Analysis of peak locomotor demands in women's football-the influence of different epoch lengths.

The quantification of peak locomotor demands has been gathering researchers' attention in the past years. Regardless of the different methodological approaches used, the most selected epochs are between 1-, 3-, 5- and 15-minutes time windows. However, the selection of these time frames is frequently arbitrary. The aim of this study was to analyse the peak locomotor demands of short time epochs (15, 30, 45, and 60 seconds) in women's football, with special emphasis over the high-speed metrics. During two seasons, the match physical performance of 100 female football players was collected with Global Positioning System units (STATSports Apex). Peak locomotor demands for the selected variables were calculated by using a 1-second moving average approach. For statistical procedures, linear mixed modelling was used, with total distance, high-speed running distance (>16 km∙h-1), sprint distance (>20 km∙h-1), and acceleration and deceleration distance (±2.26 m∙s-2) considered as the dependent variables and the epoch lengths (15, 30, 45, and 60 seconds) considered as the independent variables. A novel finding was the high ratio observed in the 15 seconds epochs of high-speed running distance and sprint distance (77.6% and 91.3%, respectively). The results show that most peak high-speed demands within 60 seconds are completed within just 15 seconds. Thus, intensity-related variables, such as high-speed metrics, would be better contextualised and adapted into training practices if analysed in shorter epoch lengths (15-30 seconds), while longer periods might be used for volume-related metrics (i.e., total distance), depending on the purpose of the analysis.

An analysis of training load in highly trained female football players.

This observational study aimed to analyze external training load in highly trained female football players, comparing starters and non-starters across various cycle lengths and training days. METHOD: External training load [duration, total distance [TD], high-speed running distance [HSRD], sprint distance [SpD], and acceleration- and deceleration distance [AccDecdist] from 100 female football players (22.3 ± 3.7 years of age) in the Norwegian premier division were collected over two seasons using STATSports APEX. This resulted in a final dataset totaling 10498 observations after multiple imputation of missing data. Microcycle length was categorized based on the number of days between matches (2 to 7 days apart), while training days were categorized relative to match day (MD, MD+1, MD+2, MD-5, MD-4, MD-3, MD-2, MD-1). Linear mixed modeling was used to assess differences between days, and starters vs. non-starters. RESULTS: In longer cycle lengths (5-7 days between matches), the middle of the week (usually MD-4 or MD-3) consistently exhibited the highest external training load (~21-79% of MD TD, MD HSRD, MD SpD, and MD AccDecdist); though, with the exception of duration (~108-120% of MD duration), it remained lower than MD. External training load was lowest on MD+2 and MD-1 (~1-37% of MD TD, MD HSRD, MD SpD, MD AccDecdist, and ~73-88% of MD peak speed). Non-starters displayed higher loads (~137-400% of starter TD, HSRD, SpD, AccDecdist) on MD+2 in cycles with 3 to 7 days between matches, with non-significant differences (~76-116%) on other training days. CONCLUSION: Loading patterns resemble a pyramid or skewed pyramid during longer cycle lengths (5-7 days), with higher training loads towards the middle compared to the start and the end of the cycle. Non-starters displayed slightly higher loads on MD+2, with no significant load differentiation from MD-5 onwards.

A large-scale multivariate soccer athlete health, performance, and position monitoring dataset.

Data analysis for athletic performance optimization and injury prevention is of tremendous interest to sports teams and the scientific community. However, sports data are often sparse and hard to obtain due to legal restrictions, unwillingness to share, and lack of personnel resources to be assigned to the tedious process of data curation. These constraints make it difficult to develop automated systems for analysis, which require large datasets for learning. We therefore present SoccerMon, the largest soccer athlete dataset available today containing both subjective and objective metrics, collected from two different elite women's soccer teams over two years. Our dataset contains 33,849 subjective reports and 10,075 objective reports, the latter including over six billion GPS position measurements. SoccerMon can not only play a valuable role in developing better analysis and prediction systems for soccer, but also inspire similar data collection activities in other domains which can benefit from subjective athlete reports, GPS position information, and/or time-series data in general.

The influence of age on the match-to-match variability of physical performance in women's elite football.

