Quantification of tumorsphere migration with a physics-based machine learning method.

Current analysis techniques available for migration assays only provide quantitative measurements for overall migration. However, the potential of regional migration analyses can open further insight into migration patterns and more avenues of experimentation with the same assays. Previously, we developed an analysis pipeline utilizing the finite element (FE) method to show its potential in analyzing glioblastoma (GBM) tumorsphere migration, especially in characterizing regional changes in the migration pattern. This study aims to streamline and further automate the analysis system by integrating the machine-learning-based U-Net segmentation with the FE method. Our U-Net-based segmentation achieved a 98% accuracy in segmenting our tumorspheres. From the segmentations, FE models made up of 3D hexahedral elements were generated, and the migration patterns of the tumorspheres were analyzed under treatments B and C (under non-disclosure agreements). Our results show that our overall migration analysis correlated very strongly (R2 of 0.9611 and 0.9986 for treatments B and C, respectively) with ImageJ's method of migration area analysis, which is the most common method of tumorsphere migration analysis. Additionally, we were able to quantitatively represent the regional migration patterns in our FE models, which the methods purely based on segmentations could not do. Moreover, the new pipeline improved the efficiency and accessibility of the initial pipeline by implementing machine learning-based automated segmentation onto a mainly open-sourced FE analysis platform. In conclusion, our algorithm enables the development of a high-content and high-throughput in vitro screening platform to elucidate anti-migratory molecules that may reduce the invasiveness of these malignant tumors.

A Narrative Review of Personalized Musculoskeletal Modeling Using the Physiome and Musculoskeletal Atlas Projects.

In this narrative review, we explore developments in the field of computational musculoskeletal model personalization using the Physiome and Musculoskeletal Atlas Projects. Model geometry personalization; statistical shape modeling; and its impact on segmentation, classification, and model creation are explored. Examples include the trapeziometacarpal and tibiofemoral joints, Achilles tendon, gastrocnemius muscle, and pediatric lower limb bones. Finally, a more general approach to model personalization is discussed based on the idea of multiscale personalization called scaffolds.

A Novel In Vitro and In Silico System for Analyzing Complex Mechanobiological Behavior of Chondrocytes in Three-Dimensional Hydrogel Constructs.

Physiological loading is essential for the maintenance of articular cartilage through the regulation of tissue remodeling. To correctly understand the behavior of chondrocytes in their native environment, cell stimulating devices and bioreactors have been developed to examine the effect of mechanical stimuli on chondrocytes. This study describes the design and validation of a novel system for analyzing chondrocyte deformation patterns. This involves an in vitro mechanical device for a controlled application of multi-axial-loading regimes to chondrocyte-seeded agarose constructs and in silico models for analyzing chondrocyte deformation patterns. The computer-controlled device precisely applies compressive, tensile, and shear strains to hydrogel constructs using a customizable macro-based program. The synchronization of the displacements is shown to be accurate with a 1.2% error and is highly reproducible. The device design allows housing for up to eight novel designed free-swelling three-dimensional hydrogel constructs. Constructs include mesh ends and are optimized to withstand the application of up to 7% mechanical tensile and 15% shear strains. Constructs were characterized through mapping the strain within as mechanical load was applied and was validated using light microscopy methods, chondrocyte viability using live/dead imaging, and cell deformation strains. Images were then analyzed to determine the complex deformation strain patterns of chondrocytes under a range of dynamic mechanical stimulations. This is one of the first systems that have characterized construct strains to cellular strains. The features in this device make the system ideally suited for a systematic approach for the investigation of the response of chondrocytes to a complex physiologically relevant deformation profile.

The role of diffusion tensor imaging in characterizing injury patterns on athletes with concussion and subconcussive injury: a systematic review.

Traumatic brain injury (TBI) is a major public health problem. The majority of TBIs are in the form of mild TBI (also known as concussion) with sports-related concussion (SRC) receiving public attention in recent years.Here we have performed a systematic review of the literature on the use of Diffusion Tensor Imaging (DTI) on sports-related concussion and subconcussive injuries. Our review found different patterns of change in DTI parameters between concussed and subconcussed groups. The Fractional Anisotropy (FA) was either unchanged or increased for the concussion group, while the subconcussed group generally experienced a decrease in FA. A reverse pattern was observed for Mean Diffusivity (MD) - where the concussed group experienced a decrease in MD while the subconcussed group showed an increase in MD. However, in general, discrepancies were observed in the results reported in the literature - likely due to the huge variations in DTI acquisition parameters, and image processing and analysis methods used in these studies. This calls for more comprehensive and well-controlled studies in this field, including those that combine the advanced brain imaging with biomechancial modeling and kinematic sensors - to shed light on the underlying mechanisms behind the structural changes observed from the imaging studies.

