References of "Marée, Raphaël"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailCollaborative analysis of multi-gigapixel imaging data using Cytomine
Marée, Raphaël ULg; Rollus, Loïc; Stévens, Benjamin et al

in Bioinformatics (2016)

Motivation: Collaborative analysis of massive imaging datasets is essential to enable scientific discoveries. Results: We developed Cytomine to foster active and distributed collaboration of ... [more ▼]

Motivation: Collaborative analysis of massive imaging datasets is essential to enable scientific discoveries. Results: We developed Cytomine to foster active and distributed collaboration of multidisciplinary teams for large-scale image-based studies. It uses web development methodologies and machine learning in order to readily organize, explore, share, and analyze (semantically and quantitatively) multi-gigapixel imaging data over the internet. We illustrate how it has been used in several biomedical applications. Availability: Cytomine (http://www.cytomine.be/) is freely available under an open-source license from http://github.com/cytomine/. A documentation wiki (http://doc.cytomine.be) and a demo server (http://demo.cytomine.be) are also available. [less ▲]

Detailed reference viewed: 128 (24 ULg)
Full Text
Peer Reviewed
See detailAn approach for detection of glomeruli in multisite digital pathology
Marée, Raphaël ULg; Olivo-Marin, Jean-Christophe; Meas-Yedid, Vannary

in Proceedings International Symposium on Biomedical Imaging (2016)

We present a novel bioimage informatics workflow that combines Icy and Cytomine software and their algorithms to enable large-scale analysis of digital slides from multiple sites. In particular, we apply ... [more ▼]

We present a novel bioimage informatics workflow that combines Icy and Cytomine software and their algorithms to enable large-scale analysis of digital slides from multiple sites. In particular, we apply this workflow on renal biopsies and evaluate empirically our approach for the automatic detection of glomeruli in hundreds of tissue sections. [less ▲]

Detailed reference viewed: 76 (8 ULg)
Full Text
Peer Reviewed
See detailTowards Generic Image Classification using Tree-based Learning: an Extensive Empirical Study
Marée, Raphaël ULg; Geurts, Pierre ULg; Wehenkel, Louis ULg

in Pattern Recognition Letters (2016)

This paper considers the general problem of image classification without using any prior knowledge about image classes. We study variants of a method based on supervised learning whose common steps are ... [more ▼]

This paper considers the general problem of image classification without using any prior knowledge about image classes. We study variants of a method based on supervised learning whose common steps are the extraction of random subwindows described by raw pixel intensity values and the use of ensemble of extremely randomized trees to directly classify images or to learn image features. The influence of method parameters and variants is thoroughly evaluated so as to provide baselines and guidelines for future studies. Detailed results are provided on 80 publicly available datasets that depict very diverse types of images (more than 3800 image classes and over 1.5 million images). [less ▲]

Detailed reference viewed: 306 (50 ULg)
Full Text
See detailConduire un projet techno-pédagogique avec trois universités francophones belges
Vincke, Grégoire ULg; Marée, Raphaël ULg; Wehenkel, Louis ULg et al

Poster (2015, November 10)

L’imagerie numérique devient omniprésente dans beaucoup de métiers, dont ceux de la médecine. Sa montée en puissance questionne l’université quant à la meilleure manière d’entraîner les étudiants à lire ... [more ▼]

