Search

Your search keyword '"José Dolz"' showing total 28 results
Start Over Author "José Dolz"
28 results on '"José Dolz"'

1. State-of-the-art retinal vessel segmentation with minimalistic models

Author

Adrian Galdran, André Anjos, José Dolz, Hadi Chakor, Hervé Lombaert, and Ismail Ben Ayed

Subjects
Medicine, Science
Abstract

Abstract The segmentation of retinal vasculature from eye fundus images is a fundamental task in retinal image analysis. Over recent years, increasingly complex approaches based on sophisticated Convolutional Neural Network architectures have been pushing performance on well-established benchmark datasets. In this paper, we take a step back and analyze the real need of such complexity. We first compile and review the performance of 20 different techniques on some popular databases, and we demonstrate that a minimalistic version of a standard U-Net with several orders of magnitude less parameters, carefully trained and rigorously evaluated, closely approximates the performance of current best techniques. We then show that a cascaded extension (W-Net) reaches outstanding performance on several popular datasets, still using orders of magnitude less learnable weights than any previously published work. Furthermore, we provide the most comprehensive cross-dataset performance analysis to date, involving up to 10 different databases. Our analysis demonstrates that the retinal vessel segmentation is far from solved when considering test images that differ substantially from the training data, and that this task represents an ideal scenario for the exploration of domain adaptation techniques. In this context, we experiment with a simple self-labeling strategy that enables moderate enhancement of cross-dataset performance, indicating that there is still much room for improvement in this area. Finally, we test our approach on Artery/Vein and vessel segmentation from OCTA imaging problems, where we again achieve results well-aligned with the state-of-the-art, at a fraction of the model complexity available in recent literature. Code to reproduce the results in this paper is released.

Published
2022
Full Text
View/download PDF

3. Undular Hydraulic Jump

Author

Oscar Castro-Orgaz, José Roldán, and José Dolz

Subjects
Flujo ondulatorio, Ondas de choque, Resalto hidráulico, Vórtice, Ocean engineering, TC1501-1800, Hydraulic engineering, TC1-978
Abstract

The transition from subcritical to supercritical flow when the inflow Froude number Fo is close to unity appears in the form of steady state waves called undular hydraulic jump. The characterization of the undular hydraulic jump is complex due to the existence of a non-hydrostatic pressure distribution that invalidates the gradually-varied flow theory, and supercritical shock waves. The objective of this work is to present a mathematical model for the undular hydraulic jump obtained from an approximate integration of the Reynolds equations for turbulent flow assuming that the Reynolds number R is high. Simple analytical solutions are presented to reveal the physics of the theory, and a numerical model is used to integrate the complete equations. The limit of application of the theory is discussed using a wave breaking condition for the inception of a surface roller. The validity of the mathematical predictions is critically assessed using physical data, thereby revealing aspects on which more research is needed

Published
2015
Full Text
View/download PDF

13. Experimental study of subcritical dividing flow in an equal-width four-branch junction

Author

Manuel Gómez, Juan Pomares, José Dolz, Leonardo S. Nanía, and Pau Comas

Subjects
Engineering, Civil, Aspect ratio, Astrophysics::High Energy Astrophysical Phenomena, Engineering, Multidisciplinary, Inflow, Astrophysics::Cosmology and Extragalactic Astrophysics, Physics::Fluid Dynamics, symbols.namesake, Froude number, Geotechnical engineering, Engineering, Ocean, Choked flow, Engineering, Aerospace, Engineering, Biomedical, Astrophysics::Galaxy Astrophysics, Water Science and Technology, Civil and Structural Engineering, Mathematics, Mechanical Engineering, Mechanics, Supercritical flow, Computer Science, Software Engineering, Engineering, Marine, Open-channel flow, Engineering, Manufacturing, Engineering, Mechanical, Engineering, Industrial, symbols, Outflow, Momentum-depth relationship in a rectangular channel
Abstract

An experimental study of the subcritical dividing flow in an equal-width, four-branch junction with two inflows and two outflows is presented. A brief description of the flow characteristics is given. From the analysis of test data, a linear relationship among five nondimensional parameters, including inflow ratio, outflow ratio, Froude number of inflow in one direction, outflow depth ratio, and outflow aspect ratio, is proposed and proven to successfully predict the flow distribution in the junction. It can be used to solve the dividing flow problem in a street junction, and it can be included as a part of a numerical model of a street network involving subcritical flows.

