Prediction of spinal curve progression in Adolescent Idiopathic Scoliosis using Random Forest regression

Garcia-Cano, Edgar; Cosı́o, Fernando Arámbula; Duong, Luc; Bellefleur, Christian; Roy‐Beaudry, Marjolaine; Joncas, Julie; Parent, Stefan; Labelle, Hubert

doi:10.1016/j.compbiomed.2018.09.029

Cited by 35 publications

(38 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective of the present paper is to provide a review of the publications that use ML algorithms is that they can be represented by tree diagrams, which are relatively easy to be understood by the user 64 . However, in the 2 publications that NN and tree based algorithms were compared to predict the biomechanical behavior of an anatomical structure, NN displayed an either similar 17 or superior performance 7 . Particularly, the publication where NN displayed a similar performance to tree based algorithms processed vectors with hundreds of thousands of elements to describe each training element, while the publication where NN displayed a vastly superior performance processed vectors with hundreds of millions of elements.…”

Section: Discussionmentioning

confidence: 99%

“…The feed forward NN displays a vastly superior performance when compared to RF in this particular case. In the second case, a combined approach is used to predict the evolution of the shape of the spine in subjects affected by AIS 17 . Initially, descriptors of the spine shape are calculated using either independent component analysis (ICA) or stacked denoising autoencoders (SDAE), based on a feedforward NN.…”

Section: Accepted Articlementioning

confidence: 99%

“…In the second case, a combined approach is used to predict the evolution of the shape of the spine in subjects affected by AIS. 17 Initially, descriptors of the spine shape are calculated using either independent component analysis (ICA) or stacked denoising autoencoders (SDAE), based on a feedforward NN. Then, the descriptors are used as input to a RF algorithm to calculate the final prediction.…”

Section: Machine Learning Algorithms Used As An Alternative To the Fimentioning

confidence: 99%

“…Fatigue and consequent crack growth in cancellous bone, specifically in the femur, is also studied with BM, in order to prevent and analyze the causes of bone fracture 15,16 . Additionally, prediction of the spine deformation in patients that suffer adolescent idiopathic scoliosis (AIS) is also modelled with BM 17,18 .…”

Section: Introductionmentioning

confidence: 99%

“…15,16 Additionally, prediction of the spine deformation in patients that suffer adolescent idiopathic scoliosis (AIS) is also modeled with BM. 17,18 As it can be noted, the BM of the behavior of anatomical structures is important for many clinical and research applications. In order to achieve a suitable BM, a set of PDEs and their corresponding boundary conditions have to be satisfied.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

et al. 2020

Self Cite

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

Section: Discussionmentioning

confidence: 99%

Section: Accepted Articlementioning

confidence: 99%

Section: Machine Learning Algorithms Used As An Alternative To the Fimentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

Natural History of Idiopathic Scoliosis

Shiju Majeed

2023

Paediatric Scoliosis

View full text Add to dashboard Cite

Current and emerging artificial intelligence applications for pediatric musculoskeletal radiology

Offiah

2021

Pediatr Radiol

View full text Add to dashboard Cite

Artificial intelligence (AI) is playing an ever-increasing role in radiology (more so in the adult world than in pediatrics), to the extent that there are unfounded fears it will completely take over the role of the radiologist. In relation to musculoskeletal applications of AI in pediatric radiology, we are far from the time when AI will replace radiologists; even for the commonest application (bone age assessment), AI is more often employed in an AI-assist mode rather than an AI-replace or AI-extend mode. AI for bone age assessment has been in clinical use for more than a decade and is the area in which most research has been conducted. Most other potential indications in children (such as appendicular and vertebral fracture detection) remain largely in the research domain. This article reviews the areas in which AI is most prominent in relation to the pediatric musculoskeletal system, briefly summarizing the current literature and highlighting areas for future research. Pediatric radiologists are encouraged to participate as members of the research teams conducting pediatric radiology artificial intelligence research.

show abstract

Prediction of spinal curve progression in Adolescent Idiopathic Scoliosis using Random Forest regression

Cited by 35 publications

References 27 publications

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

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

Natural History of Idiopathic Scoliosis

Current and emerging artificial intelligence applications for pediatric musculoskeletal radiology

Contact Info

Product

Resources

About