L’imagerie numérique devient omniprésente dans beaucoup de métiers, dont ceux de la médecine. Sa montée en puissance questionne l’université quant à la meilleure manière d’entraîner les étudiants à lire, interpréter, comparer, contextualiser et discuter ces ressources inédites. A l’université, ces compétences s’acquièrent principalement, aux premiers stades de la formation, dans les cours d’histologie. Dans ce contexte, l’IFRES a initié un projet wallon (Appel Germaine Tillion / Convention n°1318185 http://histoweb.ifres.ulg.ac.be ) dont l’objectif est la transformation de la plate-forme logicielle wallonne Cytomine – http://cytomine.be une solution Web existante d'échange, de visualisation, d'annotation et d’analyse collaborative semi-automatique d'images numérisées – en un système d’activités pédagogiques tirant parti des initiatives partielles existant chez les partenaires et des évolutions techniques les plus récentes. Le projet HistoWeb travaille à cette transformation en s’appuyant, au plan conceptuel, sur l’exploration de la notion d’« écologie d’apprentissage ». Le projet compte parmi ses partenaires 3 universités (ULB, UNamur, Liège) et exige donc de chercher un équilibre entre des développements techno-pédagogiques susceptibles de les intéresser tous et des développements spécifiques et en prise avec les écologies d’apprentissage propres à chaque institution. Le poster présente les manières choisies par l’IFRES pour coordonner l'ensemble du projet, travaillant tantôt individuellement tantôt collectivement avec les différents partenaires. Le poster aura un mot par ailleurs sur la collaboration entre pédagogues et développeurs informatiques. En effet, l’IFRES, sur toute la durée du projet est appelé à travailler avec une équipe de recherche (Systmod) dépourvue de familiarité avec les leviers de l’enseignement et de l’apprentissage. Il évoquera aussi les collaborations espérées d’un passage en Open source. Le poster pourra apporter des éclairages aux questions : - qu’entend-on précisément par collaboration lorsqu’il s’agit de mener de la « recherche » dans un contexte académique ? Il sera ici question de cet équilibre entre convergence et différentiation. - Qui est susceptible de se développer professionnellement ? Les bénéfices tirés du projet par les uns et les autres au niveau pédagogique seront ici évoqués. [less ▲]

Detailed reference viewed: 83 (12 ULg)
Full Text
See detailDétection automatique de glomérules en pathologie digitale
Marée, Raphaël ULg; Jean-Christophe, Olivo-Marin; Vannary, Meas-Yedid

Scientific conference (2015, September 08)

Dans cet article, nous proposons une méthodologie de détection de glomérules au sein d’images de biopsies rénales. Elle combine des techniques de traitement d’images et d’apprentissage supervisé. Nous ... [more ▼]

Dans cet article, nous proposons une méthodologie de détection de glomérules au sein d’images de biopsies rénales. Elle combine des techniques de traitement d’images et d’apprentissage supervisé. Nous évaluons l’approche sur des images présentant plusieurs sources de variations et montrons que les comptages automatiques sont très bien corrélés avec les comptages des experts [less ▲]

Detailed reference viewed: 67 (3 ULg)
Full Text
Peer Reviewed
See detailActivation of the calcium-sensing receptor before renal ischemia/reperfusion exacerbates kidney injury
WEEKERS, Laurent ULg; De Tullio, Pascal ULg; BOVY, Christophe ULg et al

in American Journal of Translational Research (2015), 7(1), 128-138

Activation of the calcium-sensing receptor (CaSR) by ischemia/reperfusion (I/R) favours apoptosis in cardiomyocytes, hepatocytes and neurons. Its role in renal I/R is unknown. We investigated the impact ... [more ▼]

Activation of the calcium-sensing receptor (CaSR) by ischemia/reperfusion (I/R) favours apoptosis in cardiomyocytes, hepatocytes and neurons. Its role in renal I/R is unknown. We investigated the impact of pharmacological preactivation of the CaSR on kidney structure and function in a murine model of bilateral renal 30-min ischemia and 48-hour reperfusion, and in a 6-year cohort of kidney transplant recipients (KTR). C57BL/6J mice were administered daily with CaSR agonist, R-568, or with vehicle for 48 hours. Evaluation of serum urea and creatinine levels, renal histology and urine metabolome by nuclear magnetic resonance showed that R-568 was not nephrotoxic per se. Following I/R, serum urea and creatinine levels increased higher in R-568-treated animals than in controls. Jablonski’s score was significantly greater in R-568-treated kidneys, which showed a higher rate of cell proliferation and apoptosis in comparison to controls. Next, we retrospectively identified 36 patients (10.7% of our cohort) who were treated by CaSR agonist, cinacalcet, at the time of kidney transplantation (KTx). After matching these to 61 KTR upon type of donor, cold ischemic time, residual diuresis, and donor age, we observed that delayed graft function, i.e. need for dialysis in the first week after KTx, occurred in 42 and 23% of cinacalcet-treated and control groups, respectively (p≤0.05). These data suggest that pharmacological preactivation of the CaSR before renal I/R exacerbates kidney injury. [less ▲]

