|
1.
|
|
12 p, 4.0 MB |
Domain generalization in deep learning for contrast-enhanced imaging
/
Sendra-Balcells, C. (Universitat de Barcelona) ;
Campello, Victor M (Universitat de Barcelona) ;
Martín-Isla, C. (Universitat de Barcelona) ;
Viladés Medel, David (Institut d'Investigació Biomèdica Sant Pau) ;
Descalzo, Martin (Institut d'Investigació Biomèdica Sant Pau) ;
Guala, Andrea (Hospital Universitari Vall d'Hebron) ;
Rodriguez-Palomares, Jose F (Hospital Universitari Vall d'Hebron) ;
Lekadir, K. (Universitat de Barcelona) ;
Universitat Autònoma de Barcelona
The domain generalization problem has been widely investigated in deep learning for non-contrast imaging over the last years, but it received limited attention for contrast-enhanced imaging. However, there are marked differences in contrast imaging protocols across clinical centers, in particular in the time between contrast injection and image acquisition, while access to multi-center contrast-enhanced image data is limited compared to available datasets for non-contrast imaging. [...]
2022 -  10.1016/j.compbiomed.2022.106052
Computers in Biology and Medicine, Vol. 149 (october 2022) , p. 106052
|
|
|
2.
|
|
13 p, 2.2 MB |
Reinforcement learning in videogames
/
Villar Casino, Raúl ;
Casas Roma, Jordi, dir. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació) ;
Universitat Autònoma de Barcelona.
Escola d'Enginyeria
This work aims to delve into the main Reinforcement Learning (RL) models and explore their potential in environments of varying complexity. As a starting point, an exhaustive review of the state-of-the-art was conducted, covering both tabular methods (Q-Learning, Value Iteration, Monte Carlo) and Deep RL (Deep Q-Learning, PPO). [...]
Aquest treball pretén aprofundir en els principals models d'aprenentatge per reforç (RL) i explorar el seu potencial en entorns de diversa complexitat. Com a punt de partida, es va realitzar una revisió exhaustiva de l'estat de l'art, abastant tant mètodes tabulars (Q-Learning, Value Iteration, MonteCarlo) com Deep RL (Deep Q-Learning, PPO). [...]
Este trabajo tiene como objetivo profundizar en los principales modelos de Aprendizaje por Refuerzo (RL) y explorar su potencial en entornos de diversa complejidad. Como punto de partida, se realizó una revisión exhaustiva del estado del arte, abarcando tanto métodos tabulares (Q-Learning, Iteración de Valores, Monte Carlo) como Aprendizaje por Refuerzo Profundo (Deep Q-Learning, PPO). [...]
2024
Enginyeria Informàtica [958]
|
|
|
3.
|
|
23 p, 7.8 MB |
Deep learning applications in single-cell genomics and transcriptomics data analysis
/
Erfanian, Nafiseh (Birjand University of Medical Sciences, Birjand, Iran) ;
Heydari, A.Ali (University of California, USA) ;
Feriz, Adib Miraki (Birjand University of Medical Sciences, Birjand, Iran) ;
Iañez, Pablo (Institut Germans Trias i Pujol. Institut de Recerca contra la Leucèmia Josep Carreras) ;
Derakhshani, Afshin (University of Calgary, Canada) ;
Ghasemigol, Mohammad (University of North Dakota, USA) ;
Farahpour, Mohsen (University of Birjand, Iran) ;
Razavi, Seyyed Mohammad (University of Birjand, Iran) ;
Nasseri, Saeed (Birjand University of Medical Sciences, Iran) ;
Safarpour, Hossein (Birjand University of Medical Sciences, Iran) ;
Sahebkar, Amirhossein (Mashhad University of Medical Sciences, Mashhad, Iran)
Traditional bulk sequencing methods are limited to measuring the average signal in a group of cells, potentially masking heterogeneity, and rare populations. The single-cell resolution, however, enhances our understanding of complex biological systems and diseases, such as cancer, the immune system, and chronic diseases. [...]
