Automatic tracking of healthy joint kinematics from stereo-radiography sequences

Scan-Free and Fully Automatic Tracking of Native Knee Anatomy from Dynamic Stereo-Radiography with Statistical Shape and Intensity Models

Kinematic tracking of native anatomy from stereo-radiography provides a quantitative basis for evaluating human movement. Conventional tracking procedures require significant manual effort and call for acquisition and annotation of subject-specific volumetric medical images. The current work introduces a framework for fully automatic tracking of native knee anatomy from dynamic stereo-radiography which forgoes reliance on volumetric scans. The method consists of three computational steps. First, captured radiographs are annotated with segmentation maps and anatomic landmarks using a convolutional neural network. Next, a non-convex polynomial optimization problem formulated from annotated landmarks is solved to acquire preliminary anatomy and pose estimates. Finally, a global optimization routine is performed for concurrent refinement of anatomy and pose. An objective function is maximized which quantifies similarities between masked radiographs and digitally reconstructed radiographs produced from statistical shape and intensity models. The proposed framework was evaluated against manually tracked trials comprising dynamic activities, and additional frames capturing a static knee phantom. Experiments revealed anatomic surface errors routinely below 1.0 mm in both evaluation cohorts. Median absolute errors of individual bone pose estimates were below 1.0∘ or mm for 15 out of 18 degrees of freedom in both evaluation cohorts. Results indicate that accurate pose estimation of native anatomy from stereo-radiography may be performed with significantly reduced manual effort, and without reliance on volumetric scans.

Fully automatic tracking of native knee kinematics from stereo-radiography with digitally reconstructed radiographs

Precise measurement of joint-level motion from stereo-radiography facilitates understanding of human movement. Conventional procedures for kinematic tracking require significant manual effort and are time intensive. The current work introduces a method for fully automatic tracking of native knee kinematics from stereo-radiography sequences. The framework consists of three computational steps. First, biplanar radiograph frames are annotated with segmentation maps and key points using a convolutional neural network. Next, initial bone pose estimates are acquired by solving a polynomial optimization problem constructed from annotated key points and anatomic landmarks from digitized models. A semidefinite relaxation is formulated to realize the global minimum of the non-convex problem. Pose estimates are then refined by registering computed tomography-based digitally reconstructed radiographs to masked radiographs. A novel rendering method is also introduced which enables generating digitally reconstructed radiographs from computed tomography scans with inconsistent slice widths. The automatic tracking framework was evaluated with stereo-radiography trials manually tracked with model-image registration, and with frames which capture a synthetic leg phantom. The tracking method produced pose estimates which were consistently similar to manually tracked values; and demonstrated pose errors below 1.0 degree or millimeter for all femur and tibia degrees of freedom in phantom trials. Results indicate the described framework may benefit orthopaedics and biomechanics applications through acceleration of kinematic tracking.

Investigation of Characteristic Motion Patterns of the Knee Joint During a Weightbearing Flexion

This study aimed to develop and validate a novel flexion axis concept by calculating the points on femoral condyles that could maintain constant heights during knee flexion. Twenty-two knees of 22 healthy subjects were investigated when performing a weightbearing single leg lunge. The knee positions were captured using a validated dual fluoroscopic image system. The points on sagittal planes of the femoral condyles that had minimal changes in heights from the tibial plane along the flexion path were calculated. It was found that the points do formulate a medial-lateral flexion axis that was defined as the iso-height axis (IHA). The six degrees of freedom (6DOF) kinematics data calculated using the IHA were compared with those calculated using the conventional transepicondylar axis and geometrical center axis. The IHA measured minimal changes in proximal-distal translations and varus-valgus rotations along the flexion path, indicating that the IHA may have interesting clinical implications. Therefore, identifying the IHA could provide an alternative physiological reference for improvement of contemporary knee surgeries, such as ligament reconstruction and knee replacement surgeries that are aimed to reproduce normal knee kinematics and medial/lateral soft tissue tensions during knee flexion.

Joint Track Machine Learning: An Autonomous Method of Measuring Total Knee Arthroplasty Kinematics From Single-Plane X-Ray Images

BACKGROUND

Dynamic radiographic measurements of 3-dimensional (3-D) total knee arthroplasty (TKA) kinematics have provided important information for implant design and surgical technique for over 30 years. However, current methods of measuring TKA kinematics are too cumbersome, inaccurate, or time-consuming for practical clinical application. Even state-of-the-art techniques require human-supervision to obtain clinically reliable kinematics. Eliminating human supervision could potentially make this technology practical for clinical use.

METHODS

We demonstrate a fully autonomous pipeline for quantifying 3D-TKA kinematics from single-plane radiographic imaging. First, a convolutional neural network (CNN) segmented the femoral and tibial implants from the image. Second, those segmented images were compared to precomputed shape libraries for initial pose estimates. Lastly, a numerical optimization routine aligned 3D implant contours and fluoroscopic images to obtain the final implant poses.

RESULTS

The autonomous technique reliably produces kinematic measurements comparable to human-supervised measures, with root-mean-squared differences of less than 0.7 mm and 4° for our test data, and 0.8 mm and 1.7° for external validation studies.

CONCLUSION

A fully autonomous method to measure 3D-TKA kinematics from single-plane radiographic images produces results equivalent to a human-supervised method, and may soon make it practical to perform these measurements in a clinical setting.