Detailed reference viewed: 135 (15 ULg)
Full Text
Peer Reviewed
See detailThe timing of surgery after neoadjuvant radiotherapy influences tumor dissemination in a preclinical model
Leroi, Natacha ULg; Sounni, Nor Eddine ULg; Van Overmeire, Eva et al

in Oncotarget (2015)

Neoadjuvant radiotherapy (neoRT) used in cancer treatments aims at improving local tumor control and patient overall survival. The neoRT schedule and the timing of the surgical treatment (ST) are ... [more ▼]

Neoadjuvant radiotherapy (neoRT) used in cancer treatments aims at improving local tumor control and patient overall survival. The neoRT schedule and the timing of the surgical treatment (ST) are empirically based and influenced by the clinician’s experience. The current study examines how the sequencing of neoRT and ST affects metastatic dissemination. In a breast carcinoma model, tumors were exposed to different neoRT schedules (2x5Gy or 5x2Gy) followed by surgery at day 4 or 11 post- RT. The impact on the tumor microenvironment and lung metastases was evaluated through immunohistochemical and flow cytometry analyses. After 2x5Gy, early ST (at day 4 post-RT) led to increased size and number of lung metastases as compared to ST performed at day 11. Inversely, after 5x2Gy neoRT, early ST protected the mice against lung metastases. This intriguing relationship between tumor aggressiveness and ST timing could not be explained by differences in classical parameters studied such as hypoxia, vessel density and matrix remodeling. The study of tumor-related inflammation and immunity reveals an increased circulating NK cell percentage following neoRT as compared to non irradiated mice. Then, radiation treatment and surgery were applied to tumor-bearing NOD/SCID mice. In the absence of NK cells, neoRT appears to increase lung metastatic dissemination as compared to non irradiated tumor-bearing mice. Altogether our data demonstrate that the neoRT schedule and the ST timing affect metastasis formation in a pre-clinical model and points out the potential role of NK cells. These findings highlight the importance to cautiously tailor the optimal window for ST following RT. [less ▲]

Detailed reference viewed: 63 (33 ULg)
Full Text
Peer Reviewed
See detailPhenotype Classification of Zebrafish Embryos by Supervised Learning
Jeanray, Nathalie ULg; Marée, Raphaël ULg; Pruvot, Benoist et al

in PLoS ONE (2015), 10(1), 01169891-20

Zebrafish is increasingly used to assess biological properties of chemical substances and thus is becoming a specific tool for toxicological and pharmacological studies. The effects of chemical substances ... [more ▼]

Zebrafish is increasingly used to assess biological properties of chemical substances and thus is becoming a specific tool for toxicological and pharmacological studies. The effects of chemical substances on embryo survival and development are generally evaluated manually through microscopic observation by an expert and documented by several typical photographs. Here, we present a methodology to automatically classify brightfield images of wildtype zebrafish embryos according to their defects by using an image analysis approach based on supervised machine learning. We show that, compared to manual classification, automatic classification results in 90 to 100 % agreement with consensus voting of biological experts in nine out of eleven considered defects in 3 days old zebrafish larvae. Automation of the analysis and classification of zebrafish embryo pictures reduces the workload and time required for the biological expert and increases the reproducibility and objectivity of this classification. [less ▲]

Detailed reference viewed: 90 (23 ULg)
Full Text
Peer Reviewed
See detailGenetic study of triple negative breast cancers
Boukerroucha, M; Josse, Claire ULg; El Guendi, Sonia ULg et al

Poster (2015)

