References of "Marée, Raphaël"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailBIAFLOWS: A Collaborative Framework to Reproducibly Deploy and Benchmark Bioimage Analysis Workflows
Rubens, Ulysse ULiege; Mormont, Romain ULiege; Paavolainen, Lassi et al

in Patterns (2020), 1

Image analysis is key to extracting quantitative information from scientific microscopy images, but the methods involved are now often so refined that they can no longer be unambiguously described by ... [more ▼]

Image analysis is key to extracting quantitative information from scientific microscopy images, but the methods involved are now often so refined that they can no longer be unambiguously described by written protocols. We introduce BIAFLOWS, an open-source web tool enabling to reproducibly deploy and benchmark bioimage analysis workflows coming from any software ecosystem. A curated instance of BIAFLOWS populated with 34 image analysis workflows and 15 microscopy image datasets recapitulating common bioimage analysis problems is available online. The workflows can be launched and assessed remotely by comparing their performance visually and according to standard benchmark metrics. We illustrated these features by comparing seven nuclei segmentation workflows, including deep-learning methods. BIAFLOWS enables to benchmark and share bioimage analysis workflows, hence safeguarding research results and promoting high-quality standards in image analysis. The platform is thoroughly documented and ready to gather annotated microscopy datasets and workflows contributed by the bioimaging community. [less ▲]

Detailed reference viewed: 37 (7 ULiège)
Full Text
Peer Reviewed
See detailMulti-task pre-training of deep neural networks for digital pathology
Mormont, Romain ULiege; Geurts, Pierre ULiege; Marée, Raphaël ULiege

in IEEE Journal of Biomedical and Health Informatics (2020)

In this work, we investigate multi-task learning as a way of pre-training models for classification tasks in digital pathology. It is motivated by the fact that many small and medium-size datasets have ... [more ▼]

In this work, we investigate multi-task learning as a way of pre-training models for classification tasks in digital pathology. It is motivated by the fact that many small and medium-size datasets have been released by the community over the years whereas there is no large scale dataset similar to ImageNet in the domain. We first assemble and transform many digital pathology datasets into a pool of 22 classification tasks and almost 900k images. Then, we propose a simple architecture and training scheme for creating a transferable model and a robust evaluation and selection protocol in order to evaluate our method. Depending on the target task, we show that our models used as feature extractors either improve significantly over ImageNet pre-trained models or provide comparable performance. Fine-tuning improves performance over feature extraction and is able to recover the lack of specificity of ImageNet features, as both pre-training sources yield comparable performance. [less ▲]

Detailed reference viewed: 145 (10 ULiège)
Full Text
Peer Reviewed
See detailOpen Practices and Resources for Collaborative Digital Pathology
Marée, Raphaël ULiege

in Frontiers in Medicine (2019)

In this paper, we describe open practices and open resources in the field of digital pathology with a specific focus on approaches that ease collaboration in research and education settings. Our review ... [more ▼]

In this paper, we describe open practices and open resources in the field of digital pathology with a specific focus on approaches that ease collaboration in research and education settings. Our review includes open access journals and open peer review, open-source software (libraries, desktop tools, and web applications), and open access collections. We illustrate applications and discuss current limitations and perspectives. [less ▲]

Detailed reference viewed: 35 (8 ULiège)
Full Text
Peer Reviewed
See detailOzone-primed neutrophils promote early steps of tumor cell metastasis to lungs by enhancing their NET production
Rocks, Natacha ULiege; Vanwinge, Céline ULiege; Radermecker, Coraline ULiege et al

in Thorax (2019), 0

Air pollution, including particulates and gazes such as ozone (O3), is detrimental for patient’s health and has repeatedly been correlated to increased morbidity and mortality in industrialized countries ... [more ▼]

Air pollution, including particulates and gazes such as ozone (O3), is detrimental for patient’s health and has repeatedly been correlated to increased morbidity and mortality in industrialized countries. Although studies have described a link between ambient particulate matter and increased lung cancer morbidity, no direct relation has yet been established between O3 exposure and metastatic dissemination to lungs. [less ▲]

Detailed reference viewed: 100 (34 ULiège)
Full Text
Peer Reviewed
See detailCytomine: towards an open and collaborative software platform for digital pathology bridged to molecular investigations
Rubens, Ulysse ULiege; Hoyoux, Renaud; Vanosmael, Laurent et al

in Proteomics. Clinical Applications (2018)

PURPOSE: Digital histology is being increasingly used in research and clinical applications. In parallel new tissue imaging methods (e.g. imaging mass spectrometry) are currently regarded as very ... [more ▼]