Fully automatic tracking of native glenohumeral kinematics from stereo-radiography

The current work introduces a system for fully automatic tracking of native glenohumeral kinematics in stereo-radiography sequences. The proposed method first applies convolutional neural networks to obtain segmentation and semantic key point predictions in biplanar radiograph frames. Preliminary bone pose estimates are computed by solving a non-convex optimization problem with semidefinite relaxations to register digitized bone landmarks to semantic key points. Initial poses are then refined by registering computed tomography-based digitally reconstructed radiographs to captured scenes, which are masked by segmentation maps to isolate the shoulder joint. A particular neural net architecture which exploits subject-specific geometry is also introduced to improve segmentation predictions and increase robustness of subsequent pose estimates. The method is evaluated by comparing predicted glenohumeral kinematics to manually tracked values from 17 trials capturing 4 dynamic activities. Median orientation differences between predicted and ground truth poses were 1.7∘ and 8.6∘ for the scapula and humerus, respectively. Joint-level kinematics differences were less than 2∘ in 65%, 13%, and 63% of frames for XYZ orientation DoFs based on Euler angle decompositions. Automation of kinematic tracking can increase scalability of tracking workflows in research, clinical, or surgical applications.

Ball-in-socket medial conformity with posterior cruciate ligament retention neither limits internal tibial rotation and knee flexion nor lowers clinical outcome scores after unrestricted kinematically aligned total knee arthroplasty

PURPOSE

For a new tibial insert design with ball-in-socket (B-in-S) medial conformity (MC), posterior cruciate ligament (PCL) retention, and flat lateral articular surface (B-in-S MC + PCL), this study determined whether internal tibial rotation and knee flexion were limited and clinical outcome scores were lower during weight-bearing activities relative to an insert with intermediate (I) (i.e., less than ball-in-socket) medial conformity (I MC + PCL).

METHODS

Twenty-five patients were treated with bilateral unrestricted, caliper-verified kinematic alignment (KA) total knee arthroplasty (TKA) with an I MC + PCL insert and B-in-S MC + PCL insert in opposite knees. Each patient performed weight-bearing deep knee bend, step up, and chair rise under single-plane fluoroscopy. Analysis following 3D model-to-2D image registration determined internal tibial rotation. For each TKA, knee flexion was measured and patients completed clinical outcome scoring questionnaires.

RESULTS

Internal tibial rotation did not differ between conformities during chair rise and step up (p = 0.3419 and 0.1030, respectively). During deep knee bend, internal tibial rotation between 90° and maximum flexion was 3° greater in the B-in-S MC + PCL group (18° vs 15°) (p = 0.0290). Mean knee flexion (p = 0.3115) and median Forgotten Joint Score (FJS), Oxford Knee Score (OKS), and Western Ontario and McMasters Universities Arthritis Index (WOMAC) scores (p = 0.2100, 0.2154, and 0.4542, respectively) did not differ between conformities.

CONCLUSION

An insert with ball-in-socket medial conformity, which maximizes anteroposterior (AP) stability, did not limit internal tibial rotation and knee flexion and did not lower patient-reported outcomes when implanted with unrestricted caliper-verified KA and PCL retention. The high AP stability provided by the medial ball-in-socket might interest those surgeons exploring the treatment of the active patient with a desire to return to high-level and athletic activities.

Designing anisotropic porous bone scaffolds using a self-learning convolutional neural network model

The design of bionic bone scaffolds to mimic the behaviors of native bone tissue is crucial in clinical application, but such design is very challenging due to the complex behaviors of native bone tissues. In the present study, bionic bone scaffolds with the anisotropic mechanical properties similar to those of native bone tissues were successfully designed using a novel self-learning convolutional neural network (CNN) framework. The anisotropic mechanical property of bone was first calculated from the CT images of bone tissues. The CNN model constructed was trained and validated using the predictions from the heterogonous finite element (FE) models. The CNN model was then used to design the scaffold with the elasticity matrix matched to that of the replaced bone tissues. For the comparison, the bone scaffold was also designed using the conventional method. The results showed that the mechanical properties of scaffolds designed using the CNN model are closer to those of native bone tissues. In conclusion, the self-learning CNN framework can be used to design the anisotropic bone scaffolds and has a great potential in the clinical application.

PredMHC: An Effective Predictor of Major Histocompatibility Complex Using Mixed Features

The major histocompatibility complex (MHC) is a large locus on vertebrate DNA that contains a tightly linked set of polymorphic genes encoding cell surface proteins essential for the adaptive immune system. The groups of proteins encoded in the MHC play an important role in the adaptive immune system. Therefore, the accurate identification of the MHC is necessary to understand its role in the adaptive immune system. An effective predictor called PredMHC is established in this study to identify the MHC from protein sequences. Firstly, PredMHC encoded a protein sequence with mixed features including 188D, APAAC, KSCTriad, CKSAAGP, and PAAC. Secondly, three classifiers including SGD, SMO, and random forest were trained on the mixed features of the protein sequence. Finally, the prediction result was obtained by the voting of the three classifiers. The experimental results of the 10-fold cross-validation test in the training dataset showed that PredMHC can obtain 91.69% accuracy. Experimental results on comparison with other features, classifiers, and existing methods showed the effectiveness of PredMHC in predicting the MHC.