Detailed reference viewed: 25 (4 ULg)
Full Text
Peer Reviewed
See detailEvaluation of BRCA1-related molecular features and microRNAs as prognostic factors for triple negative breast cancers.
Boukerroucha, Meriem ULg; Josse, Claire ULg; El Guendi, Sonia ULg et al

in BMC cancer (2015), 15(1), 755

BACKGROUND: The BRCA1 gene plays a key role in triple negative breast cancers (TNBCs), in which its expression can be lost by multiple mechanisms: germinal mutation followed by deletion of the second ... [more ▼]

BACKGROUND: The BRCA1 gene plays a key role in triple negative breast cancers (TNBCs), in which its expression can be lost by multiple mechanisms: germinal mutation followed by deletion of the second allele; negative regulation by promoter methylation; or miRNA-mediated silencing. This study aimed to establish a correlation among the BRCA1-related molecular parameters, tumor characteristics and clinical follow-up of patients to find new prognostic factors. METHODS: BRCA1 protein and mRNA expression was quantified in situ in the TNBCs of 69 patients. BRCA1 promoter methylation status was checked, as well as cytokeratin 5/6 expression. Maintenance of expressed BRCA1 protein interaction with BARD1 was quantified, as a marker of BRCA1 functionality, and the tumor expression profiles of 27 microRNAs were determined. RESULTS: miR-548c-5p was emphasized as a new independent prognostic factor in TNBC. A combination of the tumoral expression of miR-548c and three other known prognostic parameters (tumor size, lymph node invasion and CK 5/6 expression status) allowed for relapse prediction by logistic regression with an area under the curve (AUC) = 0.96. BRCA1 mRNA and protein in situ expression, as well as the amount of BRCA1 ligated to BARD1 in the tumor, lacked any associations with patient outcomes, likely due to high intratumoral heterogeneity, and thus could not be used for clinical purposes. CONCLUSIONS: In situ BRCA1-related expression parameters could be used for clinical purposes at the time of diagnosis. In contrast, miR-548c-5p showed a promising potential as a prognostic factor in TNBC. [less ▲]

Detailed reference viewed: 40 (10 ULg)
Full Text
Peer Reviewed
See detailZebrafish bone and general physiology are differently affected by hormones or changes in gravity.
Aceto, Jessica ULg; Nourizadeh-Lillabadi, Rasoul; Marée, Raphaël ULg et al

in PLoS ONE (2015), 10(6), 1-42

Teleost fish such as zebrafish (Danio rerio) are increasingly used for physiological, genetic and developmental studies. Our understanding of the physiological consequences of altered gravity in an entire ... [more ▼]

Teleost fish such as zebrafish (Danio rerio) are increasingly used for physiological, genetic and developmental studies. Our understanding of the physiological consequences of altered gravity in an entire organism is still incomplete. We used altered gravity and drug treatment experiments to evaluate their effects specifically on bone formation and more generally on whole genome gene expression. By combining morphometric tools with an objective scoring system for the state of development for each element in the head skeleton and specific gene expression analysis, we confirmed and characterized in detail the decrease or increase of bone formation caused by a 5 day treatment (from 5dpf to 10 dpf) of, respectively parathyroid hormone (PTH) or vitamin D3 (VitD3). Microarray transcriptome analysis after 24 hours treatment reveals a general effect on physiology upon VitD3 treatment, while PTH causes more specifically developmental effects. Hypergravity (3g from 5dpf to 9 dpf) exposure results in a significantly larger head and a significant increase in bone formation for a subset of the cranial bones. Gene expression analysis after 24 hrs at 3g revealed differential expression of genes involved in the development and function of the skeletal, muscular, nervous, endocrine and cardiovascular systems. Finally, we propose a novel type of experimental approach, the "Reduced Gravity Paradigm", by keeping the developing larvae at 3g hypergravity for the first 5 days before returning them to 1g for one additional day. 5 days exposure to 3g during these early stages also caused increased bone formation, while gene expression analysis revealed a central network of regulatory genes (hes5, sox10, lgals3bp, egr1, edn1, fos, fosb, klf2, gadd45ba and socs3a) whose expression was consistently affected by the transition from hyper- to normal gravity. [less ▲]

