3D free-hand ultrasound to register anatomical landmarks at the pelvis and localize the hip joint center in lean and obese individuals.

3D free-hand ultrasound (3DFUS) is becoming increasingly popular to assist clinical gait analysis because it is cost- and time-efficient and does not expose participants to radiation. The aim of this study was to evaluate its reliability in localizing the anterior superior iliac spine (ASIS) at the pelvis and the hip joint centers (HJC). Additionally, we evaluated its accuracy to get a rough estimation of the potential to use of 3DFUS to segment bony surface. This could offer potential to register medical images to motion capture data in future. To evaluate reliability, a test-retest study was conducted in 16 lean and 19 obese individuals. The locations of the ASIS were determined by manual marker placement (MMP), an instrumented pointer technique (IPT), and with 3DFUS. The HJC location was also determined with 3DFUS. To quantify reliability, intraclass correlation coefficients (ICCs), the standard error of measurement (SEm), among other statistical parameters, were calculated for the identified locations between the test and retest. To assess accuracy, the surface of a human plastic pelvic phantom was segmented with 3DFUS in a distilled water bath in 27 trials and compared to a 3D laser scan of the pelvis. Regarding reliability, the MMP, but especially the IPT showed high reliability in lean (SEm: 2-3 mm) and reduced reliability in obese individuals (SEm: 6-15 mm). Compared to MMP and IPT, 3DFUS presented lower reliability in the lean group (SEm: 2-4 mm vs. 2-8 mm, respectively) but slightly better values in the obese group (SEm: 7-11 mm vs. 6-16 mm, respectively). Correlations between test-retest reliability and torso body fat mass (% of body mass) indicated a moderate to strong relationship for MMP and IPT but only a weak correlation for the 3DFUS approach. The water-bath experiments indicated an acceptable level of 3.5 (1.7) mm of accuracy for 3DFUS in segmenting bone surface. Despite some difficulties with single trials, our data give further rise to the idea that 3DFUS could serve as a promising tool in future to inform marker placement and hip joint center location, especially in groups with higher amount of body fat.

Reliability of walking and stair climbing kinematics in a young obese population using a standard kinematic and the CGM2 model.

BACKGROUND: Recently, the successor of the Conventional Gait Model, the CGM2 was introduced. Even though achievable reliability of gait kinematics is a well-assessed topic in gait analysis for several models, information about reliability in difficult study samples with high amount of subcutaneous fat is scarce and to date, not available for the CGM2. Therefore, this study evaluated the test-retest reliability of the CGM2 model for difficult data with high amount of soft tissue artifacts. RESEARCH QUESTION: What is the test-retest reliability of the CGM2 during level walking and stair climbing in a young obese population? Is there a clinically relevant difference in reliability between a standard direct kinematic model and the CGM2? METHODS: A retrospective test-retest dataset from eight male and two female volunteers was used. It comprised standard 3D gait analysis data of three walking conditions: level walking, stair ascent and descent. To quantify test-retest reliability the Standard Error of Measurement (SEM) was calculated for each kinematic waveform for a direct kinematic model (Cleveland clinic marker set) and the CGM2. RESULTS: Both models showed an acceptable level of test-retest reliability in all three walking conditions. However, SEM ranged between two and five degrees (∘) for both models and, thus, needs consideration during interpretation. The choice of model did not affect reliability considerably. Differences in SEM between stair climbing and level walking were small and not clinically relevant (<1°). SIGNIFICANCE: Results showed an acceptable level of reliability and only small differences between the models. It is noteworthy, that the SEM was increased during the first half of swing in all walking conditions. This might be attributed to increased variability resulting for example from inaccurate knee and ankle axis definitions or increased variability in the gait pattern and needs to be considered during data interpretation.

GaiTRec, a large-scale ground reaction force dataset of healthy and impaired gait.

The quantification of ground reaction forces (GRF) is a standard tool for clinicians to quantify and analyze human locomotion. Such recordings produce a vast amount of complex data and variables which are difficult to comprehend. This makes data interpretation challenging. Machine learning approaches seem to be promising tools to support clinicians in identifying and categorizing specific gait patterns. However, the quality of such approaches strongly depends on the amount of available annotated data to train the underlying models. Therefore, we present GAITREC, a comprehensive and completely annotated large-scale dataset containing bi-lateral GRF walking trials of 2,084 patients with various musculoskeletal impairments and data from 211 healthy controls. The dataset comprises data of patients after joint replacement, fractures, ligament ruptures, and related disorders at the hip, knee, ankle or calcaneus during their entire stay(s) at a rehabilitation center. The data sum up to a total of 75,732 bi-lateral walking trials and enable researchers to classify gait patterns at a large-scale as well as to analyze the entire recovery process of patients.

