The treatment of organ and joint disorders is evolving rapidly with emerging applications leveraging the fields of machine learning, statistics, image analysis, and biomechanics. Biomechanical data and analysis of the tissues, organs and structures involved is crucial for diagnosis and treatment. Statistical inference based on statistical shape, kinematics, and intensity modeling allows for a principled and robust way of characterizing anatomical geometry (shape), relative pose (kinematics), and modality-specific image intensity representation of organs. Such statistical models of the structure and the materials involved can facilitate the determination of biomechanical data through computational biomechanics. Model complexity increases dramatically when a combination of features and/or multiple organs/joints are modeled together. Regardless, methods incorporating such models are now more frequently encountered in clinical applications.
While these model complexities are intrinsic to shape modeling and computer vision domains, they have potentially crucial applications in understanding personalized joint (e.g. knee), soft tissue (e.g. ligaments), and organ (e.g. heart) biomechanics in a multitude of disorders. Kinematic information in terms of joint motion or organ functional deformations has provided a deeper understanding of diagnosis and the management of underlying disorders or their treatment.
The interface of statistical anatomical and biomechanical modeling of the human organs has been recently recognized within the research community. Emerging modeling frameworks have been applied for studying the effects of organ biological variability on the etiology of multiple diseases or disorders. The techniques involved have promising application towards modeling patient-specificity in terms of its biomechanical understanding. New shallow and deep learning-based models have been shown to outperform statistical models, however, they need extremely large datasets and typically lack robustness and generalization ability, key elements for any clinical applicability. Thus, statistical models which have relatively lower dataset requirements, and are generally considered robust, with good generalizability, remain of interest. However, current literature lacks clinically oriented statistical modeling-based studies reporting metrics of performance on pipelines targeting computational biomechanics in organ disorders or bone and joint disease.
The goal of this Research Topic is to highlight statistical modeling-based computational biomechanics methods and/or frameworks and report on their utility (validation) in clinical applications related to organ or bone and joint disorders. We aim to publish recent developments in the translational field of computational anatomy (statistical shape and kinematics modeling of human organs and joints), computer vision (medical image visualization and analysis), their applications in clinical practice and beyond.
This Research Topic will give a comprehensive overview on the state-of-the-art of using statistical models in computational biomechanics for the treatment of joint or internal organ disorders. Contributions to this collection should focus on the innovative methods integrating statistical modeling approaches in shape, intensity, and/or kinematics for solving biomechanically oriented clinical problems, validation conducted on such methods, or application of such methods to solve specific clinical problems.
The themes addressed by this Research Topic will include, but are not limited to, the following:
· Computational biomechanics
· Gaussian mixture models
· Determining population-based organ or joint biomechanics
· Statistical models of shape, pose, kinematics and appearances
· Reporting performance metrics of statistical model-based frameworks for clinical applications
· Model-based image segmentation and disease classification,
· Advanced clinical applications of statistical shape models
We welcome the submission of Original Research, Technical Notes, Reviews, Mini-reviews, Case studies, and Perspective articles.
The treatment of organ and joint disorders is evolving rapidly with emerging applications leveraging the fields of machine learning, statistics, image analysis, and biomechanics. Biomechanical data and analysis of the tissues, organs and structures involved is crucial for diagnosis and treatment. Statistical inference based on statistical shape, kinematics, and intensity modeling allows for a principled and robust way of characterizing anatomical geometry (shape), relative pose (kinematics), and modality-specific image intensity representation of organs. Such statistical models of the structure and the materials involved can facilitate the determination of biomechanical data through computational biomechanics. Model complexity increases dramatically when a combination of features and/or multiple organs/joints are modeled together. Regardless, methods incorporating such models are now more frequently encountered in clinical applications.
While these model complexities are intrinsic to shape modeling and computer vision domains, they have potentially crucial applications in understanding personalized joint (e.g. knee), soft tissue (e.g. ligaments), and organ (e.g. heart) biomechanics in a multitude of disorders. Kinematic information in terms of joint motion or organ functional deformations has provided a deeper understanding of diagnosis and the management of underlying disorders or their treatment.
The interface of statistical anatomical and biomechanical modeling of the human organs has been recently recognized within the research community. Emerging modeling frameworks have been applied for studying the effects of organ biological variability on the etiology of multiple diseases or disorders. The techniques involved have promising application towards modeling patient-specificity in terms of its biomechanical understanding. New shallow and deep learning-based models have been shown to outperform statistical models, however, they need extremely large datasets and typically lack robustness and generalization ability, key elements for any clinical applicability. Thus, statistical models which have relatively lower dataset requirements, and are generally considered robust, with good generalizability, remain of interest. However, current literature lacks clinically oriented statistical modeling-based studies reporting metrics of performance on pipelines targeting computational biomechanics in organ disorders or bone and joint disease.
The goal of this Research Topic is to highlight statistical modeling-based computational biomechanics methods and/or frameworks and report on their utility (validation) in clinical applications related to organ or bone and joint disorders. We aim to publish recent developments in the translational field of computational anatomy (statistical shape and kinematics modeling of human organs and joints), computer vision (medical image visualization and analysis), their applications in clinical practice and beyond.
This Research Topic will give a comprehensive overview on the state-of-the-art of using statistical models in computational biomechanics for the treatment of joint or internal organ disorders. Contributions to this collection should focus on the innovative methods integrating statistical modeling approaches in shape, intensity, and/or kinematics for solving biomechanically oriented clinical problems, validation conducted on such methods, or application of such methods to solve specific clinical problems.
The themes addressed by this Research Topic will include, but are not limited to, the following:
· Computational biomechanics
· Gaussian mixture models
· Determining population-based organ or joint biomechanics
· Statistical models of shape, pose, kinematics and appearances
· Reporting performance metrics of statistical model-based frameworks for clinical applications
· Model-based image segmentation and disease classification,
· Advanced clinical applications of statistical shape models
We welcome the submission of Original Research, Technical Notes, Reviews, Mini-reviews, Case studies, and Perspective articles.