Zobrazeno 1 - 10
of 3 714
pro vyhledávání: '"Molchanova AS"'
Autor:
Spagnolo, Federico, Molchanova, Nataliia, Pineda, Mario Ocampo, Melie-Garcia, Lester, Cuadra, Meritxell Bach, Granziera, Cristina, Andrearczyk, Vincent, Depeursinge, Adrien
To date, several methods have been developed to explain deep learning algorithms for classification tasks. Recently, an adaptation of two of such methods has been proposed to generate instance-level explainable maps in a semantic segmentation scenari
Externí odkaz:
http://arxiv.org/abs/2409.03772
Autor:
Molchanova, Nataliia, Cagol, Alessandro, Gordaliza, Pedro M., Ocampo-Pineda, Mario, Lu, Po-Jui, Weigel, Matthias, Chen, Xinjie, Depeursinge, Adrien, Granziera, Cristina, Müller, Henning, Cuadra, Meritxell Bach
Uncertainty quantification (UQ) has become critical for evaluating the reliability of artificial intelligence systems, especially in medical image segmentation. This study addresses the interpretability of instance-wise uncertainty values in deep lea
Externí odkaz:
http://arxiv.org/abs/2407.05761
Autor:
Spagnolo, Federico, Molchanova, Nataliia, Schaer, Roger, Cuadra, Meritxell Bach, Pineda, Mario Ocampo, Melie-Garcia, Lester, Granziera, Cristina, Andrearczyk, Vincent, Depeursinge, Adrien
In recent years, explainable methods for artificial intelligence (XAI) have tried to reveal and describe models' decision mechanisms in the case of classification tasks. However, XAI for semantic segmentation and in particular for single instances ha
Externí odkaz:
http://arxiv.org/abs/2406.09335
Starting from a model of nonlinear magnetoelasticity where magnetization is defined in the Eulerian configuration while elastic deformation is in the Lagrangean one, we rigorously derive a linearized model that coincides with the standard one that al
Externí odkaz:
http://arxiv.org/abs/2401.09586
Autor:
Molchanova, Nataliia, Raina, Vatsal, Malinin, Andrey, La Rosa, Francesco, Depeursinge, Adrien, Gales, Mark, Granziera, Cristina, Muller, Henning, Graziani, Mara, Cuadra, Meritxell Bach
Publikováno v:
Computers in Biology and Medicine 184(2025)109336
This paper explores uncertainty quantification (UQ) as an indicator of the trustworthiness of automated deep-learning (DL) tools in the context of white matter lesion (WML) segmentation from magnetic resonance imaging (MRI) scans of multiple sclerosi
Externí odkaz:
http://arxiv.org/abs/2311.08931
Autor:
Tatyana Ya. Korchina, Vladimir I. Korchin, Elena P. Fedorova, Vladimir V. Dyachkov, Olga V. Grubii, Aleksey V. Ratiev, Tatyana P. Fomicheva, Zhanna I. Molchanova
Publikováno v:
Журнал медико-биологических исследований, Vol 12, Iss 4, Pp 466-474 (2024)
Taking into account the wide range of physiological effects of vitamin D on the human body and the dependence of its synthesis in the skin on insolation, it is of undoubted interest to study vitamin D status in various population groups in the Russia
Externí odkaz:
https://doaj.org/article/d4b3d75e6a3b41ff8022d87f50c04f4e
Autor:
V. V. Zotov, O. I. Molchanova
Publikováno v:
Цифровая социология, Vol 7, Iss 3, Pp 80-90 (2024)
Infographics are used to display information in a visual form with a graphic component, and have become widespread due to the convergence of the media space, which has transformed the processes of collecting, processing, broadcasting, and, most impor
Externí odkaz:
https://doaj.org/article/09354f5dcfb7435ba08b460c9960937d
Publikováno v:
Psihologo-Pedagogičeskie Issledovaniâ, Vol 16, Iss 3, Pp 52-68 (2024)
The article presents the results of a population study on the mental and physical development of preschool children using a standardized interdisciplinary diagnostic complex (State Registration Number 624012303596-7 dated January 23, 2024). The study
Externí odkaz:
https://doaj.org/article/9151b68b650a49809dce29f39e9e7adb
We present a new example for the Lavrentiev phenomenon in context of nonlinear elasticity, caused by an interplay of the elastic energy's resistance to infinite compression and the Ciarlet-Ne\v{c}as condition, a constraint preventing global interpene
Externí odkaz:
http://arxiv.org/abs/2309.08288
Autor:
Molchanova, Nataliia, Maréchal, Bénédicte, Thiran, Jean-Philippe, Kober, Tobias, Huelnhagen, Till, Richiardi, Jonas
With the rise of open data, identifiability of individuals based on 3D renderings obtained from routine structural magnetic resonance imaging (MRI) scans of the head has become a growing privacy concern. To protect subject privacy, several algorithms
Externí odkaz:
http://arxiv.org/abs/2305.16922