Zobrazeno 1 - 10
of 3 953
pro vyhledávání: '"Voiculescu, A"'
Autor:
Willoughby, James, Voiculescu, Irina
Microscopy structure segmentation, such as detecting cells or nuclei, generally requires a human to draw a ground truth contour around each instance. Weakly supervised approaches (e.g. consisting of only single point labels) have the potential to red
Externí odkaz:
http://arxiv.org/abs/2411.13528
Many image processing applications rely on partitioning an image into disjoint regions whose pixels are 'similar.' The watershed and waterfall transforms are established mathematical morphology pixel clustering techniques. They are both relevant to m
Externí odkaz:
http://arxiv.org/abs/2410.08946
Autor:
Wyatt, Julian, Voiculescu, Irina
Cephalometric Landmark Detection is the process of identifying key areas for cephalometry. Each landmark is a single GT point labelled by a clinician. A machine learning model predicts the probability locus of a landmark represented by a heatmap. Thi
Externí odkaz:
http://arxiv.org/abs/2410.04445
Autor:
Wyatt, Julian, Voiculescu, Irina
Anatomical Landmark Detection is the process of identifying key areas of an image for clinical measurements. Each landmark is a single ground truth point labelled by a clinician. A machine learning model predicts the locus of a landmark as a probabil
Externí odkaz:
http://arxiv.org/abs/2407.09192
Autor:
Willoughby, James, Voiculescu, Irina
Segmentation has become a crucial pre-processing step to many refined downstream tasks, and particularly so in the medical domain. Even with recent improvements in segmentation models, many segmentation tasks remain difficult. When multiple organs ar
Externí odkaz:
http://arxiv.org/abs/2406.08217
Publikováno v:
Journal of Materials Research and Technology, Vol 33, Iss , Pp 7136-7146 (2024)
In recent decades, thanks to the advancements within materials science and engineering, a novel class of metallic compounds, named high and medium-entropy alloys, has begun to capture the attention of researchers worldwide. Despite their excellent me
Externí odkaz:
https://doaj.org/article/738fc9e64d6d47a292a088ca49df5d86
Developmental dysplasia of the hip (DDH) is a condition in infants where the femoral head is incorrectly located in the hip joint. We propose a deep learning algorithm for segmenting key structures within ultrasound images, employing this to calculat
Externí odkaz:
http://arxiv.org/abs/2211.04350
Autor:
Anca Magda VOICULESCU
Publikováno v:
Challenges of the Knowledge Society, Vol 17, Iss 1, Pp 348-358 (2024)
Council Regulation (EU) 2019/1111, recently entered into force, brought significant progress for EU Member States in the specific area of international child abductions. In the context of freedom of movement within the European Union guaranteed by ar
Externí odkaz:
https://doaj.org/article/9f19f0331571474096f4689a4b28b334
Autor:
Vladimir Potop, Liviu E. Mihailescu, Ion Mahaila, Monika Zawadka-Kunikowska, Wladyslaw Jagiello, Andrii Chernozub, Mihai – Sebastian Baican, Olivia Carmen Timnea, Carmen Ene-Voiculescu, Alexandru Ascinte
Publikováno v:
Physical Education of Students, Vol 28, Iss 2, Pp 106-119 (2024)
Background and Study Aim. Biomechanics is a fundamental component of Kinesiology, offering critical insights into the mechanics of human movement. As the demand for comprehensive educational programs in Kinesiology grows, understanding the role and e
Externí odkaz:
https://doaj.org/article/d7d323f3e2814558bcdb411fbc27adf4
Autor:
Wang, Ziyang, Voiculescu, Irina
Deep learning models, e.g. supervised Encoder-Decoder style networks, exhibit promising performance in medical image segmentation, but come with a high labelling cost. We propose TriSegNet, a semi-supervised semantic segmentation framework. It uses t
Externí odkaz:
http://arxiv.org/abs/2208.06303