Section: Resultsmentioning

confidence: 99%

Feature selection, artificial neural network prediction and experimental testing for predicting breakage rate of maize kernels based on mechanical properties

Xia

Yang

et al. 2020

J Food Process Engineering

View full text Add to dashboard Cite

The kernel breakage in harvest process is a significant problem which causes massive grain losses. In order to solve this problem, a possible solution is to predict the breakage rate and give suitable harvest time thus reducing grain losses. This study focused on using mechanical properties to predict breakage rate. Compression tests, compression–relaxation tests, insertion–retraction and stretch tests were conducted and 20 parameters were derived. Threshing tests were conducted to get breakage rate. As these parameters might be related and it is not practical to use massive parameters for prediction, the feature selection using neighborhood component analysis (FSNCA) was used for picking important parameters. The variables were compacted to an acceptable level by the FSNCA while various aspects of mechanical properties were included. The FSNCA determined the hardness of floury endosperm, rupture energy in vertical direction (x‐axis), allowable stress in lateral direction (z‐axis), hysteresis in x‐axis and elastic modulus in z‐axis as predictors. The artificial neural network (ANN) was built for prediction. The built ANN model showed an agreement in prediction results and real breakage rate (R = 0.98). The prediction error was ±1.7%.Practical ApplicationsThe mechanical properties were illustrated as potential indexes which can be utilized for predicting breakage rate of maize kernels in threshing process. The selection method reduced the dimension of predictors, which means fewer tests are required for prediction. As a result, this research proposed a possible solution for the prediction of maize breakage in harvest. Moreover, the prediction model can give guidance for optimal harvest time and thus reduce breakage rate in harvest.

show abstract

Section: Resultsmentioning

confidence: 99%

Feature selection, artificial neural network prediction and experimental testing for predicting breakage rate of maize kernels based on mechanical properties

Xia

Yang

et al. 2020

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…Microscopy images of the samples are then used to train deep learning (DL) models to classify tissue stiffness and to predict nonlinear anisotropic stress-strain curves. The strategy of obtaining data from animal samples is also used by Mouloodi et al 44,45 as they use nine hydrated bones from cadavers of horses. Different loads are applied to the bones and measures of strain and displacement are registered.…”

Section: Data Collectionmentioning

confidence: 99%

“…9,10,53 On the other hand, it is also possible to estimate the deformation of harder structures, such as the bones as they are affected by load. 45 It was also observed, in two publications, 44,47 that external forces can be calculated as the output of an ML algorithm that receives tissue deformation data as input. Both publications target bones and they estimate the applied load as output, by sending bone deformation data as input to an ML algorithm.…”

Section: Input and Output Featuresmentioning

confidence: 99%

Real‐time biomechanics using the finite element method and machine learning: Review and perspective

et al. 2020

View full text Add to dashboard Cite

The finite element method (FEM) is the preferred method to simulate phenomena in anatomical structures. However, purely FEM-based mechanical simulations require considerable time, limiting their use in clinical applications that require real-time responses, such as haptics simulators. Machine learning (ML) approaches have been proposed to help with the reduction of the required time. The present paper reviews cases where ML could help to generate faster simulations, without considerably affecting the performance results. Methods: This review details the ML approaches used, considering the anatomical structures involved, the data collection strategies, the selected ML algorithms, with corresponding features, the metrics used for validation, and the resulting time gains. Results: A total of 41 references were found. ML algorithms are mainly trained with FEM-based simulations, in 32 publications. The preferred ML approach is neural networks, including deep learning, in 35 publications. Tissue deformation is simulated in 18 applications, but other features are also considered. The average distance error and mean squared error are the most frequently used performance metrics, in 14 and 17 publications, respectively. The time gains were considerable, going from hours or minutes for purely FEM-based simulations to milliseconds, when using ML. Conclusions: ML algorithms can be used to accelerate FEM-based biomechanical simulations of anatomical structures, possibly reaching real-time responses. Fast and real-time simulations of anatomical structures, generated with ML algorithms, can help to reduce the time required by FEM-based simulations and accelerate their adoption in the clinical practice.

show abstract

“…In an effort to quantify in vivo loading patterns using biomechanical models, several load estimation algorithms have been developed. Artificial neural network-based approaches have been proposed (Garijo et al, 2014(Garijo et al, , 2017Mouloodi et al, 2020) but lack interpretability, which is critical for moving to diagnostic use in patients to guide local therapeutic interventions. As a result, an algebraic method introduced by Christen et al (2012) has been widely implemented to approximate the internal load history based on bone morphology (Christen et al, 2014;Badilatti et al, 2017;Synek et al, 2019;Cheong et al, 2020;né Betts et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Bone Mechanoregulation Allows Subject-Specific Load Estimation Based on Time-Lapsed Micro-CT and HR-pQCT in Vivo

Walle

Marques

Ohs

et al. 2021

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Patients at high risk of fracture due to metabolic diseases frequently undergo long-term antiresorptive therapy. However, in some patients, treatment is unsuccessful in preventing fractures or causes severe adverse health outcomes. Understanding load-driven bone remodelling, i.e., mechanoregulation, is critical to understand which patients are at risk for progressive bone degeneration and may enable better patient selection or adaptive therapeutic intervention strategies. Bone microarchitecture assessment using high-resolution peripheral quantitative computed tomography (HR-pQCT) combined with computed mechanical loads has successfully been used to investigate bone mechanoregulation at the trabecular level. To obtain the required mechanical loads that induce local variances in mechanical strain and cause bone remodelling, estimation of physiological loading is essential. Current models homogenise strain patterns throughout the bone to estimate load distribution in vivo, assuming that the bone structure is in biomechanical homoeostasis. Yet, this assumption may be flawed for investigating alterations in bone mechanoregulation. By further utilising available spatiotemporal information of time-lapsed bone imaging studies, we developed a mechanoregulation-based load estimation (MR) algorithm. MR calculates organ-scale loads by scaling and superimposing a set of predefined independent unit loads to optimise measured bone formation in high-, quiescence in medium-, and resorption in low-strain regions. We benchmarked our algorithm against a previously published load history (LH) algorithm using synthetic data, micro-CT images of murine vertebrae under defined experimental in vivo loadings, and HR-pQCT images from seven patients. Our algorithm consistently outperformed LH in all three datasets. In silico-generated time evolutions of distal radius geometries (n = 5) indicated significantly higher sensitivity, specificity, and accuracy for MR than LH (p < 0.01). This increased performance led to substantially better discrimination between physiological and extra-physiological loading in mice (n = 8). Moreover, a significantly (p < 0.01) higher association between remodelling events and computed local mechanical signals was found using MR [correct classification rate (CCR) = 0.42] than LH (CCR = 0.38) to estimate human distal radius loading. Future applications of MR may enable clinicians to link subtle changes in bone strength to changes in day-to-day loading, identifying weak spots in the bone microstructure for local intervention and personalised treatment approaches.

show abstract

Prediction of load in a long bone using an artificial neural network prediction algorithm

Cited by 22 publications

References 50 publications

Feature selection, artificial neural network prediction and experimental testing for predicting breakage rate of maize kernels based on mechanical properties

Feature selection, artificial neural network prediction and experimental testing for predicting breakage rate of maize kernels based on mechanical properties

Real‐time biomechanics using the finite element method and machine learning: Review and perspective

Bone Mechanoregulation Allows Subject-Specific Load Estimation Based on Time-Lapsed Micro-CT and HR-pQCT in Vivo

Contact Info

Product

Resources

About