Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 8
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Uninformed Teacher-Student for hard-samples distillation in weakly supervised mitosis localization

  • Fernández-Martín, Claudio
  • Silva-Rodríguez, Julio
  • Kiraz, Umay
  • Janssen, Emiel A.M.
  • Morales, Sandra|||0000-0003-0763-1545
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Background and Objective: Mitotic activity is a crucial biomarker for diagnosing and predicting outcomes for different types of cancers, particularly breast cancer. However, manual mitosis counting is challenging and time-consuming for pathologists, with moderate reproducibility due to biopsy slide size, low mitotic cell density, and pattern heterogeneity. In recent years, deep learning methods based on convolutional neural networks (CNNs) have been proposed to address these limitations. Nonetheless, these methods have been hampered by the available data labels, which usually consist only of the centroids of mitosis, and by the incoming noise from annotated hard negatives. As a result, complex algorithms with multiple stages are often required to refine the labels at the pixel level and reduce the number of false positives. Methods: This article presents a novel weakly supervised approach for mitosis detection that utilizes only image-level labels on histological hematoxylin and eosin (H&E) images, avoiding the need for complex labeling scenarios. Also, an Uninformed Teacher-Student (UTS) pipeline is introduced to detect and distill hard samples by comparing weakly supervised localizations and the annotated centroids, using strong augmentations to enhance uncertainty. Additionally, an automatic proliferation score is proposed that mimicks the pathologist-annotated mitotic activity index (MAI). The proposed approach is evaluated on three publicly available datasets for mitosis detection on breast histology samples, and two datasets for mitotic activity counting in whole-slide images. Results: The proposed framework achieves competitive performance with relevant prior literature in all the datasets used for evaluation without explicitly using the mitosis location information during training. This approach challenges previous methods that rely on strong mitosis location information and multiple stages to refine false positives. Furthermore, the proposed pipeline for hard-sample distillation demonstrates promising dataset-specific improvements. Concretely, when the annotation has not been thoroughly refined by multiple pathologists, the UTS model offers improvements of up to in mitosis localization, thanks to the detection and distillation of uncertain cases. Concerning the mitosis counting task, the proposed automatic proliferation score shows a moderate positive correlation with the MAI annotated by pathologists at the biopsy level on two external datasets. Conclusions: The proposed Uninformed Teacher-Student pipeline leverages strong augmentations to distill uncertain samples and measure dissimilarities between predicted and annotated mitosis. Results demonstrate the feasibility of the weakly supervised approach and highlight its potential as an objective evaluation tool for tumor proliferation., This work was funded by the Horizon 2020 European Union research and innovation programme under the Marie Sklodowska Curie grant agreement No 860627 (CLARIFY Project) . The work of Sandra Morales has been co-funded by the Universitat Politecnica de Valencia, Spain through the program PAID-10-20. The work of J. Silva-Rodriguez was carried out during his previous position at Universitat Politecnica de Valencia. This work was partially funded by Generalitat Valenciana through project CIPROM/2022/20 and with Ayuda a Primeros Proyectos de Investigacion (PAID-06-23) , Vicerrectorado de Investigacion of the Universitat Politecnica de Valencia. Funding for open access charge: Universitat Politecnica de Valencia (PAID-12-23).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Genetic Dissection of ToLCNDV Resistance in Resistant Sources of Cucumis melo