2023 - 10.1016/j.biopha.2023.115077
Biomedicine & pharmacotherapy, Vol. 165 (september 2023)
|
|
|
4.
|
|
15 p, 3.5 MB |
A Scalable Reduced-Complexity Compression of Hyperspectral Remote Sensing Images Using Deep Learning
/
Mijares i Verdú, Sebastià (Universitat Autònoma de Barcelona. Departament d'Enginyeria de la Informació i de les Comunicacions) ;
Ballé, Johannes (Google Research) ;
Laparra, Valero (Universitat de Valencia. Laboratori de Processament d'imatges) ;
Bartrina Rapesta, Joan (Universitat Autònoma de Barcelona. Departament d'Enginyeria de la Informació i de les Comunicacions) ;
Hernández-Cabronero, Miguel (Universitat Autònoma de Barcelona. Departament d'Enginyeria de la Informació i de les Comunicacions) ;
Serra Sagristà, Joan (Universitat Autònoma de Barcelona. Departament d'Enginyeria de la Informació i de les Comunicacions)
Two key hurdles to the adoption of Machine Learning (ML) techniques in hyperspectral data compression are computational complexity and scalability for large numbers of bands. These are due to the limited computing capacity available in remote sensing platforms and the high computational cost of compression algorithms for hyperspectral data, especially when the number of bands is large. [...]
2023 - 10.3390/rs15184422
Remote sensing (Basel), Vol. 15, Issue 18 (September 2023) , art. 4422
|
|
|
5.
|
|
25 p, 6.4 MB |
Intelligent Control of Wastewater Treatment Plants Based on Model-Free Deep Reinforcement Learning
/
Aponte-Rengifo, Oscar (Universidad de Salamanca. Departamento de Informática y Automática) ;
Francisco, Mario (Universidad de Salamanca. Departamento de Informática y Automática) ;
Vilanova i Arbós, Ramon (Universitat Autònoma de Barcelona. Departament de Telecomunicació i Enginyeria de Sistemes) ;
Vega, Pastora (Universidad de Salamanca. Departamento de Informática y Automática) ;
Revollar, Silvana (Universidad de Salamanca. Departamento de Informática y Automática)
In this work, deep reinforcement learning methodology takes advantage of transfer learning methodology to achieve a reasonable trade-off between environmental impact and operating costs in the activated sludge process of Wastewater treatment plants (WWTPs). [...]
2023 - 10.3390/pr11082269
Processes, Vol. 11, Issue 8 (August 2023) , art. 2269
|
|
|
6.
|
|
55 p, 707.1 KB |
Advances in the Use of Deep Learning for the Analysis of Magnetic Resonance Image in Neuro-Oncology
/
Pitarch, Carla (Universitat Politècnica de Catalunya. Departament d'Informàtica) ;
Ungan, Gulnur Semahat (Universitat Autònoma de Barcelona. Departament de Bioquímica i de Biologia Molecular) ;
Julià Sapé, Ma. Margarita (Universitat Autònoma de Barcelona. Institut de Biotecnologia i de Biomedicina "Vicent Villar Palasí") ;
Vellido, Alfredo (Universitat Politècnica de Catalunya. Departament d'Informàtica)
Machine Learning is entering a phase of maturity, but its medical applications still lag behind in terms of practical use. The field of oncological radiology (and neuro-oncology in particular) is at the forefront of these developments, now boosted by the success of Deep-Learning methods for the analysis of medical images. [...]
2024 - 10.3390/cancers16020300
Cancers, Vol. 16, Issue 2 (January 2024) , art. 300
|
|
|
7.
|
|
17 p, 5.2 MB |
3D Apple Detection from Large Point Clouds Using Deep Learning
/
Arpaci, Berkay ;
Ruiz Hidalgo, Javier, dir. (Universitat Politècnica de Catalunya) ;
Gené-Mola, Jordi, dir. (IRTA - Institute of Agrifood Research and Technology) ;
Universitat Autònoma de Barcelona.
Escola d'Enginyeria ;
Universitat Autònoma de Barcelona.
Departament de Ciències de la Computació
In this work, the 3D deep learning object detection model, PointRCNN, is evaluated for apples detection. Point clouds obtained from two different methods, LiDAR and photogrammetry, and a combination of the data obtained from them are used to see the effect of positional accuracy, cloud density and the effect of additional parameters such as color and reflectance. [...]
