A markerless beam's eye view tumor tracking algorithm based on structure conversion and demons registration in medical image / 中华放射肿瘤学杂志

Objective:To propose a markerless beam's eye view (BEV) tumor tracking algorithm, which can be applied to megavolt (MV) images with poor image quality, multi-leaf collimator (MLC) occlusion and non-rigid deformation.Methods:Window template matching, image structure transformation and demons non-rigid registration method were used to solve the registration problem in MV images. The quality assurance (QA) plan was generated in the phantom and executed after manually setting the treatment offset on the accelerator, and 682 electronic portal imaging device (EPID) images in the treatment process were collected as fixed images. Meanwhile, the digitally reconstructured radiograph (DRR) images corresponding to the field angle in the planning system were collected as floating images to verify the accuracy of the algorithm. In addition, a total of 533 images were collected from 21 cases of lung tumor treatment data for tumor tracking study, providing quantitative results of tumor location changes during treatment. Image similarity was used for third-party verification of tracking results.Results:The algorithm could cope with different degrees (10%-80%) of image missing. In the phantom verification, 86.8% of the tracking errors were less than 3 mm, and 80% were less than 2 mm. Normalized mutual information (NMI) varied from 1.182±0.026 to 1.202±0.027 ( P<0.005) before and after registration and the change of Hausdorff distance (HD) was from 57.767±6.474 to 56.664±6.733 ( P<0.005). The case results were predominantly translational (-6.0 mm to 6.2 mm), but non-rigid deformation still existed. NMI varied from 1.216±0.031 to 1.225±0.031 ( P<0.005) before and after registration and the change of HD was from 46.384±7.698 to 45.691±8.089 ( P<0.005). Conclusions:The proposed algorithm can cope with different degrees of image missing and performs well in non-rigid registration with data missing images which can be applied in different radiotherapy technologies. It provides a reference idea for processing MV images with multi-modality, partial data and poor image quality.

Markerless Gait Analysis System Based on Deep Learning Fusion algorithm / 医用生物力学

Objective Taking three-dimensional (3D) motion capture system (MoCap) as the gold standard, a deep learning fusion model based on bi-lateral long short-term memory (BiLSTM) recurrent neural network and linear regression algorithm was developed to reduce system error of the Kinect sensor in lower limb kinematics measurement. Methods Ten healthy male college students were recruited for gait analysis. The 3D coordinates of the reflective markers and the lower limb joint centers were simultaneously collected using the MoCap system and the Kinect V2 sensor, respectively. The joint angles of lower limbs were calculated using the Cleveland clinic kinematic model and the Kinect kinematic model, respectively. The dataset was constructed using the MoCap system as the target and the angles via the Kinect system as the input. A BiLSTM network and a linear regression model for all lower limb angles were developed to obtain the refined angles. A leave-one subject-out cross-validation method was employed to study the performance of the models. The coefficient of multiple correlations (CMC) and root mean square error (RMSE) were used to investigate the similarity and the mean deviation between the joint angle waveforms via the MoCap and the Kinect system. ResultsIn comparison with the linear regression algorithm, the BiLSTM had better performance in the aspect of dealing highly nonlinear regression problems, especially for hip flexion/extension, hip adduction/abduction, and ankle dorsi/plantar flexion angles. The deep learning refined model significantly reduced the system error of Kinect. The mean RMSEs for all joint angles were mainly smaller than 10°, and the RMSEs of the hip joint were smaller than 5°. The joint angle waveforms presented very good similarity with the golden standard. The CMCs of joint angles were greater than 0.7 except for hip rotation angle. Conclusions The markerless gait analysis system based on deep learning fusion model developed in this study can accurately assess lower limb kinematics, joint mobility, walking functions, and has good prospect to be applied in clinical and home rehabilitation.

A pilot study on the functional outcome using markerless motion analysis tool and surface emg of nerve transfers for upper trunk brachial plexus injuries

INTRODUCTION@#Brachial plexus injuries (BPI) have devastating functional effects. Clinical outcomes of BPI reconstruction have been documented in literature; however, these do not use EMG and quantitative kinematic studies.@*OBJECTIVE@#This study aims to use a markerless motion analysis tool (KINECT) and surface EMG to assess the functional outcomes of adult patients with traumatic upper trunk BPI who have undergone nerve transfers for the shoulder and elbow in comparison to the normal contralateral limb.@*METHODS@#This is an exploratory study which evaluated three participants with BPI after nerve reconstruction. KINECT was used to evaluate the kinematics (range of motion, velocity, and acceleration) and the surface EMG for muscle electrical signals (root mean square, peak EMG signal, and peak activation time) of the extremities. The means of each parameter were computed and compared using t-test or Mann-Whitney U test.@*RESULTS@#Participant C, with the best clinical recovery, showed mostly higher KINECT and EMG values for the BPI extremity. There was a significant difference between the KINECT data of Participants A and B, with lower mean values for the BPI extremity. Most of the EMG results showed lower signals for the BPI extremity, with statistical significance.@*CONCLUSION@#The KINECT and surface EMG provide simple, cost-effective, quick, and objective assessment tools. These can be used for monitoring and as basis for formulating individualized interventions. A specific algorithm should be developed for the KINECT sensors to address errors in data collection. A fine needle EMG may be more useful in evaluating the muscles involved in shoulder external rotation.

Upper extremity temporospatial parameters and kinematics of Filipino track and field paralympians during wheelchair Propulsion: An analysis using a Kinect-based markerless motion analysis system

@#<p style="text-align: justify;"><strong>OBJECTIVE:</strong> The potential of a low-cost, novel Kinect?-based markerless motion analysis system as a tool to measure temporospatial parameters, joint and muscle kinematics, and hand trajectory patterns during the propulsion and recovery phase of wheelchair propulsion (WCP) was determined.</p><p style="text-align: justify;"><strong>METHODS:</strong>Twenty (20) adult male track and field paralympians,(mean age = 36 ± 8.47) propelled themselves on a wheelchair ergometer system while their upper extremity motion was recorded by two Kinect? cameras and processed.</p><p style="text-align: justify;"><strong>RESULTS:</strong> The temporospatial parameters, joint kinematics, and hand trajectory patterns during the propulsion and recovery phase of each participant's WCP cycle were determined and averaged. Average cycle time was 1.45s ± 0.19, average cadence was 0.70 cycles/s ± 0.09, and average speed was 0.76m/s ± 0.32. Average shoulder flexion was 30.99° ± 28.38, average elbow flexion was 24.23° ± 12.25, and average wrist flexion was 12.82° ± 26.78. Eighty five percent (85%) of the participants used a semicircular hand trajectory pattern.</p><p style="text-align: justify;"><strong>CONCLUSION:</strong> The low-cost, novel Kinect?-based markerless motion analysis system had the potential to obtain measurable values during independent wheelchair propu