Detailed reference viewed: 207 (21 ULg)
Full Text
Peer Reviewed
See detailEvaluation and Comparison of Anatomical Landmark Detection Methods for Cephalometric X-Ray Images: A Grand Challenge
Ching Wei, Wang; Cheng-Ta, Huang; Meng-Che, Hsieh et al

in IEEE Transactions on Medical Imaging (2015)

Detailed reference viewed: 65 (5 ULg)
Full Text
See detailTowards generic image classification: an extensive empirical study
Marée, Raphaël ULg; Geurts, Pierre ULg; Wehenkel, Louis ULg

E-print/Working paper (2014)

This paper considers the general problem of image classification without using any prior knowledge about image classes. We study variants of a method based on supervised learning whose common steps are ... [more ▼]

This paper considers the general problem of image classification without using any prior knowledge about image classes. We study variants of a method based on supervised learning whose common steps are the extraction of random subwindows described by raw pixel intensity values and the use of ensemble of extremely randomized trees to directly classify images or to learn image features. The influence of method parameters and variants is thoroughly evaluated so as to provide baselines and guidelines for future studies. Detailed results are provided on 80 publicly available datasets that depict very diverse types of images (more than 3800 image classes and over 1.5 million images). [less ▲]

Detailed reference viewed: 149 (13 ULg)
Full Text
See detailHistoWeb - Toward a new learning ecology for histology
Vincke, Grégoire ULg; Marée, Raphaël ULg; Wehenkel, Louis ULg et al

Conference (2014, December 16)

HistoWeb targets the transformation of the professional tool Cytomineinto a comprehensive and innovative teaching platform, valuing the notions of learning ecology and new learning dimensions seeking for ... [more ▼]

HistoWeb targets the transformation of the professional tool Cytomineinto a comprehensive and innovative teaching platform, valuing the notions of learning ecology and new learning dimensions seeking for lifelong competencies. The poster was released at the Digital Learning round table, organized by the European Commission around H2020 funding instruments and call 2 "ICT-20 Technologies for better human learning" [less ▲]

Detailed reference viewed: 98 (24 ULg)
Full Text
See detailHistoWeb - Transforming a professional bioimages platform into a learning tool for histology
QUATRESOOZ, Pascale ULg; Defaweux, Valérie ULg; Rollus, Loïc ULg et al

Scientific conference (2014, October 30)

In 2012, medical studies in Belgium has undergone an important reform that leads to a rocketing rise of the number of students. The University of Liège took this renewed context as an opportunity to ... [more ▼]

In 2012, medical studies in Belgium has undergone an important reform that leads to a rocketing rise of the number of students. The University of Liège took this renewed context as an opportunity to thoroughly revamp its teaching methods in histology, extending CYTOMINE [1] (http://cytomine.be : a web-based, image storage, annotation, and analysis platform) with new pedagogical features. [less ▲]

Detailed reference viewed: 95 (28 ULg)
Full Text
Peer Reviewed
See detailA hybrid human-computer approach for large-scale image-based measurements using web services and machine learning
Marée, Raphaël ULg; Rollus, Loïc ULg; Stevens, Benjamin ULg et al

in Proceedings IEEE International Symposium on Biomedical Imaging (2014, May)

We present a novel methodology combining web-based software development practices, machine learning, and spatial databases for computer-aided quantification of regions of interest (ROIs) in large-scale ... [more ▼]

We present a novel methodology combining web-based software development practices, machine learning, and spatial databases for computer-aided quantification of regions of interest (ROIs) in large-scale imaging data. We describe our main methodological choices, and then illustrate the benefits of the approach (workload reduction, improved precision, scalability, and traceability) on hundreds of whole-slide images of biological tissue slices in cancer research. [less ▲]

Detailed reference viewed: 429 (51 ULg)