Published
2020

14. Plunge pool pressures due to a falling rectangular jet

Author

José Dolz and Jerónimo Puertas

Subjects
Jet (fluid), Engineering, Engineering, Civil, business.industry, Mechanical Engineering, Engineering, Multidisciplinary, Technical note, Stagnation point, Computer Science, Software Engineering, Engineering, Marine, Engineering, Manufacturing, Engineering, Mechanical, Laboratory test, Cushion, Engineering, Industrial, Geotechnical engineering, Engineering, Ocean, Plunge pool, Arch, Falling (sensation), business, Engineering, Aerospace, Engineering, Biomedical, Water Science and Technology, Civil and Structural Engineering
Abstract

This Technical Note presents the results of a large set of laboratory tests and tries to determine the conditions that ensure the existence of a water cushion that is not expelled by the impingement of a nappe (effective cushion). Second, values of mean dynamic pressures at the stagnation point of nonsymmetric plunge pools downstream of arch dams are assessed.

Published
2020

15. Surface stormwater hazard assessment in steep urban areas. case of the city of mendoza, argentina

Author

José Dolz, Leonardo S. Nanía, and Manuel Gómez

Subjects
Hydrology, Engineering, Civil, Geography, Planning and Development, Stormwater, Engineering, Multidisciplinary, Storm, Pedestrian, Hazard analysis, Computer Science, Software Engineering, Civil engineering, Hazard, Engineering, Marine, Engineering, Manufacturing, Engineering, Mechanical, Engineering, Industrial, Environmental science, Engineering, Ocean, Surface runoff, Engineering, Aerospace, Engineering, Biomedical, Water Science and Technology, Street network, Urban runoff
Abstract

The current paper focusses on the hazard assessment associated with urban runoff on streets. A review of the existing criteria to evaluate such a hazard is made. Two new criteria based on theoretical analysis of the water's force acting on a static pedestrian are presented: no slipping criterion and stability to tilt criterion. According to these criteria, either a maximum depth, or a maximum velocity or some relation between depths and velocities should be fulfilled in order to guarantee the pedestrian's and driver's safety in the case of medium to large storms. A one-dimensional numerical model is used to solve the urban storm runoff within a street network. This model is applied to an urban watershed of the city of Mendoza (Argentina), obtaining the runoff values belonging to return periods of 5, 10 and 25 years. The results are evaluated bearing in mind four hazard criteria. In conclusion, the numerical model is shown to be a useful tool in relation to the application of the hazards criteria. It is also conclude that an effort should be made to determine specific hazard criteria based on experimental data.

Published
2020

16. Experimental study of the dividing flow in steep street crossings

Author

Leonardo S. Nanía, José Dolz, and Manuel Gómez

Subjects
Hydrology, Engineering, Civil, Series (mathematics), Flow distribution, Engineering, Multidisciplinary, Geometry, Inflow, Street crossing, Computer Science, Software Engineering, Engineering, Marine, Physics::Fluid Dynamics, Engineering, Manufacturing, Engineering, Mechanical, Flow (mathematics), Power ratio, Engineering, Industrial, Engineering, Ocean, Scale model, Engineering, Aerospace, Engineering, Biomedical, Geology, Water Science and Technology, Civil and Structural Engineering, Street network
Abstract

A first approach to the experimental study of the dividing flow in steep street crossings is presented. A scale model of a street crossing has been built and a series of tests has been conducted for studying the flow pattern in the crossing when the flow in the streets is supercritical. It has been found that the inflow power ratio at the entrance of the crossing can be used as a non-dimensional parameter for predicting the flow distribution as well as the flow pattern. On the basis of these relationships a one-dimensional formulation can be developed in order to predict the dividing flow in crossings.

Published
2020

17. Thermal response of Sanabria lake to global change (NW Spain)

Author

Anaïs Ramos, Joan Armengol, José Dolz, Antonio Casasola, Alejandro Rodríguez-Martín, José Carlos Vega, Antoni Palau, Universitat Politècnica de Catalunya. Departament d'Enginyeria Civil i Ambiental, and Universitat Politècnica de Catalunya. FLUMEN - Dinàmica Fluvial i Enginyeria Hidrològica

