Stealthy Measurement-Aided Pole-Dynamics Attacks With Nominal Models.

When traditional pole-dynamics attacks (TPDAs) are implemented with nominal models, model mismatch between exact and nominal models often affects their stealthiness, or even makes the stealthiness lost. To solve this problem, this article presents a novel stealthy measurement-aided pole-dynamics attacks (MAPDAs) method with model mismatch. First, the limitations of TPDAs using exact models are revealed. Second, to handle the limitations, the proposed MAPDAs method is designed by using an adaptive control strategy, which can keep the stealthiness. Moreover, it is easier to implement as only the measurements are needed in comparison with the existing methods requiring both measurements and control inputs. Third, the performance of the proposed MAPDAs method is explored using convergence of multivariate measurements, and MAPDAs with model mismatch have the same stealthiness and similar destructiveness as TPDAs. Finally, experimental results from a networked inverted pendulum system confirm the feasibility and effectiveness of the proposed method.

Prognostic value of the geriatric nutritional risk index in patients with non-metastatic clear cell renal cell carcinoma: a propensity score matching analysis.

BACKGROUND: This study aimed to investigate the prognostic value of the geriatric nutritional risk index (GNRI) in patients with non-metastatic clear cell renal cell carcinoma (ccRCC) who underwent nephrectomy. METHODS: Patients with non-metastatic ccRCC who underwent nephrectomy between 2013 and 2021 were analyzed retrospectively. The GNRI was calculated within one week before surgery. The optimal cut-off value of GNRI was determined using X-tile software, and the patients were divided into a low GNRI group and a high GNRI group. The Kaplan-Meier method was used to compare the overall survival (OS), cancer-specific survival (CSS) and recurrence-free survival (RFS) between the two groups. Univariate and multivariate Cox proportional hazard models were used to determine prognostic factors. In addition, propensity score matching (PSM) was performed with a matching ratio of 1:3 to minimize the influence of confounding factors. Variables entered into the PSM model were as follows: sex, age, history of hypertension, history of diabetes, smoking history, BMI, tumor sidedness, pT stage, Fuhrman grade, surgical method, surgical approach, and tumor size. RESULTS: A total of 645 patients were included in the final analysis, with a median follow-up period of 37 months (range: 1-112 months). The optimal cut-off value of GNRI was 98, based on which patients were divided into two groups: a low GNRI group (≤ 98) and a high GNRI group (> 98). Kaplan-Meier analysis showed that OS (P < 0.001), CSS (P < 0.001) and RFS (P < 0.001) in the low GNRI group were significantly worse than those in the high GNRI group. Univariate and multivariate Cox analysis showed that GNRI was an independent prognostic factor of OS, CSS and RFS. Even after PSM, OS (P < 0.05), CSS (P < 0.05) and RFS (P < 0.05) in the low GNRI group were still worse than those in the high GNRI group. In addition, we observed that a low GNRI was associated with poor clinical outcomes in elderly subgroup (> 65) and young subgroup (≤ 65), as well as in patients with early (pT1-T2) and low-grade (Fuhrman I-II) ccRCC. CONCLUSION: As a simple and practical tool for nutrition screening, the preoperative GNRI can be used as an independent prognostic indicator for postoperative patients with non-metastatic ccRCC. However, larger prospective studies are necessary to validate these findings.

Analysis of stress response distribution in patients with lateral ankle ligament injuries: a study of neural control strategies utilizing predictive computing models.