PURPOSE: Digital histology is being increasingly used in research and clinical applications. In parallel new tissue imaging methods (e.g. imaging mass spectrometry) are currently regarded as very promising approaches for better molecular diagnosis in pathology. However, these new data sources are still often underexploited because of the lack of collaborative software to share and correlate information for multimodal analysis. EXPERIMENTAL DESIGN: We followed the open science paradigm to develop new features in our web-based Cytomine software to support next-generation digital pathology bridged to molecular investigations. RESULTS: Our new open-source developments allow to explore whole-slide classical histology with MALDI imaging and to support preprocessing for biomarker discovery using laser microdissection-based microproteomics. CONCLUSIONS AND CLINICAL RELEVANCE: Our updated version of Cytomine is the first open and web-based tool to enable sharing data from classical histology, molecular imaging and cell counting for proteomics preprocessing. It holds good promise to fulfill imminent needs in molecular histopathology. This article is protected by copyright. All rights reserved. [less ▲]

Detailed reference viewed: 97 (25 ULiège)
Full Text
Peer Reviewed
See detailUN « MASSIVE OPEN ONLINE COURSE » (MOOC) SUR DES TRAVAUX PRATIQUES EN HISTOLOGIE : UN OBJECTIF, UN OUTIL, UN PUBLIC VARIE ! RETOUR SUR UNE PREMIERE EXPERIENCE.
Multon, Sylvie ULiege; Pesesse, Laurence ULiege; Weatherspoon, Alodie ULiege et al

in Annales de Pathologie (2018), 38(2), 76-84

Un objectif ! Le MOOC intitulé « Introduction à l’histologie, exploration des tissus du corps humain » reflète notre vision de la pratique de l’Histologie générale qui repose sur la capacité à ... [more ▼]

Un objectif ! Le MOOC intitulé « Introduction à l’histologie, exploration des tissus du corps humain » reflète notre vision de la pratique de l’Histologie générale qui repose sur la capacité à diagnostiquer les 5 familles de tissus biologiques. A terme, les participants doivent être capables de reconnaître les différents types cellulaires et tous les éléments qui les entourent afin de comprendre comment ils s’organisent entre eux pour former des tissus aux fonctions spécifiques. Un outil ! Ce savoir-faire s’appuie sur la construction d’un raisonnement à partir d’observations de structures microscopiques. Pour ce faire, les apprenants sont invités à manipuler un microscope virtuel pour explorer des prélèvements biologiques sur lames histologiques digitalisées. Des annotations, commentaires, dessins ou photos sont associés à des repères qui enrichissent l’étude de ces coupes histologiques. Un public cible ! Deux parcours pédagogiques permettent d’approfondir différemment la matière et de correspondre ainsi aux objectifs ou motivations de chacun. Après une première année d’expérience, les statistiques d’utilisation et des sondages réalisés auprès de nos apprenants montrent que le MOOC Histo a permis à chacun d’eux d’y trouver un intérêt et de fédérer une communauté d’apprenants motivés. [less ▲]

Detailed reference viewed: 92 (26 ULiège)
Full Text
Peer Reviewed
See detailLandmark detection in 2D bioimages for geometric morphometrics: a multi-resolution tree-based approach.
Vandaele, Rémy ULiege; Aceto, Jessica ULiege; Muller, Marc ULiege et al

in Scientific Reports (2018), 8(1), 538

The detection of anatomical landmarks in bioimages is a necessary but tedious step for geometric morphometrics studies in many research domains. We propose variants of a multi-resolution tree-based ... [more ▼]

The detection of anatomical landmarks in bioimages is a necessary but tedious step for geometric morphometrics studies in many research domains. We propose variants of a multi-resolution tree-based approach to speed-up the detection of landmarks in bioimages. We extensively evaluate our method variants on three different datasets (cephalometric, zebrafish, and drosophila images). We identify the key method parameters (notably the multi-resolution) and report results with respect to human ground truths and existing methods. Our method achieves recognition performances competitive with current existing approaches while being generic and fast. The algorithms are integrated in the open-source Cytomine software and we provide parameter configuration guidelines so that they can be easily exploited by end-users. Finally, datasets are readily available through a Cytomine server to foster future research. [less ▲]

Detailed reference viewed: 128 (17 ULiège)
Full Text
Peer Reviewed
See detailComparison of deep transfer learning strategies for digital pathology
Mormont, Romain ULiege; Geurts, Pierre ULiege; Marée, Raphaël ULiege

in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2018)

In this paper, we study deep transfer learning as a way of overcoming object recognition challenges encountered in the field of digital pathology. Through several experiments, we investigate various uses ... [more ▼]

In this paper, we study deep transfer learning as a way of overcoming object recognition challenges encountered in the field of digital pathology. Through several experiments, we investigate various uses of pre-trained neural network architectures and different combination schemes with random forests for feature selection. Our experiments on eight classification datasets show that densely connected and residual networks consistently yield best performances across strategies. It also appears that network fine-tuning and using inner layers features are the best performing strategies, with the former yielding slightly superior results. [less ▲]

Detailed reference viewed: 621 (95 ULiège)
Full Text
Peer Reviewed
See detailInflammation-Generated Extracellular Matrix Fragments Drive Lung Metastasis
BEKAERT, Sandrine ULiege; Fillet, Marianne ULiege; Detry, Benoit et al

in Cancer Growth and Metastasis (2017), 10

Mechanisms explaining the propensity of a primary tumor to metastasize to a specific site still need to be unveiled, and clinical studies support a link between chronic inflammation and cancer ... [more ▼]

