Research Topic

Machine Learning and Artificial Intelligence in Musculoskeletal Research

About this Research Topic

Machine learning and artificial intelligence are nowadays being used in many industrial and research fields. Artificial neural networks, which are the most commonly employed machine learning techniques, are bio-logically inspired tools used to approximate complex nonlinear functions with a high number of inputs and either real or discrete output values. Artificial neural networks, especially the most recent architectures commonly referred to as “deep learning”, are powerful tools for nonlinear regression and classification problems, and are currently used for a high number of tasks in which a robust automatic performance is needed, e.g. handwriting recognition, face identification, automated driving systems and medical diagnosis. In musculoskeletal research, machine learning has been for example used for the classification of scoliosis and of intervertebral disc degeneration, to estimate muscle loads and to examine gait and motion patterns. In medical image analysis, machine learning is already widely employed for the automated identification of landmarks and biomarkers and for segmentation and registration of image sets. In such applications, the performances of deep learning techniques commonly exceed, in some cases even by a large margin, those of complex state-of-the-art algorithms for image analysis based on traditional techniques.
Machine learning techniques are approaching maturity, and are already providing remarkable performances in several fields including musculoskeletal research. Their usefulness in medical applications is however restricted by the size and quality of the training datasets. Indeed, training data need to be large and should include all the variability of the inputs which may be expected during the later use of the tool, including noise. Building large databases (the so-called “big data”) is a key step to introduce these methods in practi-cal applications. Taking into account the huge economic relevance of such topics, a rush to data gathering by commercial enterprises should be expected, with ethical and legal issues which should not be underesti-mated.


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

Machine learning and artificial intelligence are nowadays being used in many industrial and research fields. Artificial neural networks, which are the most commonly employed machine learning techniques, are bio-logically inspired tools used to approximate complex nonlinear functions with a high number of inputs and either real or discrete output values. Artificial neural networks, especially the most recent architectures commonly referred to as “deep learning”, are powerful tools for nonlinear regression and classification problems, and are currently used for a high number of tasks in which a robust automatic performance is needed, e.g. handwriting recognition, face identification, automated driving systems and medical diagnosis. In musculoskeletal research, machine learning has been for example used for the classification of scoliosis and of intervertebral disc degeneration, to estimate muscle loads and to examine gait and motion patterns. In medical image analysis, machine learning is already widely employed for the automated identification of landmarks and biomarkers and for segmentation and registration of image sets. In such applications, the performances of deep learning techniques commonly exceed, in some cases even by a large margin, those of complex state-of-the-art algorithms for image analysis based on traditional techniques.
Machine learning techniques are approaching maturity, and are already providing remarkable performances in several fields including musculoskeletal research. Their usefulness in medical applications is however restricted by the size and quality of the training datasets. Indeed, training data need to be large and should include all the variability of the inputs which may be expected during the later use of the tool, including noise. Building large databases (the so-called “big data”) is a key step to introduce these methods in practi-cal applications. Taking into account the huge economic relevance of such topics, a rush to data gathering by commercial enterprises should be expected, with ethical and legal issues which should not be underesti-mated.


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.

Topic Editors

Loading..

Submission Deadlines

31 January 2018 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..

Topic Editors

Loading..

Submission Deadlines

31 January 2018 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..
Loading..

total views article views article downloads topic views

}
 
Top countries
Top referring sites
Loading..

Comments

Loading..

Add a comment

Add comment
Back to top