Tind Technologies (Norway)
Hes-so: ArODES Open Archive (University of Applied Sciences and Arts Western Switzerland / Haute école spécialisée de Suisse occidentale / FH Westschweiz)Not a member yet
15764 research outputs found
Sort by
A-eye ::automated 3D segmentation of healthy human eye and orbit structures and axial length extraction
No full textThis study addresses the need for accurate 3D segmentation of the human eye and orbit from MRI to improve ophthalmic diagnostics. Past efforts focused on small sample sizes and varied imaging methods. Here, two techniques (atlas-based registration and supervised deep learning) are tested for automated segmentation on a large T1-weighted MRI dataset. Results show accurate segmentations of the lens, globe, optic nerve, rectus muscles, and fat. Additionally, the study automates the estimation of axial length, a key biomarker
Evaluating the role of human and environmental factors causing the distribution of invasive plant species in the cantons of Vaud and Neuchâtel in Switzerland
No full textInvasive alien plant species are an increasing concern in many countries due to their negative impacts on local ecosystems, human health, infrastructure, and agriculture, to name a few. In Switzerland, substantial financial resources are allocated each year to combat the spread and eradicate these invasive species. Understanding their spatial distribution through species distribution modeling is crucial for improving management interventions. This study aims to examine the role of environmental and human factors in predicting the distribution of three invasive plant species (Prunus laurocerasus, Buddleja davidii, and Robinia pseudoacacia) in the Cantons of Vaud and Neuchâtel in Western Switzerland. A random forest algorithm is trained, and the resulting model is used to assess the relative importance of various environmental and human factors in predicting species distribution. The results highlight that while environmental features play a significant role in generating distribution maps, incorporating human activity patterns, such as proximity to built areas, railways, and roads, greatly enhances prediction accuracy and leads to more robust models
Beyond Malbec ::exploring winerie's perspectives on diversification strategies in Argentina's wine industry
No full textWorkplace violence and their determinants toward formal caregivers in the homecare setting: A cross-sectional study
No full textIntroduction: Workplace violence against formal caregivers
is a signifcant concern in health care, with consequences on
formal caregivers’ health state as well as care-dependent people’s quality of care. However, this topic is rarely investigated
in European home care settings. Terefore, this study aims
to assess the frequency, type of violence, consequences and
related factors of workplace violence towards formal caregivers
working with care-dependent people living at home.
Methods: A descriptive cross-sectional study was conducted,
with a convenience sample of formal caregivers employed in a
home care setting in the French-speaking part of Switzerland.
Te formal caregivers included in this study met the following
criteria: (1) aged 18 years or older, (2) directly involved in providing care to the care-dependent people living at home, and
(3) possessed sufcient profciency in French.
Results: Out of the 686 invited formal caregivers, 200 participated in the study. In total 42% of the participants reported
experiencing at least one instance of workplace violence in the
last year, including physical violence (14.5%), non-physical violence (39%), sexual harassment (8%), and sexual aggression
(2.5%). Consequences of workplace violence included injuries,
with 24% of participants experiencing injuries during the most
recent incident of physical violence.
Conclusion: Tese fndings emphasize the high rate of workplace violence toward formal caregivers in the home care setting in Switzerland and highlight the signifcant consequences
for formal caregivers. Addressing and reducing workplace violence is crucial for maintaining formal caregiver safety, quality
of work and the care-dependent people’s quality of care
Le récit de pratique, un outil professionnel
No full textÉcrire pour penser: comment les récits de pratique viennent-ils soutenir le processus de professionnalisation des praticien·nes en travail social? Réflexion
Developing an AI-powered wound assessment tool: ::a methodological approach to data collection and model optimization
No full textBackground : Chronic wounds (CWs) represent a significant and growing challenge in healthcare due to their prolonged healing times, complex management, and associated costs. Inadequate wound assessment by healthcare professionals (HCPs), often due to limited training and high clinical workload, contributes to suboptimal treatment and increased risk of complications. This study aimed to develop an artificial intelligence (AI)-powered wound assessment tool, integrated into a mobile application, to support HCPs in diagnosis, monitoring, and clinical decision-making. Methods : A multicenter observational study was conducted across three healthcare institutions in Western Switzerland. Researchers compiled a hybrid dataset of approximately 4,000 wound images through both retrospective extraction from clinical records and prospective collection using a standardized mobile application. The prospective data included high-resolution images, short videos, and 3D scans, along with structured clinical metadata. Retrospective data were anonymized and manually annotated by wound care experts. All images were labeled for wound segmentation and tissue classification to train and validate deep learning models. Results : The resulting dataset represented a broad spectrum of wound types (acute and chronic), anatomical locations, skin tones, and healing stages. The AI-based wound segmentation model, developed using the Deeplabv3 + architecture with a ResNet50 backbone, achieved a DICE score of 92% and an Intersection-over-Union (IOU) score of 85%. Tissue classification yielded a preliminary mean DICE score of 78%, although accuracy varied across tissue types, especially fibrin and necrosis. The models were optimized for mobile implementation through quantization, achieving real-time inference with an average processing time of 0.3 seconds and only a 0.3% performance reduction. The dual approach to data collection, prospective and retrospective—ensured both image standardization and real-world variability, enhancing the model’s generalizability. Conclusions : This study laid the foundation for an AI-driven digital tool to assist clinical wound assessment and education. The integration of robust datasets and AI models demonstrated the potential to improve diagnostic precision, support personalized care, and reduce wound-related healthcare costs. Although challenges remained, particularly in tissue classification, this work highlighted the promise of AI in transforming wound care and advancing clinical training