  • Pérez-Moro, Clara
  • Sáez, Cristina
  • Dhillon, Narinder P. S.
  • Sifres Cuerda, Alicia Gemma|||0000-0002-9498-0083
  • López Del Rincón, Carmelo|||0000-0001-7459-1315
  • Picó Sirvent, María Belén|||0000-0001-7761-990X
  • Pérez De Castro, Ana María|||0000-0002-4949-3323
[EN] Tomato leaf curl New Delhi virus (ToLCNDV) is a begomovirus causing significant melon (Cucumis melo) crop losses globally. This study aims to map the ToLCNDV resistance in the PI 414723 melon accession, previously identified and characterized through phenotypic studies, thereby exploring shared genomic regions with the established resistant source WM-7. In the present study, WM-7 and PI 414723 were crossed with the susceptible accessions 'Rochet' and 'Blanco' respectively, to generate F-1 hybrids. These hybrids were self-pollinated to generate the populations for mapping the ToLCNDV resistance region and designing markers for marker-assisted selection. Disease evaluation included visual symptom scoring, viral-load quantification and tissue printing. Genotyping-by-sequencing and SNP markers were used for quantitative trait loci (QTL) mapping. For genetic analysis, qPCR and bulked segregant RNA-seq (BSR-seq) were performed. Gene expression was assessed using RNA-seq, and qRT-PCR was used for confirmation. The research narrows the candidate region for resistance in WM-7 and identifies overlapping QTLs on chromosome 11 in PI 414723, found in the region of the DNA primase large subunit. BSR-seq and expression analyses highlight potential regulatory roles of chromosome 2 in conferring resistance. Differential expression was confirmed for six genes in the candidate region on chromosome 2. This study confirms the existence of common resistance genes in PI 414723 and WM-7., This work was supported by the grant PID2021-125787OR-C33, funded by MICIU/AEI/10.13039/501100011033; the 'FEDER UE' PROMETEO/2021/072 project for excellence groups Conselleria d'Educacio, Cultura, Universitats i Ocupacio (Generalitat Valenciana, Spain); and project RTC-2017-6023-2, funded MICIU/AEI/10.13039/501100011033 and by FEDER 'A way of making Europe'. C.S. was the recipient of a 'Margarita Salas' grant (MS/60) from the Requalification Program for Excellence of the Universitat Politecnica de Valencia, Spanish Ministry of Universities and European Union-Next Generation EU. C.P.M. is a recipient of the predoctoral fellowship "Programa de Ayudas de Investigacion y Desarrollo (PAID-01-19)" from Universitat Politecnica de Valencia. Funding for open access charge: Universitat Politecnica de Valencia (PAID-12-23).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Bridges over the River Turia: Genesis of the Urban History of Valencia

  • Durá-Aras, María-Montiel
  • Gielen, Eric|||0000-0002-4591-2914
  • Palencia-Jiménez, José-Sergio|||0000-0002-9587-7379
  • Miralles García, José Luis|||0000-0001-5638-2608
[EN] The foundation of the city of Valencia was created by the Romans on an island formed by the River Turia, strategically located between Carthago Nova (Cartagena) and Tarraco (Tarragona), and is directly connected to the sea. This raises the question of how the elements of access to the city came about and how the river and its bridges might have affected its evolution. This article delves into the study of the origins of the city, with a time frame that extends into the 11th century, the time at which an event took place that confirms one of the major changes in the city¿s urban morphology: when it stopped being an island. The intrinsic relationship that exists between bridges and main communication routes as fundamental elements to the access of an island is the driving force behind this article, which is based on research, until now undone, on the existence and construction of the first bridges in the city of Valencia and their influence on the city¿s subsequent development. This paper will start by studying the founding and location of this city and will then analyze the communication routes existing at the time. It will also study the communication routes that were created later and how all of them were forced to cross a fluvial accident, the River Turia. For this purpose, the number of bridges built until the city ceased to be an island have been identified, and analyses of their typology, location and who was responsible for them has been carried out to study how they may have affected the normal flow and evolution of the riverbed and their possible influence on the city¿s development., This research was funded by Universitat Politècnica de València.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