Subjects
Engineering, Civil, Limnology--Spain--Sanabria Lake, Engineering, Multidisciplinary, Sanabria Lake, Aquatic Science, Vertical transfer, Engineering, Ocean, Engineering, Aerospace, Engineering, Biomedical, Global change, Water Science and Technology, Enginyeria civil::Geologia::Hidrologia [Àrees temàtiques de la UPC], Ecology, Stratification period, Thermal stability, Computer Science, Software Engineering, Engineering, Marine, Engineering, Manufacturing, Engineering, Mechanical, Geography, Water temperature, Limnologia -- Espanya, Engineering, Industrial, Humanities, Internal organization
Abstract

espanol?Pueden ser las grandes masas de agua sensores de cambio global? Como acumuladoras de agua y calor, algunas de sus caracteristicas termicas podrian verse alteradas por cambios hidrometeorologicos a medio y largo plazo y asi ser utilizadas como indicadoras de los efectos del cambio global sobre los ecosistemas fluviales. Este trabajo se centra en el estudio de la incidencia de cambio global (cambio climatico mas cambio de usos de agua y suelo) en la organizacion interna del lago de Sanabria, concretamente en su ciclo anual termico. Se estudia la existencia de tendencias temporales en el comportamiento termico del lago, donde se dispone de perfiles de temperatura del agua desde el ano 1986. Los analisis de datos incluyen las tecnicas estadisticas no parametricas del test de tendencia de Man-Kendall y la estimacion de pendiente de Sen para evaluar patrones estacionales y a largo plazo de variables hidrometeorologicas y termicas del lago. Los resultados principales indican que, sorprendentemente, el lago de Sanabria se esta enfriando globalmente, lo cual podria explicarse por un fortalecimiento de la termoclina y un descenso de la transferencia de calor al hipolimnion durante el periodo de estratificacion. Estos resultados contribuyen a entender y cuantificar la susceptibilidad de las masas de agua ibericas al cambio global EnglishAre large water bodies able to act as sensors of global change? As accumulators of water and heat, some of their thermal characteristics might be altered by long term (decadal) hydrometeorological changes and thus may be used as indicators of the effects of global change on fluvial ecosystems. This work focuses on the effect of global change (climate change plus water quantity and land use changes) in the internal organization of Sanabria Lake, specifically in its thermal annual cycle. The existence of temporal trends in the thermal behaviour of the lake was investigated based on the water temperature profiles that are available since 1986. Data analyses include the non-parametric Mann-Kendall trend test and the Sen slope estimate to evaluate long term and seasonal patterns of hydrometeorological and in-lake thermal variables. The main results surprisingly point to a net lake cooling that could be explained by a stronger thermocline and a weaker vertical transfer of heat to the hypolimnion during the stratification period. These results contribute to understand and quantify the effects of global change on Iberian freshwater bodies

Published
2020

18. Determining regional brain growth in premature and mature infants in relation to age at MRI using deep neural networks

Author

Farzad Beizaee, Michele Bona, Christian Desrosiers, Jose Dolz, and Gregory Lodygensky

Subjects
Medicine, Science
Abstract

Abstract Neonatal MRIs are used increasingly in preterm infants. However, it is not always feasible to analyze this data. Having a tool that assesses brain maturation during this period of extraordinary changes would be immensely helpful. Approaches based on deep learning approaches could solve this task since, once properly trained and validated, they can be used in practically any system and provide holistic quantitative information in a matter of minutes. However, one major deterrent for radiologists is that these tools are not easily interpretable. Indeed, it is important that structures driving the results be detailed and survive comparison to the available literature. To solve these challenges, we propose an interpretable pipeline based on deep learning to predict postmenstrual age at scan, a key measure for assessing neonatal brain development. For this purpose, we train a state-of-the-art deep neural network to segment the brain into 87 different regions using normal preterm and term infants from the dHCP study. We then extract informative features for brain age estimation using the segmented MRIs and predict the brain age at scan with a regression model. The proposed framework achieves a mean absolute error of 0.46 weeks to predict postmenstrual age at scan. While our model is based solely on structural T2-weighted images, the results are superior to recent, arguably more complex approaches. Furthermore, based on the extracted knowledge from the trained models, we found that frontal and parietal lobes are among the most important structures for neonatal brain age estimation.

Published
2023
Full Text
View/download PDF

21. Undular Hydraulic Jump

Author

José Dolz, Oscar Castro-Orgaz, and J. Roldán

Subjects
Shock waves, Vórtice, Undular flow, Resalto hidráulico, Ondas de choque, Flujo ondulatorio, Hydraulic jump, Vortex
Abstract