Applying Physiologically Relevant Strains to Tenocytes in an In Vitro Cell Device Induces In Vivo Like Behaviors.

We have developed a novel cell stretching device (called Cell Gym) capable of applying physiologically relevant low magnitude strains to tenocytes on a collagen type I coated membrane. We validated our device thoroughly on two levels: (1) substrate strains, (2) cell level strains. Our cell level strain results showed that the applied stretches were transferred to cells accurately (∼90%). Our gene expression data showed that mechanically stimulated tenocytes (4%) expressed a lower level of COL I gene. COX2 gene was increased but did not reach statistical significance. Our device was then tested to see if it could reproduce results from an in vivo study that measured time-dependent changes in collagen synthesis. Our results showed that collagen synthesis peaked at 24 hrs after exercise and then decreased, which matched the results from the in vivo study. Our study demonstrated that it is important to incorporate physiologically relevant low strain magnitudes in in vitro cell mechanical studies and the need to validate the device thoroughly to operate the device at small strains. This device will be used in designing novel tendon tissue engineering scaffolds in the future.

Altered load transfer in the pelvis in the presence of periprosthetic osteolysis.

Periprosthetic osteolysis in the retroacetabular region with cancellous bone loss is a recognized phenomenon in the long-term follow-up of total hip replacement. The effects on load transfer in the presence of defects are less well known. A validated, patient-specific, 3D finite element (FE) model of the pelvis was used to assess changes in load transfer associated with periprosthetic osteolysis adjacent to a cementless total hip arthroplasty (THA) component. The presence of a cancellous defect significantly increased (p < 0.05) von Mises stress in the cortical bone of the pelvis during walking and a fall onto the side. At loads consistent with single leg stance, this was still less than the predicted yield stress for cortical bone. During higher loads associated with a fall onto the side, highest stress concentrations occurred in the superior and inferior pubic rami and in the anterior column of the acetabulum with larger cancellous defects.

A hybrid statistical morphometry free-form deformation approach to 3D personalized foot-ankle models.

Foot and ankle joint models are widely used in the biomechanics community for musculoskeletal and finite element analysis. However, personalizing a foot and ankle joint model is highly time-consuming in terms of medical image collection and data processing. This study aims to develop and evaluate a framework for constructing a comprehensive 3D foot model that integrates statistical shape modeling (SSM) with free-form deformation (FFD) of internal bones. The SSM component is derived from external foot surface scans (skin measurements) of 50 participants, utilizing principal component analysis (PCA) to capture the variance in foot shapes. The derived surface shapes from SSM then guide the FFD process to accurately reconstruct the internal bone structures. The workflow accuracy was established by comparing three model-generated foot models against corresponding skin and bone geometries manually segmented and not part of the original training set. We used the top ten principal components representing 85 % of the population variation to create the model. For prediction validation, the average Dice similarity coefficient, Hausdorff distance error, and root mean square error were 0.92 ± 0.01, 2.2 ± 0.19 mm, and 2.95 ± 0.23 mm for soft tissues, and 0.84 ± 0.03, 1.83 ± 0.1 mm, and 2.36 ± 0.12 mm for bones, respectively. This study presents an efficient approach for 3D personalized foot model reconstruction via SSM generation of the foot surface that informs bone reconstruction based on FFD. The proposed workflow is part of the open-source Musculoskeletal Atlas Project linked to OpenSim and makes it feasible to accurately generate foot models informed by population anatomy, and suitable for rigid body analysis and finite element simulation.

Rethinking running biomechanics: a critical review of ground reaction forces, tibial bone loading, and the role of wearable sensors.

This study presents a comprehensive review of the correlation between tibial acceleration (TA), ground reaction forces (GRF), and tibial bone loading, emphasizing the critical role of wearable sensor technology in accurately measuring these biomechanical forces in the context of running. This systematic review and meta-analysis searched various electronic databases (PubMed, SPORTDiscus, Scopus, IEEE Xplore, and ScienceDirect) to identify relevant studies. It critically evaluates existing research on GRF and tibial acceleration (TA) as indicators of running-related injuries, revealing mixed findings. Intriguingly, recent empirical data indicate only a marginal link between GRF, TA, and tibial bone stress, thus challenging the conventional understanding in this field. The study also highlights the limitations of current biomechanical models and methodologies, proposing a paradigm shift towards more holistic and integrated approaches. The study underscores wearable sensors' potential, enhanced by machine learning, in transforming the monitoring, prevention, and rehabilitation of running-related injuries.

