Zobrazeno 1 - 10
of 494
pro vyhledávání: '"A. Pegios"'
Autor:
Olsen, Markus Ditlev Sjøgren, Ambsdorf, Jakob, Lin, Manxi, Taksøe-Vester, Caroline, Svendsen, Morten Bo Søndergaard, Christensen, Anders Nymark, Nielsen, Mads, Tolsgaard, Martin Grønnebæk, Feragen, Aasa, Pegios, Paraskevas
Congenital malformations of the brain are among the most common fetal abnormalities that impact fetal development. Previous anomaly detection methods on ultrasound images are based on supervised learning, rely on manual annotations, and risk missing
Externí odkaz:
http://arxiv.org/abs/2408.03654
Autor:
Pegios, Paraskevas, Lin, Manxi, Weng, Nina, Svendsen, Morten Bo Søndergaard, Bashir, Zahra, Bigdeli, Siavash, Christensen, Anders Nymark, Tolsgaard, Martin, Feragen, Aasa
Obstetric ultrasound image quality is crucial for accurate diagnosis and monitoring of fetal health. However, producing high-quality standard planes is difficult, influenced by the sonographer's expertise and factors like the maternal BMI or the fetu
Externí odkaz:
http://arxiv.org/abs/2403.08700
Autor:
Lin, Manxi, Ambsdorf, Jakob, Sejer, Emilie Pi Fogtmann, Bashir, Zahra, Wong, Chun Kit, Pegios, Paraskevas, Raheli, Alberto, Svendsen, Morten Bo Søndergaard, Nielsen, Mads, Tolsgaard, Martin Grønnebæk, Christensen, Anders Nymark, Feragen, Aasa
We introduce the notion of semantic image quality for applications where image quality relies on semantic requirements. Working in fetal ultrasound, where ranking is challenging and annotations are noisy, we design a robust coarse-to-fine model that
Externí odkaz:
http://arxiv.org/abs/2402.08294
Shortcut learning is when a model -- e.g. a cardiac disease classifier -- exploits correlations between the target label and a spurious shortcut feature, e.g. a pacemaker, to predict the target label based on the shortcut rather than real discriminat
Externí odkaz:
http://arxiv.org/abs/2312.14223
Autor:
Tsakyridis, A., Moralis-Pegios, M., Giamougiannis, G., Kirtas, M., Passalis, N., Tefas, A., Pleros, N.
The recent explosive compute growth, mainly fueled by the boost of AI and DNNs, is currently instigating the demand for a novel computing paradigm that can overcome the insurmountable barriers imposed by conventional electronic computing architecture
Externí odkaz:
http://arxiv.org/abs/2312.00037
We investigate the hypothetical X17 boson on neutron stars and Quark Stars (QSs) using various hadronic Equation of States (EoSs) with phenomenological or microscopic origin. Our aim is to set realistic constraints on its coupling constant and the ma
Externí odkaz:
http://arxiv.org/abs/2309.12469
Autor:
Moralis-Pegios, Miltiadis, Giamougiannis, George, Tsakyridis, Apostolos, Lazovsky, David, Pleros, Nikos
In recent years, there has been growing interest in using photonic technology to perform the underlying linear algebra operations required by different applications, including neuromorphic photonics, quantum computing and microwave processing, mainly
Externí odkaz:
http://arxiv.org/abs/2306.17728
Autor:
Petousis, Vlasios1 vlasios.petousis@cvut.cz, Kanakis-Pegios, Alkiviadis2 alkanaki@auth.gr, Moustakidis, Charalambos2 moustaki@auth.gr, Veselský, Martin1 Martin.Veselsky@cvut.cz, Leja, Jozef3 jozef.leja@stuba.sk
Publikováno v:
EPJ Web of Conferences. 10/8/2024, Vol. 304, p1-6. 6p.
Autor:
Divaris, Manolis1 edivar@auth.gr, Kanakis-Pegios, Alkiviadis1 alkanaki@auth.gr, Moustakidis, Charalampos1 moustaki@auth.gr
Publikováno v:
EPJ Web of Conferences. 10/8/2024, Vol. 304, p1-6. 6p.
Autor:
Miltiadis Moralis-Pegios, George Giamougiannis, Apostolos Tsakyridis, David Lazovsky, Nikos Pleros
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-8 (2024)
Abstract Recently there has been growing interest in using photonics to perform the linear algebra operations of neuromorphic and quantum computing applications, aiming at harnessing silicon photonics’ (SiPho) high-speed and energy-efficiency crede
Externí odkaz:
https://doaj.org/article/5ea069b234564b23bd33e27ec748f535