Mechanisms explaining the propensity of a primary tumor to metastasize to a specific site still need to be unveiled, and clinical studies support a link between chronic inflammation and cancer dissemination to specific tissues. Using different mouse models, we demonstrate the role of inflammation-generated extracellular matrix fragments ac-PGP (N-acetyl-proline-glycine-proline) on tumor cells dissemination to lung parenchyma. In mice exposed to cigarette smoke or lipopolysaccharide, lung neutrophilic inflammation produces increased levels of MMP-9 (matrix metalloproteinase 9) that contributes to collagen breakdown and allows the release of ac-PGP tripeptides. By silencing CXCR2 gene expression in tumor cells, we show that these generated ac-PGP tripeptides exert a chemotactic activity on tumor cells in vivo by binding CXCR2. [less ▲]

Detailed reference viewed: 87 (27 ULiège)
Full Text
Peer Reviewed
See detailAutomated multimodal volume registration based on supervised 3D anatomical landmark detection
Vandaele, Rémy ULiege; LALLEMAND, François ULiege; MARTINIVE, Philippe ULiege et al

in SCITEPRESS Digital Library (2017)

We propose a new method for automatic 3D multimodal registration based on anatomical landmark detection. Landmark detectors are learned independantly in the two imaging modalities using Extremely ... [more ▼]

We propose a new method for automatic 3D multimodal registration based on anatomical landmark detection. Landmark detectors are learned independantly in the two imaging modalities using Extremely Randomized Trees and multi-resolution voxel windows. A least-squares fitting algorithm is then used for rigid registration based on the landmark positions as predicted by these detectors in the two imaging modalities. Experiments are carried out with this method on a dataset of pelvis CT and CBCT scans related to 45 patients. On this dataset, our fully automatic approach yields results very competitive with respect to a manually assisted state-of-the-art rigid registration algorithm. [less ▲]

Detailed reference viewed: 238 (44 ULiège)
Full Text
Peer Reviewed
See detailThe need for careful data collection for pattern recognition in digital pathology
Marée, Raphaël ULiege

in Journal of Pathology Informatics (2017)

Effective pattern recognition requires carefully designed ground-truth datasets. In this technical note, we first summarize potential data collection issues in digital pathology and then propose ... [more ▼]

Effective pattern recognition requires carefully designed ground-truth datasets. In this technical note, we first summarize potential data collection issues in digital pathology and then propose guidelines to build more realistic ground-truth datasets and to control their quality. We hope our comments will foster the effective application of pattern recognition approaches in digital pathology. [less ▲]

Detailed reference viewed: 128 (22 ULiège)
Full Text
Peer Reviewed
See detailSLDC: an open-source workflow for object detection in multi-gigapixel images
Mormont, Romain ULiege; Begon, Jean-Michel ULiege; Hoyoux, Renaud ULiege et al

Conference (2016, September 12)

Detailed reference viewed: 350 (61 ULiège)
Full Text
Peer Reviewed
See detailMettre en place des « tableaux » de bord dans l’étude de l’histologie – Une exploration du potentiel pédagogique des traces d’apprentissage
Verpoorten, Dominique ULiege; Vincke, Grégoire ULiege; Pesesse, Laurence ULiege et al

Conference (2016, June 06)

La communication synthétise les résultats d'un questionnaire visant à estimer les attentes d'enseignants en histologie en matière de visualisations de traces d'apprentissage laissées par leurs étudiants ... [more ▼]

La communication synthétise les résultats d'un questionnaire visant à estimer les attentes d'enseignants en histologie en matière de visualisations de traces d'apprentissage laissées par leurs étudiants lorsqu'ils travaillent avec un outil spécialisé (Cytomine) permettant une interaction avec des coupes histologiques numérisées. [less ▲]

Detailed reference viewed: 114 (32 ULiège)
Full Text
Peer Reviewed
See detailCollaborative analysis of multi-gigapixel imaging data using Cytomine
Marée, Raphaël ULiege; 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: 205 (44 ULiège)
Full Text
Peer Reviewed
See detailTowards Generic Image Classification using Tree-based Learning: an Extensive Empirical Study
Marée, Raphaël ULiege; Geurts, Pierre ULiege; Wehenkel, Louis ULiege

in Pattern Recognition Letters (2016), 74(15), 17-23

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: 449 (70 ULiège)
Full Text
Peer Reviewed
See detailAn approach for detection of glomeruli in multisite digital pathology
Marée, Raphaël ULiege; 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: 120 (22 ULiège)
Full Text
See detailConduire un projet techno-pédagogique avec trois universités francophones belges
Vincke, Grégoire ULiege; Marée, Raphaël ULiege; Wehenkel, Louis ULiege 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: 139 (24 ULiège)
Full Text
See detailDétection automatique de glomérules en pathologie digitale
Marée, Raphaël ULiege; 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: 78 (3 ULiège)