Background: Ankle sprains are prevalent in sports, often causing complex injuries to the lateral ligaments. Among these, anterior talofibular ligament (ATFL) injuries constitute 85%, and calcaneofibular ligament (CFL) injuries comprise 35%. Despite conservative treatment, some ankle sprain patients develop chronic lateral ankle instability (CLAI). Thus, this study aimed to investigate stress response and neural control alterations during landing in lateral ankle ligament injury patients. Method: This study recruited twenty individuals from a Healthy group and twenty CLAI patients performed a landing task using relevant instruments to collect biomechanical data. The study constructed a finite element (FE) foot model to examine stress responses in the presence of laxity of the lateral ankle ligaments. The lateral ankle ligament was modeled as a hyperelastic composite structure with a refined representation of collagen bundles and ligament laxity was simulated by adjusting material parameters. Finally, the validity of the finite element model is verified by a high-speed dual fluoroscopic imaging system (DFIS). Result: CLAI patients exhibited earlier Vastus medialis (p < 0.001) and tibialis anterior (p < 0.001) muscle activation during landing. The FE analysis revealed that with laxity in the ATFL, the peak von Mises stress in the fifth metatarsal was 20.74 MPa, while with laxity in the CFL, it was 17.52 MPa. However, when both ligaments were relaxed simultaneously, the peak von Mises stress surged to 21.93 MPa. When the ATFL exhibits laxity, the CFL is subjected to a higher stress of 3.84 MPa. Conversely, when the CFL displays laxity, the ATFL experiences a peak von Mises stress of 2.34 MPa. Conclusion: This study found that changes in the laxity of the ATFL and the CFL are linked to shifts in metatarsal stress levels, potentially affecting ankle joint stability. These alterations may contribute to the progression towards CLAI in individuals with posterolateral ankle ligament injuries. Additionally, significant muscle activation pattern changes were observed in CLAI patients, suggesting altered neural control strategies post-ankle ligament injury.

A gut microbiota rheostat forecasts responsiveness to PD-L1 and VEGF blockade in mesothelioma.

Malignant mesothelioma is a rare tumour caused by asbestos exposure that originates mainly from the pleural lining or the peritoneum. Treatment options are limited, and the prognosis is dismal. Although immune checkpoint blockade (ICB) can improve survival outcomes, the determinants of responsiveness remain elusive. Here, we report the outcomes of a multi-centre phase II clinical trial (MiST4, NCT03654833) evaluating atezolizumab and bevacizumab (AtzBev) in patients with relapsed mesothelioma. We also use tumour tissue and gut microbiome sequencing, as well as tumour spatial immunophenotyping to identify factors associated with treatment response. MIST4 met its primary endpoint with 50% 12-week disease control, and the treatment was tolerable. Aneuploidy, notably uniparental disomy (UPD), homologous recombination deficiency (HRD), epithelial-mesenchymal transition and inflammation with CD68+ monocytes were identified as tumour-intrinsic resistance factors. The log-ratio of gut-resident microbial genera positively correlated with radiological response to AtzBev and CD8+ T cell infiltration, but was inversely correlated with UPD, HRD and tumour infiltration by CD68+ monocytes. In summary, a model is proposed in which both intrinsic and extrinsic determinants in mesothelioma cooperate to modify the tumour microenvironment and confer clinical sensitivity to AtzBev. Gut microbiota represent a potentially modifiable factor with potential to improve immunotherapy outcomes for individuals with this cancer of unmet need.

Contribution of ankle motion pattern during landing to reduce the knee-related injury risk.

BACKGROUND: Single-leg landing (SL) is an essential technique in sports such as basketball, soccer, and volleyball, which is often associated with a high risk of knee-related injury. The ankle motion pattern plays a crucial role in absorbing the load shocks during SL, but the effect on the knee joint is not yet clear. This work aims to explore the effects of different ankle plantarflexion angles during SL on the risk of knee-related injury. METHODS: Thirty healthy male subjects were recruited to perform SL biomechanics tests, and one standard subject was selected to develop the finite element model of foot-ankle-knee integration. The joint impact force was used to evaluate the impact loads on the knee at various landing angles. The internal load forces (musculoskeletal modeling) and stress (finite element analysis) around the knee joint were simulated and calculated to evaluate the risk of knee-related injury during SL. To more realistically revert and simulate the anterior cruciate ligament (ACL) injury mechanics, we developed a knee musculoskeletal model that reverts the ACL ligament to a nonlinear short-term viscoelastic mechanical mechanism (strain rate-dependent) generated by the dense connective tissue as a function of strain. RESULTS: As the ankle plantarflexion angle increased during landing, both the peak knee vertical impact force (p = 0.001) and ACL force (p = 0.001) decreased significantly. The maximum von Mises stress of ACL, meniscus, and femoral cartilage decreased as the ankle plantarflexion angle increased. The overall range of variation in ACL stress was small and was mainly distributed in the femoral and tibial attachment regions, as well as in the mid-lateral region. CONCLUSION: The current findings revealed that the use of larger ankle plantarflexion angles during landing may be an effective solution to reduce knee impact load and the risk of rupture of the medial femoral attachment area in the ACL. The findings of this study have the potential to offer novel perspectives in the optimized application of landing strategies, thus giving crucial theoretical backing for decreasing the risk of knee-related injury.