Introduction: The fluctuation of external match load throughout a season is influenced by several contextual factors. While some, have been deeply analysed in men's football literature, information is lacking on how other contextual elements, such as player's age or experience, may affect the match-to-match variability of locomotor activities. In fact, aging has been described as a multifactorial process with the potential to affect human performance. The aim of this study is to assess if the variability of match locomotor performances fluctuates according to the players' age. Methods: 59 female players from four top-level clubs were divided into three age groups and monitored during two seasons using GPS APEX (STATSports, Northern Ireland), with a sampling frequency of 10Hz, in 150 official matches to determine the coefficient of variation (CV) of full-match and 1-min peak locomotor demands of total distance (TD), high-speed running distance, sprint distance (SpD), accelerations, and decelerations. To test whether there was a group effect of age on match-to-match variability we used a one-way ANOVA with CV% as the independent variable. Results: CV values of full match variables ranged from 3.8% to 27.8%, with total distance (3.8%) in the peak age group and SpD (27.8%) in the pre-peak age group. Similarly, CV values of 1-min peaks ranged from 4.1% (post-peak group) in TD to 22.3% (peak group) in SpD. Discussion: The main finding was that there were no significant differences between the different age groups in the metrics analysed although trends indicate less variability in the post-peak age group.

FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation.

The increase of available large clinical and experimental datasets has contributed to a substantial amount of important contributions in the area of biomedical image analysis. Image segmentation, which is crucial for any quantitative analysis, has especially attracted attention. Recent hardware advancement has led to the success of deep learning approaches. However, although deep learning models are being trained on large datasets, existing methods do not use the information from different learning epochs effectively. In this work, we leverage the information of each training epoch to prune the prediction maps of the subsequent epochs. We propose a novel architecture called feedback attention network (FANet) that unifies the previous epoch mask with the feature map of the current training epoch. The previous epoch mask is then used to provide hard attention to the learned feature maps at different convolutional layers. The network also allows rectifying the predictions in an iterative fashion during the test time. We show that our proposed feedback attention model provides a substantial improvement on most segmentation metrics tested on seven publicly available biomedical imaging datasets demonstrating the effectiveness of FANet. The source code is available at https://github.com/nikhilroxtomar/FANet.

The variability of physical match demands in elite women's football.

Peak locomotor demands are considered as key metrics for conditioning drills prescription and training monitoring. However, research in female football has focused on absolute values when reporting match demands, leading to sparse information being provided regarding the degrees of variability of such metrics. Thus, the aims of this study were to investigate the sources of variability of match physical performance parameters in female football players and to provide a framework for the interpretation of meaningful changes between matches.54 female players from four top-level clubs were monitored during one season. GPS APEX (STATSports, Northern Ireland), with a sampling frequency of 10 Hz, were used in 60 official matches (n = 393) to determine the full-match and 1-min peak locomotor demands of total distance (TD), high-speed running distance (HSRD), sprint distance (SpD), accelerations and decelerations (Acc/Dec) and peak speed (Pspeed). For each variable, the between-team, between-match, between-position, between-player, and within-player variability was estimated using linear mixed-effect modelling.With exception to SpD (29.4 vs. 31.9%), all other metrics presented a higher observed match-to-match variability in the 1-min peaks than in the full-match (6.5 vs. 4.6%; 18.7% vs. 15.9%; 12.9 vs. 11.7%; for TD, HSRD and Acc/Dec, respectively). With the exception of SpD, higher changes in 1-min peaks than in full-match values are required to identify meaningful changes in each variable.Different sources of variability seem to impact differently the match physical performance of female football players. Furthermore, to identify meaningful changes, higher changes in 1-min peaks than in full-match values are required.

Video Analytics in Elite Soccer: A Distributed Computing Perspective.

Ubiquitous sensors and Internet of Things (IoT) technologies have revolutionized the sports industry, providing new methodologies for planning, effective coordination of training, and match analysis post game. New methods, including machine learning, image and video processing, have been developed for performance evaluation, allowing the analyst to track the performance of a player in real-time. Following FIFA's 2015 approval of electronics performance and tracking system during games, performance data of a single player or the entire team is allowed to be collected using GPS-based wearables. Data from practice sessions outside the sporting arena is being collected in greater numbers than ever before. Realizing the significance of data in professional soccer, this paper presents video analytics, examines recent state-of-the-art literature in elite soccer, and summarizes existing real-time video analytics algorithms. We also discuss real-time crowdsourcing of the obtained data, tactical and technical performance, distributed computing and its importance in video analytics and propose a future research perspective.

MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation.

Methods based on convolutional neural networks have improved the performance of biomedical image segmentation. However, most of these methods cannot efficiently segment objects of variable sizes and train on small and biased datasets, which are common for biomedical use cases. While methods exist that incorporate multi-scale fusion approaches to address the challenges arising with variable sizes, they usually use complex models that are more suitable for general semantic segmentation problems. In this paper, we propose a novel architecture called Multi-Scale Residual Fusion Network (MSRF-Net), which is specially designed for medical image segmentation. The proposed MSRF-Net is able to exchange multi-scale features of varying receptive fields using a Dual-Scale Dense Fusion (DSDF) block. Our DSDF block can exchange information rigorously across two different resolution scales, and our MSRF sub-network uses multiple DSDF blocks in sequence to perform multi-scale fusion. This allows the preservation of resolution, improved information flow and propagation of both high- and low-level features to obtain accurate segmentation maps. The proposed MSRF-Net allows to capture object variabilities and provides improved results on different biomedical datasets. Extensive experiments on MSRF-Net demonstrate that the proposed method outperforms the cutting-edge medical image segmentation methods on four publicly available datasets. We achieve the Dice Coefficient (DSC) of 0.9217, 0.9420, and 0.9224, 0.8824 on Kvasir-SEG, CVC-ClinicDB, 2018 Data Science Bowl dataset, and ISIC-2018 skin lesion segmentation challenge dataset respectively. We further conducted generalizability tests and achieved DSC of 0.7921 and 0.7575 on CVC-ClinicDB and Kvasir-SEG, respectively.

A Comprehensive Study on Colorectal Polyp Segmentation With ResUNet++, Conditional Random Field and Test-Time Augmentation.

Colonoscopy is considered the gold standard for detection of colorectal cancer and its precursors. Existing examination methods are, however, hampered by high overall miss-rate, and many abnormalities are left undetected. Computer-Aided Diagnosis systems based on advanced machine learning algorithms are touted as a game-changer that can identify regions in the colon overlooked by the physicians during endoscopic examinations, and help detect and characterize lesions. In previous work, we have proposed the ResUNet++ architecture and demonstrated that it produces more efficient results compared with its counterparts U-Net and ResUNet. In this paper, we demonstrate that further improvements to the overall prediction performance of the ResUNet++ architecture can be achieved by using Conditional Random Field (CRF) and Test-Time Augmentation (TTA). We have performed extensive evaluations and validated the improvements using six publicly available datasets: Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, ETIS-Larib Polyp DB, ASU-Mayo Clinic Colonoscopy Video Database, and CVC-VideoClinicDB. Moreover, we compare our proposed architecture and resulting model with other state-of-the-art methods. To explore the generalization capability of ResUNet++ on different publicly available polyp datasets, so that it could be used in a real-world setting, we performed an extensive cross-dataset evaluation. The experimental results show that applying CRF and TTA improves the performance on various polyp segmentation datasets both on the same dataset and cross-dataset. To check the model's performance on difficult to detect polyps, we selected, with the help of an expert gastroenterologist, 196 sessile or flat polyps that are less than ten millimeters in size. This additional data has been made available as a subset of Kvasir-SEG. Our approaches showed good results for flat or sessile and smaller polyps, which are known to be one of the major reasons for high polyp miss-rates. This is one of the significant strengths of our work and indicates that our methods should be investigated further for use in clinical practice.

Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning.