Mapping stroke outcomes: A review of brain connectivity atlases.

The brain connectivity-based atlas is a promising tool for understanding neural communication pathways in the brain, gaining relevance in predicting personalized outcomes for various brain pathologies. This critical review examines the robustness of the brain connectivity-based atlas for predicting post-stroke outcomes. A comprehensive literature search was conducted from 2012 to May 2023 across PubMed, Scopus, EMBASE, EBSCOhost, and Medline databases. Twenty-one studies were screened, and through analysis of these studies, we identified 18 brain connectivity atlases employed by the studies for lesion analysis in their predictions. The brain atlases were assessed for study cohorts, connectivity measures, identified brain regions, atlas applications, and limitations. Based on the analysis of these studies, most atlases were based on diffusion tensor imaging and resting-state functional magnetic resonance imaging (MRI). Studies predicting post-stroke functional outcomes relied on the atlases for multivariate lesion analysis and region of interest identification, often employing atlases derived from young, healthy populations. Current brain connectivity-based atlases for stroke applications lack standardized methods to define and map brain connectivity across atlases and cover sensorimotor functional connectivity to a limited extent. In conclusion, this review highlights the need to develop more comprehensive, robust, and adaptable brain connectivity-based atlases specifically tailored to post-stroke populations.

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review.

Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the development of more robust and effective stroke lesion segmentation models.

Histological Characterisation of a Sheep Model of Mild Traumatic Brain Injury: A Pilot Study.

Large animal models of mild traumatic brain injury (mTBI) are needed to elucidate the pathophysiology of mechanical insult to a gyrencephalic brain. Sheep (ovis aries) are an attractive model for mTBI because of their neuroanatomical similarity to humans; however, few histological studies of sheep mTBI models have been conducted. We previously developed a sheep mTBI model to pilot methods for investigating the mechanical properties of brain tissue after injury. Here, we sought to histologically characterize the cortex under the impact site in this model. Three animals received a closed skull mTBI with unconstrained head motion, delivered with an impact stunner, and 3 sham animals were anesthetized but did not receive an impact. Magnetic resonance imaging (MRI) of the brain was performed before and after the impact and revealed variable degrees of damage to the skull and brain. Fluorescent immunohistochemistry revealed regions of hemorrhage in the cortex underlying the impact site in 2 of 3 mTBI sheep, the amount of which correlated with the degree of damage observed on the post-impact MRI scans. Labeling for microtubule-associated protein 2 and neuronal nuclear protein revealed changes in cellular anatomy, but, unexpectedly, glial fibrillary acidic protein and ionized calcium-binding adaptor molecule 1 labeling were relatively unchanged compared to sham animals. Our findings provide preliminary evidence of vascular and neuronal damage with limited glial reactivity and highlight the need for further in-depth histological assessment of large animal mTBI models.

Integrating an LSTM framework for predicting ankle joint biomechanics during gait using inertial sensors.

The ankle joint plays a crucial role in gait, facilitating the articulation of the lower limb, maintaining foot-ground contact, balancing the body, and transmitting the center of gravity. This study aimed to implement long short-term memory (LSTM) networks for predicting ankle joint angles, torques, and contact forces using inertial measurement unit (IMU) sensors. Twenty-five healthy participants were recruited. Two IMU sensors were attached to the foot dorsum and the vertical axis of the distal anteromedial tibia in the right lower limb to record acceleration and angular velocity during running. We proposed a LSTM-MLP (multilayer perceptron) model for training time-series data from IMU sensors and predicting ankle joint biomechanics. The model underwent validation and testing using a custom nested k-fold cross-validation process. The average values of the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE) for ankle dorsiflexion joint and moment, subtalar inversion joint and moment, and ankle joint contact forces were 0.89 ± 0.04, 0.75 ± 1.04, and 2.96 ± 4.96 for walking, and 0.87 ± 0.07, 0.88 ± 1.26, and 4.1 ± 7.17 for running, respectively. This study demonstrates that IMU sensors, combined with LSTM neural networks, are invaluable tools for evaluating ankle joint biomechanics in lower limb pathological diagnosis and rehabilitation, offering a cost-effective and versatile alternative to traditional experimental settings.

Integration of diffusion tensor imaging parameters with mesh morphing for in-depth analysis of brain white matter fibre tracts.