A Novel Multi-modal Population-graph based Framework for Patients of Esophageal Squamous Cell Cancer Prognostic Risk Prediction.

Prognostic risk prediction is pivotal for clinicians to appraise the patient's esophageal squamous cell cancer (ESCC) progression status precisely and tailor individualized therapy treatment plans. Currently, CT-based multi-modal prognostic risk prediction methods have gradually attracted the attention of researchers for their universality, which is also able to be applied in scenarios of preoperative prognostic risk assessment in the early stages of cancer. However, much of the current work focuses only on CT images of the primary tumor, ignoring the important role that CT images of lymph nodes play in prognostic risk prediction. Additionally, it is important to consider and explore the inter-patient feature similarity in prognosis when developing models. To solve these problems, we proposed a novel multi-modal population-graph based framework leveraging CT images including primary tumor and lymph nodes combined with clinical, hematology, and radiomics data for ESCC prognostic risk prediction. A patient population graph was constructed to excavate the homogeneity and heterogeneity of inter-patient feature embedding. Moreover, a novel node-level multi-task joint loss was proposed for graph model optimization through a supervised-based task and an unsupervised-based task. Sufficient experimental results show that our model achieved state-of-the-art performance compared with other baseline models as well as the gold standard on discriminative ability, risk stratification, and clinical utility. The core code is available at https://github.com/wuchengyu123/MPGSurv.

InA: Inhibition Adaption on pre-trained language models.

Fine-tuning pre-trained language models (LMs) may not always be the most practical approach for downstream tasks. While adaptation fine-tuning methods have shown promising results, a clearer explanation of their mechanisms and further inhibition of the transmission of information is needed. To address this, we propose an Inhibition Adaptation (InA) fine-tuning method that aims to reduce the number of added tunable weights and appropriately reweight knowledge derived from pre-trained LMs. The InA method involves (1) inserting a small trainable vector into each Transformer attention architecture and (2) setting a threshold to directly eliminate irrelevant knowledge. This approach draws inspiration from the shunting inhibition, which allows the inhibition of specific neurons to gate other functional neurons. With the inhibition mechanism, InA achieves competitive or even superior performance compared to other fine-tuning methods on BERT-large, RoBERTa-large, and DeBERTa-large for text classification and question-answering tasks.

Have we found a solution for health misinformation? A ten-year systematic review of health misinformation literature 2013-2022.

BACKGROUND: Health misinformation (HM) has emerged as a prominent social issue in recent years, driven by declining public trust, popularisation of digital media platforms and escalating public health crisis. Since the Covid-19 pandemic, HM has raised critical concerns due to its significant impacts on both individuals and society as a whole. A comprehensive understanding of HM and HM-related studies would be instrumental in identifying possible solutions to address HM and the associated challenges. METHODS: Following the PRISMA procedure, 11,739 papers published from January 2013 to December 2022 were retrieved from five electronic databases, and 813 papers matching the inclusion criteria were retained for further analysis. This article critically reviewed HM-related studies, detailing the factors facilitating HM creation and dissemination, negative impacts of HM, solutions to HM, and research methods employed in those studies. RESULTS: A growing number of studies have focused on HM since 2013. Results of this study highlight that trust plays a significant while latent role in the circuits of HM, facilitating the creation and dissemination of HM, exacerbating the negative impacts of HM and amplifying the difficulty in addressing HM. CONCLUSION: For health authorities and governmental institutions, it is essential to systematically build public trust in order to reduce the probability of individuals acceptation of HM and to improve the effectiveness of misinformation correction. Future studies should pay more attention to the role of trust in how to address HM.

Can the Entire Function of the Foot Be Concentrated in the Forefoot Area during the Running Stance Phase? A Finite Element Study of Different Shoe Soles.

