Professional swimming coaches make use of videos to evaluate their athletes’ performances. Specifically, the videos are manually analyzed in order to observe the movements of all parts of the swimmer’s body during the exercise and to give indications for improving swimming technique. This operation is time-consuming, laborious and error prone. In recent years, alternative technologies have been introduced in the literature, but they still have severe limitations that make their correct and effective use impossible. In fact, the currently available techniques based on image analysis only apply to certain swimming styles; moreover, they are strongly influenced by disturbing elements (i.e., the presence of bubbles, splashes and reflections), resulting in poor measurement accuracy. The use of wearable sensors (accelerometers or photoplethysmographic sensors) or optical markers, although they can guarantee high reliability and accuracy, disturb the performance of the athletes, who tend to dislike these solutions. In this work we introduce swimmerNET, a new marker-less 2D swimmer pose estimation approach based on the combined use of computer vision algorithms and fully convolutional neural networks. By using a single 8 Mpixel wide-angle camera, the proposed system is able to estimate the pose of a swimmer during exercise while guaranteeing adequate measurement accuracy. The method has been successfully tested on several athletes (i.e., different physical characteristics and different swimming technique), obtaining an average error and a standard deviation (worst case scenario for the dataset analyzed) of approximately 1 mm and 10 mm, respectively.
BackgroundVideo‐assisted thoracoscopic surgery (VATS) resection of deep‐seated lung nodules smaller than 1 cm is extremely challenging. Several methods have been proposed to overcome this limitation but with not neglectable complications. Intraoperative lung ultrasound (ILU) is the latest minimally invasive proposed technique. The aim of the current study was to analyze the accuracy and efficacy of ILU associated with VATS to visualize solitary and deep‐seated pulmonary nodules smaller than 1 cm.MethodsPatients with subcentimetric solitary and deep‐seated pulmonary nodules were included in this retrospective study from November 2020 to December 2022. Patients who received VATS aided with ILU were considered as group A and patients who received conventional VATS as group B (control group). The rate of nodule identification and the time for localization with VATS alone and with VATS aided with ILU in each group were analyzed.ResultsA total of 43 patients received VATS aided with ILU (group A) and 31 patients received conventional VATS (group B). Mean operative time was lower in group A (p < 0.05). In group A all the nodules were correctly identified, while in group B in one case the localization failed. The time to identify the lesion was lower in group A (7.1 ± 2.2 vs. 13.8 ± 4.6; p < 0.05). During hospitalization three patients (6.5%; p < 0.05) in group B presented air leaks that were conservatively managed.ConclusionIntracavitary VATS‐US is a reliable, feasible, real‐time and effective method of localization of parenchymal lung nodules during selected wedge resection procedures.
ObjectiveTo investigate the epidemiology of pregnancy‐related urinary incontinence (UI) and the related risk factors, focusing also on women's characteristics related to maternity pathway utilization.MethodsIn this prospective cohort study, we used patient‐reported data obtained from the systematic survey on the maternity pathway that all pregnant women in Tuscany, Italy, can join. We selected 8410 women who completed—between March 2019 and November 2022—all five follow‐up questionnaires from the first trimester until 12 months postpartum, each including a UI‐specific patient‐reported outcome measure. We performed panel regression models to explore the related risk factors.ResultsPrevalence of UI was 4.4% at the first trimester, 23.7% at the third trimester, and 15.6%, 12.6%, and 12.4% at 3, 6, and 12 months postpartum. UI occurrence and severity were higher in older, overweight/obese, and unemployed women. High‐risk pregnancy and discomfort during pregnancy were risk factors. Receiving a cesarean section reduced the risk, while spontaneous tears, episiotomy, and high birth weight increased it. Women who experienced delays in pregnancy examinations because of long waiting times and women who had planned pregnancy had a higher risk, while performing during‐pregnancy pelvic‐floor‐muscle training was protective.ConclusionBesides confirming the classic risk and protective factors for UI, we also found novel determinants related to the proper maternity pathway utilization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.