Averaging is commonly used for data reduction/aggregation to analyse high-dimensional MRI data, but this often leads to information loss. To address this issue, we developed a novel technique that integrates diffusion tensor metrics along the whole volume of the fibre bundle using a 3D mesh-morphing technique coupled with principal component analysis for delineating case and control groups. Brain diffusion tensor MRI scans of high school rugby union players (n = 30, age 16-18) were acquired on a 3 T MRI before and after the sports season. A non-contact sport athlete cohort with matching demographics (n = 12) was also scanned. The utility of the new method in detecting differences in diffusion tensor metrics of the right corticospinal tract between contact and non-contact sport athletes was explored. The first step was to run automated tractography on each subject's native space. A template model of the right corticospinal tract was generated and morphed into each subject's native shape and space, matching individual geometry and diffusion metric distributions with minimal information loss. The common dimension of the 20 480 diffusion metrics allowed further data aggregation using principal component analysis to cluster the case and control groups as well as visualization of diffusion metric statistics (mean, ±2 SD). Our approach of analysing the whole volume of white matter tracts led to a clear delineation between the rugby and control cohort, which was not possible with the traditional averaging method. Moreover, our approach accounts for the individual subject's variations in diffusion tensor metrics to visualize group differences in quantitative MR data. This approach may benefit future prediction models based on other quantitative MRI methods.

Machine Learning for Medical Image Translation: A Systematic Review.

BACKGROUND: CT scans are often the first and only form of brain imaging that is performed to inform treatment plans for neurological patients due to its time- and cost-effective nature. However, MR images give a more detailed picture of tissue structure and characteristics and are more likely to pick up abnormalities and lesions. The purpose of this paper is to review studies which use deep learning methods to generate synthetic medical images of modalities such as MRI and CT. METHODS: A literature search was performed in March 2023, and relevant articles were selected and analyzed. The year of publication, dataset size, input modality, synthesized modality, deep learning architecture, motivations, and evaluation methods were analyzed. RESULTS: A total of 103 studies were included in this review, all of which were published since 2017. Of these, 74% of studies investigated MRI to CT synthesis, and the remaining studies investigated CT to MRI, Cross MRI, PET to CT, and MRI to PET. Additionally, 58% of studies were motivated by synthesizing CT scans from MRI to perform MRI-only radiation therapy. Other motivations included synthesizing scans to aid diagnosis and completing datasets by synthesizing missing scans. CONCLUSIONS: Considerably more research has been carried out on MRI to CT synthesis, despite CT to MRI synthesis yielding specific benefits. A limitation on medical image synthesis is that medical datasets, especially paired datasets of different modalities, are lacking in size and availability; it is therefore recommended that a global consortium be developed to obtain and make available more datasets for use. Finally, it is recommended that work be carried out to establish all uses of the synthesis of medical scans in clinical practice and discover which evaluation methods are suitable for assessing the synthesized images for these needs.

Understanding the form and function in Chinese bound foot from last-generation cases.

Purpose: Foot adaptation in the typically developed foot is well explored. In this study, we aimed to explore the form and function of an atypical foot, the Chinese bound foot, which had a history of over a thousand years but is not practised anymore. Methods: We evaluated the foot shape and posture via a statistical shape modelling analysis, gait plantar loading distribution via gait analysis, and bone density adaptation via implementing finite element simulation and bone remodelling prediction. Results: The atypical foot with binding practice led to increased foot arch and vertically oriented calcaneus with larger size at the articulation, apart from smaller metatarsals compared with a typically developed foot. This shape change causes the tibia, which typically acts as a load transfer beam and shock absorber, to extend its function all the way through the talus to the calcaneus. This is evident in the bound foot by i) the reduced center of pressure trajectory in the medial-lateral direction, suggesting a reduced supination-pronation; ii) the increased density and stress in the talus-calcaneus articulation; and iii) the increased bone growth in the bound foot at articulation joints in the tibia, talus, and calcaneus. Conclusion: Knowledge from the last-generation bound foot cases may provide insights into the understanding of bone resorption and adaptation in response to different loading profiles.

Foot Pronation Prediction with Inertial Sensors during Running: A Preliminary Application of Data-Driven Approaches.

Abnormal foot postures may affect foot movement and joint loading during locomotion. Investigating foot posture alternation during running could contribute to injury prevention and foot mechanism study. This study aimed to develop feature-based and deep learning algorithms to predict foot pronation during prolonged running. Thirty-two recreational runners have been recruited for this study. Nine-axial inertial sensors were attached to the right dorsum of the foot and the vertical axis of the distal anteromedial tibia. This study employed feature-based machine learning algorithms, including support vector machine (SVM), extreme gradient boosting (XGBoost), random forest, and deep learning, i.e., one-dimensional convolutional neural networks (CNN1D), to predict foot pronation. A custom nested k-fold cross-validation was designed for hyper-parameter tuning and validating the model's performance. The XGBoot classifier achieved the best accuracy using acceleration and angular velocity data from the foot dorsum as input. Accuracy and the area under curve (AUC) were 74.7 ± 5.2% and 0.82 ± 0.07 for the subject-independent model and 98 ± 0.4% and 0.99 ± 0 for the record-wise method. The test accuracy of the CNN1D model with sensor data at the foot dorsum was 74 ± 3.8% for the subject-wise approach with an AUC of 0.8 ± 0.05. This study found that these algorithms, specifically for the CNN1D and XGBoost model with inertial sensor data collected from the foot dorsum, could be implemented into wearable devices, such as a smartwatch, for monitoring a runner's foot pronation during long-distance running. It has the potential for running shoe matching and reducing or preventing foot posture-induced injuries.