En aquest treball s'avalua l'ús de xarxa neuronal 3D PointRCNN per la detecció de pomes. La base de dades utilitzada inclou núvols de punts obtinguts amb dos mètodes diferents, LiDAR i fotogrametria, i la combinació d'aquestes dades per avaluar l'efecte de l'exactitud posicional, la densitat dels núvols i altres paràmetres addicionals com el color i la reflectància. [...]
2023
Màster Universitari en Visió per Computador/Computer Vision [1172]
|
|
|
8.
|
|
9 p, 1.3 MB |
Longitudinal deep learning clustering of Type 2 Diabetes Mellitus trajectories using routinely collected health records
/
Manzini, Enrico (Institut de Recerca Sant Joan de Déu) ;
Vlacho, Bogdan (DAP-Cat Group. Unitat de Suport a la Recerca. Fundaciò Institut Universitari per a la recerca a l'Atenciò Primària de Salut Jordi Gol i Gurina (IDIAPJGol)) ;
Franch-Nadal, Josep (Primary Health Care Center Raval Sud. Institut Català de la Salut) ;
Escudero, J. (Grupo Pulso) ;
Génova, A. (Grupo Pulso) ;
Reixach, Elisenda (Fundació TIC Salut Social. Departament de Salut. Generalitat de Catalunya) ;
Andrés, E. (Fundació TIC Salut Social. Departament de Salut. Generalitat de Catalunya) ;
Pizarro, I. (Novo Nordisk) ;
Portero, J.L. (Novo Nordisk) ;
Mauricio Puente, Dídac (Institut d'Investigació Biomèdica Sant Pau) ;
Perera Lluna, Alexandre (Institut de Recerca Sant Joan de Déu)
Type 2 diabetes mellitus (T2DM) is a highly heterogeneous chronic disease with different pathophysiological and genetic characteristics affecting its progression, associated complications and response to therapies. [...]
2022 - 10.1016/j.jbi.2022.104218
Journal of Biomedical Informatics, Vol. 135 (november 2022) , p. 104218
|
|
|
9.
|
|
19 p, 5.8 MB |
Deep Learning Analyses to Delineate the Molecular Remodeling Process after Myocardial Infarction
/
Iborra Egea, Oriol (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Gálvez-Montón, Carolina (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Prat-Vidal, Cristina (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Rudilla, F (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Soler-Botija, Carolina (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Revuelta-López, Elena (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Ferrer-Curriu, Gemma (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Segú-Vergés, Cristina (Anaxomics Biotech S.L.) ;
Mellado-Bergillos, Araceli (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Gomez-Puchades, Pol (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Gastelurrutia, Paloma (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Bayés-Genís, Antoni (Institut Germans Trias i Pujol. Hospital Universitari Germans Trias i Pujol) ;
Universitat Autònoma de Barcelona
Specific proteins and processes have been identified in post-myocardial infarction (MI) pathological remodeling, but a comprehensive understanding of the complete molecular evolution is lacking. We generated microarray data from swine heart biopsies at baseline and 6, 30, and 45 days after infarction to feed machine-learning algorithms. [...]
2021 - 10.3390/cells10123268
Cells, Vol. 10 (november 2021)
|
|
|
10.
|
|
20 p, 1.7 MB |
Tracking Therapy Response in Glioblastoma Using 1D Convolutional Neural Networks
/
Ortega-Martorell, Sandra (Liverpool John Moores University) ;
Olier, Iván (Liverpool John Moores University) ;
Hernandez, Orlando (Escuela Colombiana de Ingeniería Julio Garavito) ;
Restrepo-Galvis, Paula D. (Escuela Colombiana de Ingeniería Julio Garavito) ;
Bellfield, Ryan A. A. (Liverpool John Moores University) ;
Candiota Silveira, Ana Paula (Universitat Autònoma de Barcelona. Departament de Bioquímica i de Biologia Molecular)
Glioblastoma (GB) is a malignant brain tumour with no cure, even after the best treatment. The evaluation of a therapy response is usually based on magnetic resonance imaging (MRI), but it lacks precision in early stages, and doctors must wait several weeks until they are confident information is produced, facing an uncertain time window. [...]
2023 - 10.3390/cancers15154002
Cancers, Vol. 15, Num. 15 (August 2023) , art. 4002
|
|
guest ::
email alert
or subscribe to the 
RSS feed.
