{"title":"利用深度学习神经网络模型从皮肤标记估算三维足骨运动学。","authors":"","doi":"10.1016/j.jbiomech.2024.112252","DOIUrl":null,"url":null,"abstract":"<div><p>The human foot is a complex structure comprising 26 bones, whose coordinated movements facilitate proper deformation of the foot, ensuring stable and efficient locomotion. Despite their critical role, the kinematics of foot bones during movement remain largely unexplored, primarily due to the absence of non-invasive methods for measuring foot bone kinematics. This study addresses this gap by proposing a neural network model for estimating foot bone movements using surface markers. To establish a mapping between the positions and orientations of the foot bones and 41 skin markers attached on the human foot, computed tomography scans of the foot with the markers were obtained with eleven healthy adults and thirteen cadaver specimens in different foot postures. The neural network architecture comprises four layers, with input and output layers containing the 41 marker positions and the positions and orientations of the nine foot bones, respectively. The mean errors between estimated and true foot bone position and orientation were 0.5 mm and 0.6 degrees, respectively, indicating that the neural network can provide 3D kinematics of the foot bones with sufficient accuracy in a non-invasive manner, thereby contributing to a better understanding of foot function and the pathogenetic mechanisms underlying foot disorders.</p></div>","PeriodicalId":15168,"journal":{"name":"Journal of biomechanics","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Estimating three-dimensional foot bone kinematics from skin markers using a deep learning neural network model\",\"authors\":\"\",\"doi\":\"10.1016/j.jbiomech.2024.112252\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The human foot is a complex structure comprising 26 bones, whose coordinated movements facilitate proper deformation of the foot, ensuring stable and efficient locomotion. Despite their critical role, the kinematics of foot bones during movement remain largely unexplored, primarily due to the absence of non-invasive methods for measuring foot bone kinematics. This study addresses this gap by proposing a neural network model for estimating foot bone movements using surface markers. To establish a mapping between the positions and orientations of the foot bones and 41 skin markers attached on the human foot, computed tomography scans of the foot with the markers were obtained with eleven healthy adults and thirteen cadaver specimens in different foot postures. The neural network architecture comprises four layers, with input and output layers containing the 41 marker positions and the positions and orientations of the nine foot bones, respectively. The mean errors between estimated and true foot bone position and orientation were 0.5 mm and 0.6 degrees, respectively, indicating that the neural network can provide 3D kinematics of the foot bones with sufficient accuracy in a non-invasive manner, thereby contributing to a better understanding of foot function and the pathogenetic mechanisms underlying foot disorders.</p></div>\",\"PeriodicalId\":15168,\"journal\":{\"name\":\"Journal of biomechanics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2024-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of biomechanics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0021929024003300\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"BIOPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of biomechanics","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0021929024003300","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BIOPHYSICS","Score":null,"Total":0}
Estimating three-dimensional foot bone kinematics from skin markers using a deep learning neural network model
The human foot is a complex structure comprising 26 bones, whose coordinated movements facilitate proper deformation of the foot, ensuring stable and efficient locomotion. Despite their critical role, the kinematics of foot bones during movement remain largely unexplored, primarily due to the absence of non-invasive methods for measuring foot bone kinematics. This study addresses this gap by proposing a neural network model for estimating foot bone movements using surface markers. To establish a mapping between the positions and orientations of the foot bones and 41 skin markers attached on the human foot, computed tomography scans of the foot with the markers were obtained with eleven healthy adults and thirteen cadaver specimens in different foot postures. The neural network architecture comprises four layers, with input and output layers containing the 41 marker positions and the positions and orientations of the nine foot bones, respectively. The mean errors between estimated and true foot bone position and orientation were 0.5 mm and 0.6 degrees, respectively, indicating that the neural network can provide 3D kinematics of the foot bones with sufficient accuracy in a non-invasive manner, thereby contributing to a better understanding of foot function and the pathogenetic mechanisms underlying foot disorders.
期刊介绍:
The Journal of Biomechanics publishes reports of original and substantial findings using the principles of mechanics to explore biological problems. Analytical, as well as experimental papers may be submitted, and the journal accepts original articles, surveys and perspective articles (usually by Editorial invitation only), book reviews and letters to the Editor. The criteria for acceptance of manuscripts include excellence, novelty, significance, clarity, conciseness and interest to the readership.
Papers published in the journal may cover a wide range of topics in biomechanics, including, but not limited to:
-Fundamental Topics - Biomechanics of the musculoskeletal, cardiovascular, and respiratory systems, mechanics of hard and soft tissues, biofluid mechanics, mechanics of prostheses and implant-tissue interfaces, mechanics of cells.
-Cardiovascular and Respiratory Biomechanics - Mechanics of blood-flow, air-flow, mechanics of the soft tissues, flow-tissue or flow-prosthesis interactions.
-Cell Biomechanics - Biomechanic analyses of cells, membranes and sub-cellular structures; the relationship of the mechanical environment to cell and tissue response.
-Dental Biomechanics - Design and analysis of dental tissues and prostheses, mechanics of chewing.
-Functional Tissue Engineering - The role of biomechanical factors in engineered tissue replacements and regenerative medicine.
-Injury Biomechanics - Mechanics of impact and trauma, dynamics of man-machine interaction.
-Molecular Biomechanics - Mechanical analyses of biomolecules.
-Orthopedic Biomechanics - Mechanics of fracture and fracture fixation, mechanics of implants and implant fixation, mechanics of bones and joints, wear of natural and artificial joints.
-Rehabilitation Biomechanics - Analyses of gait, mechanics of prosthetics and orthotics.
-Sports Biomechanics - Mechanical analyses of sports performance.