Machine Learning for Brain MRI Data Harmonisation: A Systematic Review.

BACKGROUND: Magnetic Resonance Imaging (MRI) data collected from multiple centres can be heterogeneous due to factors such as the scanner used and the site location. To reduce this heterogeneity, the data needs to be harmonised. In recent years, machine learning (ML) has been used to solve different types of problems related to MRI data, showing great promise. OBJECTIVE: This study explores how well various ML algorithms perform in harmonising MRI data, both implicitly and explicitly, by summarising the findings in relevant peer-reviewed articles. Furthermore, it provides guidelines for the use of current methods and identifies potential future research directions. METHOD: This review covers articles published through PubMed, Web of Science, and IEEE databases through June 2022. Data from studies were analysed based on the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Quality assessment questions were derived to assess the quality of the included publications. RESULTS: a total of 41 articles published between 2015 and 2022 were identified and analysed. In the review, MRI data has been found to be harmonised either in an implicit (n = 21) or an explicit (n = 20) way. Three MRI modalities were identified: structural MRI (n = 28), diffusion MRI (n = 7) and functional MRI (n = 6). CONCLUSION: Various ML techniques have been employed to harmonise different types of MRI data. There is currently a lack of consistent evaluation methods and metrics used across studies, and it is recommended that the issue be addressed in future studies. Harmonisation of MRI data using ML shows promises in improving performance for ML downstream tasks, while caution should be exercised when using ML-harmonised data for direct interpretation.

Roadmap for an imaging and modelling paediatric study in rural NZ.

Our study methodology is motivated from three disparate needs: one, imaging studies have existed in silo and study organs but not across organ systems; two, there are gaps in our understanding of paediatric structure and function; three, lack of representative data in New Zealand. Our research aims to address these issues in part, through the combination of magnetic resonance imaging, advanced image processing algorithms and computational modelling. Our study demonstrated the need to take an organ-system approach and scan multiple organs on the same child. We have pilot tested an imaging protocol to be minimally disruptive to the children and demonstrated state-of-the-art image processing and personalized computational models using the imaging data. Our imaging protocol spans brain, lungs, heart, muscle, bones, abdominal and vascular systems. Our initial set of results demonstrated child-specific measurements on one dataset. This work is novel and interesting as we have run multiple computational physiology workflows to generate personalized computational models. Our proposed work is the first step towards achieving the integration of imaging and modelling improving our understanding of the human body in paediatric health and disease.

Quantitative CT with finite element analysis: towards a predictive tool for bone remodelling around an uncemented tapered stem.

PURPOSE: We used quantitative CT in conjunction with finite element analysis to provide a new tool for assessment of bone quality after total hip arthroplasty in vivo. The hypothesis of this prospective five-year study is that the combination of the two modalities allows 3D patient-specific imaging of cortical and cancellous bone changes and stress shielding. METHOD: We tested quantitative CT in conjunction with finite elements on a cohort of 29 patients (31 hips) who have been scanned postoperatively and at one year, two years and five years follow-up. The method uses cubic Hermite finite element interpolation for efficient mesh generation directly from qCT datasets. The element Gauss points that are used for the geometric interpolation functions are also used for interpolation of osteodensitometry data. RESULTS: The study showed changes of bone density suggestive of proximal femur diaphysis load transfer with osteointegration and moderate metaphyseal stress shielding. Our model revealed that cortical bone initially became porous in the greater trochanter, but this phenomenon progressed to the cortex of the lesser trochanter and the posterior aspect of the metaphysis. The diaphyseal area did not experience major change in bone density for either cortical or cancellous bone. CONCLUSION: The combination of quantitative CT with finite element analysis allows visualization of changes to bone density and architecture. It also provides correlation of bone density/architectural changes with stress patterns enabling the study of the effects of stress shielding on bone remodelling in vivo. This technology can be useful in predicting bone remodeling and the quality of implant fixation using prostheses with different design and/or biomaterials.