The goal of this study was to use the finite element (FE) method to compare and study the differences between bionic shoes (BS) and normal shoes (NS) forefoot strike patterns when running. In addition, we separated the forefoot area when forefoot running as a way to create a small and independent area of instability. An adult male of Chinese descent was recruited for this investigation (age: 26 years old; body height: 185 cm; body mass: 82 kg) (forefoot strike patterns). We analyzed forefoot running under two different conditions through FE analysis, and used bone stress distribution feature classification and recognition for further analysis. The metatarsal stress values in forefoot strike patterns with BS were less than with NS. Additionally, the bone stress classification of features and the recognition accuracy rate of metatarsal (MT) 2, MT3 and MT5 were higher than other foot bones in the first 5%, 10%, 20% and 50% of nodes. BS forefoot running helped reduce the probability of occurrence of metatarsal stress fractures. In addition, the findings further revealed that BS may have important implications for the prevention of hallux valgus, which may be more effective in adolescent children. Finally, this study presents a post-processing method for FE results, which is of great significance for further understanding and exploration of FE results.

Structural and Organizational Strategies of Locomotor Modules during Landing in Patients with Chronic Ankle Instability.

BACKGROUND: Human locomotion involves the coordinated activation of a finite set of modules, known as muscle synergy, which represent the motor control strategy of the central nervous system. However, most prior studies have focused on isolated muscle activation, overlooking the modular organization of motor behavior. Therefore, to enhance comprehension of muscle coordination dynamics during multi-joint movements in chronic ankle instability (CAI), exploring muscle synergies during landing in CAI patients is imperative. METHODS: A total of 22 patients with unilateral CAI and 22 healthy participants were recruited for this research. We employed a recursive model for second-order differential equations to process electromyographic (EMG) data after filtering preprocessing, generating the muscle activation matrix, which was subsequently inputted into the non-negative matrix factorization model for extraction of the muscle synergy. Muscle synergies were classified utilizing the K-means clustering algorithm and Pearson correlation coefficients. Statistical parameter mapping (SPM) was employed for temporal modular parameter analyses. RESULTS: Four muscle synergies were identified in both the CAI and healthy groups. In Synergy 1, only the gluteus maximus showed significantly higher relative weight in CAI compared to healthy controls (p = 0.0035). Synergy 2 showed significantly higher relative weights for the vastus lateralis in the healthy group compared to CAI (p = 0.018), while in Synergy 4, CAI demonstrated significantly higher relative weights of the vastus lateralis compared to healthy controls (p = 0.030). Furthermore, in Synergy 2, the CAI group exhibited higher weights of the tibialis anterior compared to the healthy group (p = 0.042). CONCLUSIONS: The study suggested that patients with CAI exhibit a comparable modular organizational framework to the healthy group. Investigation of amplitude adjustments within the synergy spatial module shed light on the adaptive strategies employed by the tibialis anterior and gluteus maximus muscles to optimize control strategies during landing in patients with CAI. Variances in the muscle-specific weights of the vastus lateralis across movement modules reveal novel biomechanical adaptations in CAI, offering valuable insights for refining rehabilitation protocols.

New Insights Optimize Landing Strategies to Reduce Lower Limb Injury Risk.

Single-leg landing (SL) is often associated with a high injury risk, especially anterior cruciate ligament (ACL) injuries and lateral ankle sprain. This work investigates the relationship between ankle motion patterns (ankle initial contact angle [AICA] and ankle range of motion [AROM]) and the lower limb injury risk during SL, and proposes an optimized landing strategy that can reduce the injury risk. To more realistically revert and simulate the ACL injury mechanics, we developed a knee musculoskeletal model that reverts the ACL ligament to a nonlinear short-term viscoelastic mechanical mechanism (strain rate-dependent) generated by the dense connective tissue as a function of strain. Sixty healthy male subjects were recruited to collect biomechanics data during SL. The correlation analysis was conducted to explore the relationship between AICA, AROM, and peak vertical ground reaction force (PVGRF), joint total energy dissipation (TED), peak ankle knee hip sagittal moment, peak ankle inversion angle (PAIA), and peak ACL force (PAF). AICA exhibits a negative correlation with PVGRF (r = -0.591) and PAF (r = -0.554), and a positive correlation with TED (r = 0.490) and PAIA (r = 0.502). AROM exhibits a positive correlation with TED (r = 0.687) and PAIA (r = 0.600). The results suggested that the appropriate increases in AICA (30° to 40°) and AROM (50° to 70°) may reduce the lower limb injury risk. This study has the potential to offer novel perspectives on the optimized application of landing strategies, thus giving the crucial theoretical basis for decreasing injury risk.

