Automatic tracking of healthy joint kinematics from stereo-radiography sequences. (December 2021)

• Record Type: Journal Article
• Authors: Burton, William S.; Myers, Casey A.; Jensen, Andrew; Hamilton, Landon; Shelburne, Kevin B.; Banks, Scott A.; Rullkoetter, Paul J.
• Is Part Of: Computers in biology and medicine. Volume 139(2021)
• Publication Date: 2021-12
• Subjects: Biomechanics -- Deep learning -- Optimization -- Knee -- Medical imaging; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104945
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Kinematic tracking of healthy joints in radiography sequences is frequently performed by maximizing similarities between computed perspective projections of 3D computer models and corresponding objects' appearances in radiographic images. Significant human effort associated with manual tracking presents a major bottleneck in biomechanics research methods and limits the scale of target applications. The current work introduces a method for fully-automatic tracking of tibiofemoral and patellofemoral kinematics in stereo-radiography sequences for subjects performing dynamic activities. The proposed method involves the application of convolutional neural networks for annotating radiographs and a multi-stage optimization pipeline for estimating bone pose based on information provided by neural net predictions. Predicted kinematics are evaluated by comparing against manually-tracked trends across 20 distinct trials. Median absolute differences below 1.5 millimeters or degrees for 6 tibiofemoral and 3 patellofemoral degrees of freedom demonstrate the utility of our approach, which improves upon previous semi-automatic methods by enabling end-to-end automation. Implementation of a fully-automatic pipeline for kinematic tracking will benefit evaluation of human movement by enabling large-scale studies of healthy knee kinematics. Highlights: Tracking of knee kinematics from stereo-radiography is performed with model-image registration. Model-image registration is frequently performed using semi-automatic approaches. Semi-automatic methods moderately accelerate the tracking process but limit scalability. The current work introduces a fully-automatic method for kinematic tracking of healthy knees. The proposed method draws upon optimization and deep learning algorithms to automate tracking.