Input representations and classification strategies for automated human gait analysis.

BACKGROUND: Quantitative gait analysis produces a vast amount of data, which can be difficult to analyze. Automated gait classification based on machine learning techniques bear the potential to support clinicians in comprehending these complex data. Even though these techniques are already frequently used in the scientific community, there is no clear consensus on how the data need to be preprocessed and arranged to assure optimal classification accuracy outcomes. RESEARCH QUESTION: Is there an optimal data aggregation and preprocessing workflow to optimize classification accuracy outcomes? METHODS: Based on our previous work on automated classification of ground reaction force (GRF) data, a sequential setup was followed: firstly, several aggregation methods - early fusion and late fusion - were compared, and secondly, based on the best aggregation method identified, the expressiveness of different combinations of signal representations was investigated. The employed dataset included data from 910 subjects, with four gait disorder classes and one healthy control group. The machine learning pipeline comprised principle component analysis (PCA), z-standardization and a support vector machine (SVM). RESULTS: The late fusion aggregation, i.e., utilizing majority voting on the classifier's predictions, performed best. In addition, the use of derived signal representations (relative changes and signal differences) seems to be advantageous as well. SIGNIFICANCE: Our results indicate that great caution is needed when data preprocessing and aggregation methods are selected, as these can have an impact on classification accuracies. These results shall serve future studies as a guideline for the choice of data aggregation and preprocessing techniques to be employed.

Automatic Classification of Functional Gait Disorders.

This paper proposes a comprehensive investigation of the automatic classification of functional gait disorders (GDs) based solely on ground reaction force (GRF) measurements. The aim of this study is twofold: first, to investigate the suitability of the state-of-the-art GRF parameterization techniques (representations) for the discrimination of functional GDs; and second, to provide a first performance baseline for the automated classification of functional GDs for a large-scale dataset. The utilized database comprises GRF measurements from 279 patients with GDs and data from 161 healthy controls (N). Patients were manually classified into four classes with different functional impairments associated with the "hip", "knee", "ankle", and "calcaneus". Different parameterizations are investigated: GRF parameters, global principal component analysis (PCA) based representations, and a combined representation applying PCA on GRF parameters. The discriminative power of each parameterization for different classes is investigated by linear discriminant analysis. Based on this analysis, two classification experiments are pursued: distinction between healthy and impaired gait (N versus GD) and multiclass classification between healthy gait and all four GD classes. Experiments show promising results and reveal among others that several factors, such as imbalanced class cardinalities and varying numbers of measurement sessions per patient, have a strong impact on the classification accuracy and therefore need to be taken into account. The results represent a promising first step toward the automated classification of GDs and a first performance baseline for future developments in this direction.

Is the reliability of 3D kinematics of young obese participants dependent on the hip joint center localization method used?

The aim of this study was to investigate if the test-retest reliability for three-dimensional (3D) gait kinematics in a young obese population is affected by using either a predictive (Davis) or a functional (SCoRE) hip joint center (HJC) localization approach. A secondary goal was to analyze how consistent both methods perform in estimating the HJC position. A convenience sample of ten participants, two females and eight males with an age-based body mass index (BMI) above the 97th percentile (mean±SD: 34.2±3.9kg/m2) was recruited. Participants underwent two 3D gait analysis sessions separated by a minimum of one day and a maximum of seven days. The standard error of measurement (SEM) and the root mean square error (RMSE) of key kinematic parameters along with the root mean square deviation (RMSD) of the entire waveforms were used to analyze the test-retest reliability. To get an estimate of the consistency of both HJC localization methods, the HJC positions determined by both methods were compared to each other. SEM, RMSE, and RMSD results indicate that the HJC position estimations between both methods are not different and demonstrate moderate to good reliability to estimate joint kinematics. With respect to the localization of the HJC, notable inconsistencies ranging from 0 to 5.4cm were observed. In conclusion, both approaches appear equally reliable. However, the inconsistent HJC estimation points out, that accuracy seems to be a big issue in these methods. Future research should attend to this matter.