Negative Deterministic Information-Based Multiple Instance Learning for Weakly Supervised Object Detection and Segmentation.

Weakly supervised object detection (WSOD) and semantic segmentation with image-level annotations have attracted extensive attention due to their high label efficiency. Multiple instance learning (MIL) offers a feasible solution for the two tasks by treating each image as a bag with a series of instances (object regions or pixels) and identifying foreground instances that contribute to bag classification. However, conventional MIL paradigms often suffer from issues, e.g., discriminative instance domination and missing instances. In this article, we observe that negative instances usually contain valuable deterministic information, which is the key to solving the two issues. Motivated by this, we propose a novel MIL paradigm based on negative deterministic information (NDI), termed NDI-MIL, which is based on two core designs with a progressive relation: NDI collection and negative contrastive learning (NCL). In NDI collection, we identify and distill NDI from negative instances online by a dynamic feature bank. The collected NDI is then utilized in a NCL mechanism to locate and punish those discriminative regions, by which the discriminative instance domination and missing instances issues are effectively addressed, leading to improved object-and pixel-level localization accuracy and completeness. In addition, we design an NDI-guided instance selection (NGIS) strategy to further enhance the systematic performance. Experimental results on several public benchmarks, including PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO, show that our method achieves satisfactory performance. The code is available at: https://github.com/GC-WSL/NDI.

Deep Learning Methods for Calibrated Photometric Stereo and Beyond.

Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues, i.e., modeling the relationship between surface orientation and intensity at each pixel. Photometric stereo prevails in superior per-pixel resolution and fine reconstruction details. However, it is a complicated problem because of the non-linear relationship caused by non-Lambertian surface reflectance. Recently, various deep learning methods have shown a powerful ability in the context of photometric stereo against non-Lambertian surfaces. This paper provides a comprehensive review of existing deep learning-based calibrated photometric stereo methods utilizing orthographic cameras and directional light sources. We first analyze these methods from different perspectives, including input processing, supervision, and network architecture. We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set. This demonstrates the advanced performance of deep learning-based photometric stereo methods. Finally, we give suggestions and propose future research trends based on the limitations of existing models.

Transformaer-based model for lung adenocarcinoma subtypes.

BACKGROUND: Lung cancer has the highest morbidity and mortality rate among all types of cancer. Histological subtypes serve as crucial markers for the development of lung cancer and possess significant clinical values for cancer diagnosis, prognosis, and prediction of treatment responses. However, existing studies only dichotomize normal and cancerous tissues, failing to capture the unique characteristics of tissue sections and cancer types. PURPOSE: Therefore, we have pioneered the classification of lung adenocarcinoma (LAD) cancer tissues into five subtypes (acinar, lepidic, micropapillary, papillary, and solid) based on section data in whole-slide image sections. In addition, a novel model called HybridNet was designed to improve the classification performance. METHODS: HybridNet primarily consists of two interactive streams: a Transformer and a convolutional neural network (CNN). The Transformer stream captures rich global representations using a self-attention mechanism, while the CNN stream extracts local semantic features to optimize image details. Specifically, during the dual-stream parallelism, the feature maps of the Transformer stream as weights are weighted and summed with those of the CNN stream backbone; at the end of the parallelism, the respective final features are concatenated to obtain more discriminative semantic information. RESULTS: Experimental results on a private dataset of LAD showed that HybridNet achieved 95.12% classification accuracy, and the accuracy of five histological subtypes (acinar, lepidic, micropapillary, papillary, and solid) reached 94.5%, 97.1%, 94%, 91%, and 99% respectively; the experimental results on the public BreakHis dataset show that HybridNet achieves the best results in three evaluation metrics: accuracy, recall and F1-score, with 92.40%, 90.63%, and 91.43%, respectively. CONCLUSIONS: The process of classifying LAD into five subtypes assists pathologists in selecting appropriate treatments and enables them to predict tumor mutation burden (TMB) and analyze the spatial distribution of immune checkpoint proteins based on this and other clinical data. In addition, the proposed HybridNet fuses CNN and Transformer information several times and is able to improve the accuracy of subtype classification, and also shows satisfactory performance on public datasets with some generalization ability.