3D Point Cloud and GIS Approach to Assess Street Physical Attributes

  • Orozco-Carpio, Patricio Rodrigo|||0009-0007-3437-7390
  • Viñals, Mª José|||0000-0002-7589-7815
  • López González, María Concepción|||0000-0001-7542-3559
[EN] The present research explores an innovative approach to objectively assessing urban streets attributes using 3D point clouds and Geographic Information Systems (GIS). Urban streets are vital components of cities, playing a significant role in the lives of their residents. Usually, the evaluation of some of their physical attributes has been subjective, but this study leverages 3D point clouds and digital terrain models (DTM) to provide a more objective perspective. This article undertakes a microurban analysis of basic physical characteristics (slope, width, and human scale) of a representative street in the historic centre of Valencia (Spain), utilizing 3D laser-scanned point clouds and GIS tools. Applying the proposed methodology, thematic maps were generated, facilitating the objective identification of areas with physical attributes more conducive to suitable pedestrian dynamics. This approach provides a comprehensive understanding of urban street attributes, emphasizing the importance of addressing their assessment through advanced digital technologies. Moreover, this versatile methodology has diverse applications, contributing to social sustainability by enhancing the quality of urban streets and open spaces., This research was funded by the project "Analysis and Development of HBIM Integration into GIS for Creating a Cultural Heritage Tourism Planning Protocol" (ref. PID2020-119088RB-I00), funded by the Ministry of Science and Innovation, Government of Spain, and the "Programa de Ayudas de Investigacion y Desarrollo (PAID-01-22)" by the Universitat Politecnica de Valencia. The APC will be funded by Universitat Politecnica de Valencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Vector Field Heterogeneity for the Assessment of Locally Disorganised Cardiac Electrical Propagation Wavefronts From High-Density Multielectrodes

  • Pancorbo, Lucía
  • Ruiperez-Campillo, Samuel
  • Tormos, Álvaro
  • Cervigón, Raquel
  • Alberola, Antonio
  • Chorro, Francisco Javier
  • Guill Ibáñez, Antonio|||0000-0001-8546-264X
  • Millet Roig, José|||0000-0002-8879-003X
  • Castells, Francisco|||0000-0001-5044-3545
[EN] High-density multielectrode catheters are becoming increasingly popular in cardiac electrophysiology for advanced characterisation of the cardiac tissue, due to their potential to identify impaired sites. These are often characterised by abnormal electrical conduction, which may cause locally disorganised propagation wavefronts. To quantify it, a novel heterogeneity parameter based on vector field analysis is proposed, utilising finite differences to measure direction changes between adjacent cliques. The proposed Vector Field Heterogeneity metric has been evaluated on a set of simulations with controlled levels of organisation in vector maps, and a variety of grid sizes. Furthermore, it has been tested on animal experimental models of isolated Langendorff-perfused rabbit hearts. The proposed parameter exhibited superior capturing ability of heterogeneous propagation wavefronts compared to the classical Spatial Inhomogeneity Index, and simulations proved that the metric effectively captures gradual increments in disorganisation in propagation patterns. Notably, it yielded robust and consistent outcomes for $\mathbf {4\times 4}$ grid sizes, underscoring its suitability for the latest generation of orientation-independent cardiac catheters., This work was supported in part by the National Research Program, Ministerio de Ciencia e Innovación, Spanish Government under Grants PID2019- 109547RB-I00 and PID2022-142514OB-I00, and in part by Instituto de Salud Carlos II under Grant CIBERCV CB16/11/00486.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Analysis of the Current Status of Sensors and HBIM Integration: A Review Based on Bibliometric Analysis

  • Cornélio Vieira de Souza Rolim, Renan|||0000-0002-5963-9453
  • López González, María Concepción|||0000-0001-7542-3559
  • Viñals, Mª José|||0000-0002-7589-7815
[EN] This article presents a bibliometric analysis conducted on the implementation of sensor extracted data in the context of Historical Building Information Modeling (HBIM) with a focus on the conservation of heritage buildings. The study utilized recognized databases, namely, Web of Science (WoS) and Scopus. A bibliometric analysis methodology was applied, employing the VOSviewer 1.6.19 software. The results obtained provide a robust overview of the current state and trends in HBIM and sensor research and enabled the identification of emerging trends in the field of preventive conservation. Three promising trends were identified, establishing connections between this field and 4D spatial data management, energy performance, and artificial intelligence. Additionally, relations with climate change were also detected. These trends underscore a significant convergence of technologies and methodologies in the realm of heritage building conservation. The conclusions serve as a valuable contribution to guiding future research in the field of built heritage conservation., This research was conducted through the research project "Analysis and development of the integration of HBIM in GIS for the creation of a protocol for cultural heritage tourism planning"(ref. PID2020-119088RB-I00), funded by the Ministry of Science and Innovation, Government of Spain and the FPU grant (ref. FPU21/06469) funded by the Ministry of Universities, Government of Spain. The APC will be funded by the Universitat Politecnica de Valencia.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Evaluating the performance of spectral indices and meteorological variables as indicators of live fuel moisture content in Mediterranean shrublands