Computer-aided detection, localisation, and segmentation methods can help improve colonoscopy procedures. Even though many methods have been built to tackle automatic detection and segmentation of polyps, benchmarking of state-of-the-art methods still remains an open problem. This is due to the increasing number of researched computer vision methods that can be applied to polyp datasets. Benchmarking of novel methods can provide a direction to the development of automated polyp detection and segmentation tasks. Furthermore, it ensures that the produced results in the community are reproducible and provide a fair comparison of developed methods. In this paper, we benchmark several recent state-of-the-art methods using Kvasir-SEG, an open-access dataset of colonoscopy images for polyp detection, localisation, and segmentation evaluating both method accuracy and speed. Whilst, most methods in literature have competitive performance over accuracy, we show that the proposed ColonSegNet achieved a better trade-off between an average precision of 0.8000 and mean IoU of 0.8100, and the fastest speed of 180 frames per second for the detection and localisation task. Likewise, the proposed ColonSegNet achieved a competitive dice coefficient of 0.8206 and the best average speed of 182.38 frames per second for the segmentation task. Our comprehensive comparison with various state-of-the-art methods reveals the importance of benchmarking the deep learning methods for automated real-time polyp identification and delineations that can potentially transform current clinical practices and minimise miss-detection rates.

Up-to-the-Minute Privacy Policies via Gossips in Participatory Epidemiological Studies.

Researchers and researched populations are actively involved in participatory epidemiology. Such studies collect many details about an individual. Recent developments in statistical inferences can lead to sensitive information leaks from seemingly insensitive data about individuals. Typical safeguarding mechanisms are vetted by ethics committees; however, the attack models are constantly evolving. Newly discovered threats, change in applicable laws or an individual's perception can raise concerns that affect the study. Addressing these concerns is imperative to maintain trust with the researched population. We are implementing Lohpi: an infrastructure for building accountability in data processing for participatory epidemiology. We address the challenge of data-ownership by allowing institutions to host data on their managed servers while being part of Lohpi. We update data access policies using gossips. We present Lohpi as a novel architecture for research data processing and evaluate the dissemination, overhead, and fault-tolerance.

Maximal Strength, Sprint, and Jump Performance in High-Level Female Football Players Are Maintained With a Customized Training Program During the COVID-19 Lockdown.

INTRODUCTION: The COVID-19 outbreak with partial lockdown has inevitably led to an alteration in training routines for football players worldwide. Thus, coaches had to face with the novel challenge of minimizing the potential decline in fitness during this period of training disruption. METHODS: In this observational pre- to posttest study involving Norwegian female football players (18.8 ± 1.9 years, height 1.68 ± 0.4 m, mass 61.3 ± 3.7 kg), we investigated the effects of a prescribed home-based and group-based intervention, implemented during the COVID-19 lockdown, on maximal muscular force production and high velocity variables. Specifically, maximal partial squat strength one repetition maximum (1RM), counter movement jump (CMJ) and 15 m sprint time were assessed 1 week prior to the lockdown and 12 weeks after the onset of lockdown. We also collected training content and volume from the prescribed training program and self-reported perceived training quality and motivation toward training. RESULTS: We observed no change in 1RM [pretest: 104 ± 12 kg, posttest: 101 ± 11 kg (P = 0.28)], CMJ height [pretest: 28.1 ± 2.3 cm, posttest: 26.8 ± 1.9 (P = 0.09)], and 15 m sprint time [pretest: 2.60 ± 0.08 s, posttest: 2.61 ± 0.07 s (P = 0.52)]. CONCLUSION: Our findings suggest that a prescribed home-based and group-based intervention with increased training time devoted to strength, jump, and sprint ability, and regulated to obtain a sufficient infection control level is feasible and effective to preserve strength, jumping, and sprinting abilities of high-level female football players during a ∼ 3-month period of a pandemic-induced lockdown.

Kvasir-Capsule, a video capsule endoscopy dataset.

Artificial intelligence (AI) is predicted to have profound effects on the future of video capsule endoscopy (VCE) technology. The potential lies in improving anomaly detection while reducing manual labour. Existing work demonstrates the promising benefits of AI-based computer-assisted diagnosis systems for VCE. They also show great potential for improvements to achieve even better results. Also, medical data is often sparse and unavailable to the research community, and qualified medical personnel rarely have time for the tedious labelling work. We present Kvasir-Capsule, a large VCE dataset collected from examinations at a Norwegian Hospital. Kvasir-Capsule consists of 117 videos which can be used to extract a total of 4,741,504 image frames. We have labelled and medically verified 47,238 frames with a bounding box around findings from 14 different classes. In addition to these labelled images, there are 4,694,266 unlabelled frames included in the dataset. The Kvasir-Capsule dataset can play a valuable role in developing better algorithms in order to reach true potential of VCE technology.