Dark-field imaging and fluorescence dual-mode detection of microRNA-21 in living cells by core-satellite plasmonic nanoprobes.

The in situ precise quantification and simultaneous imaging of low abundance microRNAs (miRNAs) within living cells is critical for cancer diagnosis, yet it remains a significant challenge. Leveraging the excellent sensitivity and spatiotemporal resolution of dark-field microscopy (DFM) and fluorescence imaging, we have successfully devised a novel detection approach using dual-signal reporter probes (DSRPs). These probes allow for highly sensitive detection of miRNA-21 in living cells via toehold-mediated strand displacement cascades. The DSRPs were constructed by Au nanoparticles and Ag nanoclusters core-satellite nanostructures. After the recognition of miRNA-21, the strand displacement cascades were triggered, inducing the disassembly of the Au/Ag core-satellite nanostructure with apparent scattering intensity decrease and peak wavelength shifts. Additionally, the fluorescence of Ag clusters could be recovered and further enhanced when in close proximity to specific guanine-rich strands. The dual-signal response capability enables the accurate detection of miRNA-21 from 1 fM to 1 nM, with a limit of detection reached 0.75 fM. DFM and fluorescent imaging of living cells efficiently confirms the applicable detection of miRNA-21 in complex detection media. The biosensor based on DSRPs represents a promising nanoplatform for visual monitoring and imaging of biomolecules in living cells, even at the single particle level.

CLANet: A comprehensive framework for cross-batch cell line identification using brightfield images.

Cell line authentication plays a crucial role in the biomedical field, ensuring researchers work with accurately identified cells. Supervised deep learning has made remarkable strides in cell line identification by studying cell morphological features through cell imaging. However, biological batch (bio-batch) effects, a significant issue stemming from the different times at which data is generated, lead to substantial shifts in the underlying data distribution, thus complicating reliable differentiation between cell lines from distinct batch cultures. To address this challenge, we introduce CLANet, a pioneering framework for cross-batch cell line identification using brightfield images, specifically designed to tackle three distinct bio-batch effects. We propose a cell cluster-level selection method to efficiently capture cell density variations, and a self-supervised learning strategy to manage image quality variations, thus producing reliable patch representations. Additionally, we adopt multiple instance learning(MIL) for effective aggregation of instance-level features for cell line identification. Our innovative time-series segment sampling module further enhances MIL's feature-learning capabilities, mitigating biases from varying incubation times across batches. We validate CLANet using data from 32 cell lines across 93 experimental bio-batches from the AstraZeneca Global Cell Bank. Our results show that CLANet outperforms related approaches (e.g. domain adaptation, MIL), demonstrating its effectiveness in addressing bio-batch effects in cell line identification.

Long-short diffeomorphism memory network for weakly-supervised ultrasound landmark tracking.

Ultrasound is a promising medical imaging modality benefiting from low-cost and real-time acquisition. Accurate tracking of an anatomical landmark has been of high interest for various clinical workflows such as minimally invasive surgery and ultrasound-guided radiation therapy. However, tracking an anatomical landmark accurately in ultrasound video is very challenging, due to landmark deformation, visual ambiguity and partial observation. In this paper, we propose a long-short diffeomorphism memory network (LSDM), which is a multi-task framework with an auxiliary learnable deformation prior to supporting accurate landmark tracking. Specifically, we design a novel diffeomorphic representation, which contains both long and short temporal information stored in separate memory banks for delineating motion margins and reducing cumulative errors. We further propose an expectation maximization memory alignment (EMMA) algorithm to iteratively optimize both the long and short deformation memory, updating the memory queue for mitigating local anatomical ambiguity. The proposed multi-task system can be trained in a weakly-supervised manner, which only requires few landmark annotations for tracking and zero annotation for deformation learning. We conduct extensive experiments on both public and private ultrasound landmark tracking datasets. Experimental results show that LSDM can achieve better or competitive landmark tracking performance with a strong generalization capability across different scanner types and different ultrasound modalities, compared with other state-of-the-art methods.

ECGVEDNET: A Variational Encoder-Decoder Network for ECG Delineation in Morphology Variant ECGs.