  • Arcos-Villacís, María Alicia
  • Balaguer-Beser, Ángel|||0000-0003-0039-2641
  • Ruiz Fernández, Luis Ángel|||0000-0003-0073-7259
[EN] This article presents a methodology to estimate the live fuel moisture content (LFMC), a critical factor in the spread of forest fires, through machine learning tools. Random forest models were trained using field LFMC samples collected bi-weekly for 18 consecutive months in 43 shrubland plots in the Valencian region, a Mediterranean zone in eastern Spain. LFMC predictions were obtained for the weighted average of LFMC values, calculated using the Fraction of Canopy Cover (FCC) of dominant species as weights. Furthermore, a specific model was defined for predicting LFMC for the Rosmarinus officinalis species. A Forward Feature Selection (FFS) with a Leave-Location-Out Cross Validation (LLOCV) method was used to select predictors extracted from a spatiotemporal data set, which includes different spectral indices obtained from Sentinel-2 imagery and meteorological variables obtained from measurements at weather stations, along with other seasonal, geographical or topographic variables. Model predictions were validated with a LLOCV procedure, and also using independent field measurements of LFMC in another period with changes in the precipitation regime and average temperatures. Variables selected by FFS for the two LFMC models were: the cumulative precipitation in the previous 60 days (p60), the average of the daily mean temperature in the previous 60 days (t60), together with the Y-UTM coordinate and the sine and cosine of the day of the year. LFMC predictions for the weighted average of LFMC values also introduced the Transformed Chlorophyll Absorption Ratio Index (TCARI), resulting in an R2 of 68.1%. However, LFMC for the Rosmarinus officinalis species used the ratio between TCARI and the Optimized SoilAdjusted Vegetation Index (OSAVI), in addition to the average daily minimum relative humidity in the 15 days prior to the date considered (R2 = 74.9 %). LFMC time series analysis showed that the general trend of LFMC measures is satisfactorily captured by the predictions. Spatial and temporal variations in LFMC were analyzed throughout thematic maps in the studied area during the wildfire season., Ma Alicia Arcos gives thanks for the help received by the Universitat Politecnica de Valencia through a pre-doctoral contract financed in the call, PAID-01-19, subprogram 1, and the open access charge: Universitat Politecnica de Valencia (PAID-12-23) . This research was funded by through a collaboration agreement between the company Red Electrica de Espana S.A.U. and the Universitat Politecnica de Valencia (2020-2023) , as well as the research project PID2020-117808RB-C21 funded by MCIN/AEI/10.13039/501100011033 and by ESF Investing in your future.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Mapping the organizational socialization and onboarding literature: a bibliometric analysis of the field

  • Didion, Eva
  • Ambrosius, Ute
  • Perello-Marin, M Rosario|||0000-0001-9183-0568
  • Catalá-Pérez, Daniel|||0000-0001-5042-0239
[EN] This study provides a comprehensive review of the intellectual structure and current dynamics of onboarding and socialization research. Using the Web of Science (WoS) database, we found 452 research articles that met the inclusion criteria. Biblioshiny R-package and VOSviewer were used for the bibliometric analysis. We lay out the most prolific authors, journals, institutions and articles in this rapidly growing field. We find that current research is scattered all over different topics and disciplines. We identify five research fronts that authors have pursued in the last 5¿years. Researchers have focused on: psychological contracts; the role of networks and relationship building; the changing work contexts in which organizational socialization takes place; the effects of newcomer proactivity and interactions with supervisors; onboarding in distinct areas like software engineering. Promising research avenues in this field can be distinguished in: different groups of newcomers; examining interactive effects between newcomers and socialization agents; and analyzing the evolving area of digital and virtual onboarding and organizational socialization.