A comprehensive analysis of classification methods in gastrointestinal endoscopy imaging.

Gastrointestinal (GI) endoscopy has been an active field of research motivated by the large number of highly lethal GI cancers. Early GI cancer precursors are often missed during the endoscopic surveillance. The high missed rate of such abnormalities during endoscopy is thus a critical bottleneck. Lack of attentiveness due to tiring procedures, and requirement of training are few contributing factors. An automatic GI disease classification system can help reduce such risks by flagging suspicious frames and lesions. GI endoscopy consists of several multi-organ surveillance, therefore, there is need to develop methods that can generalize to various endoscopic findings. In this realm, we present a comprehensive analysis of the Medico GI challenges: Medical Multimedia Task at MediaEval 2017, Medico Multimedia Task at MediaEval 2018, and BioMedia ACM MM Grand Challenge 2019. These challenges are initiative to set-up a benchmark for different computer vision methods applied to the multi-class endoscopic images and promote to build new approaches that could reliably be used in clinics. We report the performance of 21 participating teams over a period of three consecutive years and provide a detailed analysis of the methods used by the participants, highlighting the challenges and shortcomings of the current approaches and dissect their credibility for the use in clinical settings. Our analysis revealed that the participants achieved an improvement on maximum Mathew correlation coefficient (MCC) from 82.68% in 2017 to 93.98% in 2018 and 95.20% in 2019 challenges, and a significant increase in computational speed over consecutive years.

Privacy Perceptions and Concerns in Image-Based Dietary Assessment Systems: Questionnaire-Based Study.

BACKGROUND: Complying with individual privacy perceptions is essential when processing personal information for research. Our specific research area is performance development of elite athletes, wherein nutritional aspects are important. Before adopting new automated tools that capture such data, it is crucial to understand and address the privacy concerns of the research subjects that are to be studied. Privacy as contextual integrity emphasizes understanding contextual sensitivity in an information flow. In this study, we explore privacy perceptions in image-based dietary assessments. This research field lacks empirical evidence on what will be considered as privacy violations when exploring trends in long-running studies. Prior studies have only classified images as either private or public depending on their basic content. An assessment and analysis are thus needed to prevent unwanted consequences of privacy breach and other issues perceived as sensitive when designing systems for dietary assessment by using food images. OBJECTIVE: The aim of this study was to investigate common perceptions of computer systems using food images for dietary assessment. The study delves into perceived risks and data-sharing behaviors. METHODS: We investigated the privacy perceptions of 105 individuals by using a web-based survey. We analyzed these perceptions along with perceived risks in sharing dietary information with third parties. RESULTS: We found that understanding the motive behind the use of data increases its chances of sharing with a social group. CONCLUSIONS: In this study, we highlight various privacy concerns that can be addressed during the design phase. A system design that is compliant with general data protection regulations will increase participants' and stakeholders' trust in an image-based dietary assessment system. Innovative solutions are needed to reduce the intrusiveness of a continuous assessment. Individuals show varying behaviors for sharing metadata, as knowing what the data is being used for, increases the chance of it being shared.

HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy.

Artificial intelligence is currently a hot topic in medicine. However, medical data is often sparse and hard to obtain due to legal restrictions and lack of medical personnel for the cumbersome and tedious process to manually label training data. These constraints make it difficult to develop systems for automatic analysis, like detecting disease or other lesions. In this respect, this article presents HyperKvasir, the largest image and video dataset of the gastrointestinal tract available today. The data is collected during real gastro- and colonoscopy examinations at Bærum Hospital in Norway and partly labeled by experienced gastrointestinal endoscopists. The dataset contains 110,079 images and 374 videos, and represents anatomical landmarks as well as pathological and normal findings. The total number of images and video frames together is around 1 million. Initial experiments demonstrate the potential benefits of artificial intelligence-based computer-assisted diagnosis systems. The HyperKvasir dataset can play a valuable role in developing better algorithms and computer-assisted examination systems not only for gastro- and colonoscopy, but also for other fields in medicine.

Positional Differences in Peak- and Accumulated- Training Load Relative to Match Load in Elite Football.