[ES] La transición de régimen supercrítico a régimen subcrítico cuando el número de Froude Fo aguas arriba esta próximo a la unidad da lugar a un tren de ondas estacionario llamado resalto hidráulico ondulatorio. La caracterización del resalto ondulatorio es muy compleja, debido a que el tren de ondas invalida la hipótesis de presión hidrostática usada en modelos de flujo gradualmente variado, y a otros fenómenos como las ondas de choque del flujo supercrítico. El objetivo de este trabajo es presentar un modelo para el resalto hidráulico ondulatorio obtenido de las ecuaciones de Reynolds para flujo turbulento, asumiendo que el número de Reynolds R es elevado. Se presentan soluciones analíticas sencillas para mostrar las características físicas de la teoría, así como un modelo numérico para la integración de las ecuaciones completas. El límite de aplicación de la teoría se discute en relación a la rotura de onda y formación de vórtices. La validez del modelo matemático es revisada de forma c, [EN] The transition from subcritical to supercritical flow when the inflow Froude number Fo is close to unity appears in the form of steady state waves called undular hydraulic jump. The characterization of the undular hydraulic jump is complex due to the existence of a non-hydrostatic pressure distribution that invalidates the gradually-varied flow theory, and supercritical shock waves. The objective of this work is to present a mathematical model for the undular hydraulic jump obtained from an approximate integration of the Reynolds equations for turbulent flow assuming that the Reynolds number R is high. Simple analytical solutions are presented to reveal the physics of the theory, and a numerical model is used to integrate the complete equations. The limit of application of the theory is discussed using a wave breaking condition for the inception of a surface roller. The validity of the mathematical predictions is critically assessed using physical data, thereby revealing aspects on whi

Published
2015

22. 'PRESSURE FLUCTUATIONS ON PLUNGE POOL FLOORS'

Author

Luis G. Castillo, Jerónimo Puertas, and José Dolz

Subjects
Geotechnical engineering, Plunge pool, Geology, Water Science and Technology, Civil and Structural Engineering
Abstract

(1999). “PRESSURE FLUCTUATIONS ON PLUNGE POOL FLOORS”. Journal of Hydraulic Research: Vol. 37, No. 2, pp. 272-288.

Published
1999
Full Text
View/download PDF

25. Experimental and numerical modelling of symmetrical four-branch supercritical cross junction flow

Author

Arturo S. Leon, Manuel Gómez, José Dolz, and Leonardo S. Nanía

Subjects
Work (thermodynamics), Flow (mathematics), Mechanics, GeneralLiterature_MISCELLANEOUS, Supercritical fluid, Water Science and Technology, Civil and Structural Engineering, Mathematics
Abstract

The discussers congratulate the authors for their work and would like to raise some questions and comments about their results and statements. The paper compares (i) the computed with the measured ...

Published
2010
Full Text
View/download PDF

27. Using Deep Convolutional Neural Networks for Neonatal Brain Image Segmentation

Author

Yang Ding, Rolando Acosta, Vicente Enguix, Sabrina Suffren, Janosch Ortmann, David Luck, Jose Dolz, and Gregory A. Lodygensky

Subjects
neonatal brain, brain segmentation, machine learning (artificial intelligence), convolutional neural network, T2-weighed MRI, Neurosciences. Biological psychiatry. Neuropsychiatry, RC321-571
Abstract

IntroductionDeep learning neural networks are especially potent at dealing with structured data, such as images and volumes. Both modified LiviaNET and HyperDense-Net performed well at a prior competition segmenting 6-month-old infant magnetic resonance images, but neonatal cerebral tissue type identification is challenging given its uniquely inverted tissue contrasts. The current study aims to evaluate the two architectures to segment neonatal brain tissue types at term equivalent age.MethodsBoth networks were retrained over 24 pairs of neonatal T1 and T2 data from the Developing Human Connectome Project public data set and validated on another eight pairs against ground truth. We then reported the best-performing model from training and its performance by computing the Dice similarity coefficient (DSC) for each tissue type against eight test subjects.ResultsDuring the testing phase, among the segmentation approaches tested, the dual-modality HyperDense-Net achieved the best statistically significantly test mean DSC values, obtaining 0.94/0.95/0.92 for the tissue types and took 80 h to train and 10 min to segment, including preprocessing. The single-modality LiviaNET was better at processing T2-weighted images than processing T1-weighted images across all tissue types, achieving mean DSC values of 0.90/0.90/0.88 for gray matter, white matter, and cerebrospinal fluid, respectively, while requiring 30 h to train and 8 min to segment each brain, including preprocessing.DiscussionOur evaluation demonstrates that both neural networks can segment neonatal brains, achieving previously reported performance. Both networks will be continuously retrained over an increasingly larger repertoire of neonatal brain data and be made available through the Canadian Neonatal Brain Platform to better serve the neonatal brain imaging research community.

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results