Electrocardiogram (ECG) delineation to identify the fiducial points of ECG segments, plays an important role in cardiovascular diagnosis and care. Whilst deep delineation frameworks have been deployed within the literature, several factors still hinder their development: (a) data availability: the capacity of deep learning models to generalise is limited by the amount of available data; (b) morphology variations: ECG complexes vary, even within the same person, which degrades the performance of conventional deep learning models. To address these concerns, we present a large-scale 12-leads ECG dataset, ICDIRS, to train and evaluate a novel deep delineation model-ECGVEDNET. ICDIRS is a large-scale ECG dataset with 156,145 QRS onset annotations and 156,145 T peak annotations. ECGVEDNET is a novel variational encoder-decoder network designed to address morphology variations. In ECGVEDNET, we construct a well-regularized latent space, in which the latent features of ECG follow a regular distribution and present smaller morphology variations than in the raw data space. Finally, a transfer learning framework is proposed to transfer the knowledge learned on ICDIRS to smaller datasets. On ICDIRS, ECGVEDNET achieves accuracy of 86.28%/88.31% within 5/10 ms tolerance for QRS onset and accuracy of 89.94%/91.16% within 5/10 ms tolerance for T peak. On QTDB, the average time errors computed for QRS onset and T peak are -1.86 ± 8.02 ms and -0.50 ± 12.96 ms, respectively, achieving state-of-the-art performances on both large and small-scale datasets. We will release the source code and the pre-trained model on ICDIRS once accepted.

A new method applied for explaining the landing patterns: Interpretability analysis of machine learning.

As one of many fundamental sports techniques, the landing maneuver is also frequently used in clinical injury screening and diagnosis. However, the landing patterns are different under different constraints, which will cause great difficulties for clinical experts in clinical diagnosis. Machine learning (ML) have been very successful in solving a variety of clinical diagnosis tasks, but they all have the disadvantage of being black boxes and rarely provide and explain useful information about the reasons for making a particular decision. The current work validates the feasibility of applying an explainable ML (XML) model constructed by Layer-wise Relevance Propagation (LRP) for landing pattern recognition in clinical biomechanics. This study collected 560 groups landing data. By incorporating these landing data into the XML model as input signals, the prediction results were interpreted based on the relevance score (RS) derived from LRP. The interpretation obtained from XML was evaluated comprehensively from the statistical perspective based on Statistical Parametric Mapping (SPM) and Effect Size. The RS has excellent statistical characteristics in the interpretation of landing patterns between classes, and also conforms to the clinical characteristics of landing pattern recognition. The current work highlights the applicability of XML methods that can not only satisfy the traditional decision problem between classes, but also largely solve the lack of transparency in landing pattern recognition. We provide a feasible framework for realizing interpretability of ML decision results in landing analysis, providing a methodological reference and solid foundation for future clinical diagnosis and biomechanical analysis.

Effects of different contact angles during forefoot running on the stresses of the foot bones: a finite element simulation study.

Introduction: The purpose of this study was to compare the changes in foot at different sole-ground contact angles during forefoot running. This study tried to help forefoot runners better control and improve their technical movements by comparing different sole-ground contact angles. Methods: A male participant of Chinese ethnicity was enlisted for the present study, with a recorded age of 25 years, a height of 183 cm, and a body weight of 80 kg. This study focused on forefoot strike patterns through FE analysis. Results: It can be seen that the peak von Mises stress of M1-5 (Metatarsal) of a (Contact angle: 9.54) is greater than that of b (Contact angle: 7.58) and c (Contact angle: 5.62) in the three cases. On the contrary, the peak von Mises stress of MC (Medial Cuneiform), IC (Intermediate Cuneiform), LC (Lateral Cuneiform), C (Cuboid), N (Navicular), T (Tarsal) in three different cases is opposite, and the peak von Mises stress of c is greater than that of a and b. The peak von Mises stress of b is between a and c. Conclusion: This study found that a reduced sole-ground contact angle may reduce metatarsal stress fractures. Further, a small sole-ground contact angle may not increase ankle joint injury risk during forefoot running. Hence, given the specialized nature of the running shoes designed for forefoot runners, it is plausible that this study may offer novel insights to guide their athletic pursuits.