Quantification of training and match load is an important method to personalize the training stimulus' prescription to players according to their match demands. The present study used time-motion analysis and triaxial-accelerometer to quantify and compare: a) The most demanding passages of play in training sessions and matches (5-min peaks); b) and the accumulated load of typical microcycles and official matches, by playing position. Players performance data in 15 official home matches and 11 in-season microcycles were collected for analysis. Players were divided into four different playing positions: Centre-backs, wing-backs, centre midfielders, and centre forwards. The results show that match demands were overperformed for acceleration counts (acccounts) (131%-166%) and deceleration counts (deccounts) (108%-134%), by all positions. However, relative to match values, training values for sprint distance (sprintdist) and high-intensity run distance (HIRdist) were considerably lower (36%-61% and 57%-71%) than for accelerations and decelerations. The most pronounced difference on the 5-min peaks was observed in sprints (sprintpeak), with wing-backs achieving during the microcycle only 64% of the sprintpeak in matches, while centre backs, centre midfielders, and centre forwards levelled and overperformed the match values (107%, 100%, and 107%, respectively). Differences observed across playing positions in matches and microcycles underline the lack of position specificity of common training drills/sessions adopted by coaches in elite football.

Improved maximal strength is not associated with improvements in sprint time or jump height in high-level female football players: a clusterrendomized controlled trial.

BACKGROUND: Maximal strength increments are reported to result in improvements in sprint speed and jump height in elite male football players. Although similar effects are expected in females, this is yet to be elucidated. The aim of this study was to examine the effect of maximal strength training on sprint speed and jump height in high-level female football players. METHODS: Two female football teams were team-cluster-randomized to a training group (TG) performing maximal strength training (MST) twice a week for 5 weeks, or control group (CG) doing their regular pre-season preparations. The MST consisted of 3-4 sets of 4-6 repetitions at ≥85% of 1 repetitions maximum (1RM) in a squat exercise. Sprint speed and jump height were assessed in 5-, 10- and 15 m sprints and a counter-movement jump (CMJ) test, respectively. Nineteen participants in TG (18.3 ± 2.7 years) and 14 in CG (18.3 ± 2.4 years) completed pre- and posttests and were carried forward for final analyses. RESULTS: There was no improvement in neither of the sprint times (p > 0.36), nor jump height (p = 0.87). The players increased their 1RM in squats (main of effect of time: p < 0.00, pη2 = 0.704), and an interaction effect of time x group was observed (p < 0.00, pη2 = 0.516) where the TG increased their 1RM more than the CT (between subjects effects: p < 0.001, pη2 = 0.965). CONCLUSIONS: MST improved maximal strength in female football players to a large extent; however, the improvement in maximal strength did not result in any transference to sprint speed or jump height. TRIAL REGISTRATION: This study was registered at clinicaltrials.gov PRS (Protocol registration and results System) with the code NCT04048928, 07.08.2019, retrospectively registered.

A comparison of match-physical demands between different tactical systems: 1-4-5-1 vs 1-3-5-2.

The team tactical system and distribution of the football players on the pitch is considered fundamental in team performance. The present study used time-motion analysis and triaxial-accelerometers to obtain new insights about the impact of different tactical systems (1-4-5-1 and 1-3-5-2) on physical performance, across different playing positions, in a professional football team. Player performance data in fifteen official home matches was collected for analysis. The sample included twenty-two players from five playing positions (centre backs: n = 4; full-back/wide midfielder/ wing-back: n = 9; centre midfielder: n = 6 and centre forward: n = 3), making a total of 108 match observations. A novel finding was that general match physical demands do not differ considerably between these tactical formations, probably because match-to-match variability (variation of players' running profile from match-to-match) might be higher than the differences in physical performance between tactical systems. However, change of formation had a different impact across playing positions, with centre backs playing in 1-4-5-1 performing significant more HIRcounts than in 1-3-5-2 (p = 0.031). Furthermore, a medium effect size (r = 0.33) was observed in HIRdist, with wide players covering higher distances when playing in 1-3-5-2 than in 1-4-5-1. These findings may help coaches to develop individualised training programs to meet the demands of each playing position according to the tactical system adopted.