A5037649169- AI in cancer detection
- Image Retrieval and Classification Techniques
- Radiomics and Machine Learning in Medical Imaging
- Advanced Image and Video Retrieval Techniques
- Medical Image Segmentation Techniques
- Cell Image Analysis Techniques
- 3D Modeling in Geospatial Applications
- Remote-Sensing Image Classification
- Colorectal Cancer Treatments and Studies
- Remote Sensing and LiDAR Applications
- Digital Image Processing Techniques
- Cancer Immunotherapy and Biomarkers
- 3D Surveying and Cultural Heritage
- Remote Sensing in Agriculture
- Biomedical Text Mining and Ontologies
- Computational Geometry and Mesh Generation
- Advanced Vision and Imaging
- Diamond and Carbon-based Materials Research
- Animal Nutrition and Physiology
- Meat and Animal Product Quality
- 3D Shape Modeling and Analysis
- Automated Road and Building Extraction
- Infrastructure Maintenance and Monitoring
- Gene expression and cancer classification
- Machine Learning and Data Classification
Université Paris Cité
2012-2024
Laboratoire de Recherche en Informatique de Paris 6
2013-2024
Institut de Biologie de Lille
2023
Centre Hospitalier Universitaire de Lille
2023
Centre de Recherche Jean Pierre Aubert
2023
Sorbonne Paris Cité
2017-2023
Laboratoire Informatique Paris Descartes
2022
Weatherford College
2022
Université Paris Sciences et Lettres
2017-2021
École Normale Supérieure - PSL
2021
Introduction: In the framework of Cognitive Microscope (MICO) project, we have set up a contest about mitosis detection in images H and E stained slides breast cancer for conference ICPR 2012. Mitotic count is an important parameter prognosis cancer. However, digital histopathology challenging problem that needs deeper study. Indeed, difficult because are small objects with large variety shapes, they can thus be easily confused some other or artefacts present image. We added further...
Abstract Primary liver cancer arises either from hepatocytic or biliary lineage cells, giving rise to hepatocellular carcinoma (HCC) intrahepatic cholangiocarcinoma (ICCA). Combined hepatocellular- cholangiocarcinomas (cHCC-CCA) exhibit equivocal mixed features of both, causing diagnostic uncertainty and difficulty in determining proper management. Here, we perform a comprehensive deep learning-based phenotyping multiple cohorts patients. We show that learning can reproduce the diagnosis HCC...
Efficient transfer of the quantum state ensembles electronic spins to nuclear is at root many novel quantum-based technologies. However, accomplishing this requires magnetic fields aligned specific crystalline axes or cryogenic temperatures, limiting range applications. Here, we observe fast Rabi oscillations on electron-nuclear spin exchanging transitions, coherent population trapping, and polarization under ambient conditions using uncritical field angles. For this, employ nominally...
We present some results on systems for automatically detecting bridges in high-resolution satellite images. had made preliminary explorations the use of geometric models to detect and round-abouts panchromatic, ((50 cm)/sup 2/ per pixel) not yet systematically evaluated system, but false alarms seemed be its most important problem. In parallel, we also built a which used local radiometric textural features classify terrain pixels into number semantically-meaningful classes, then applied...
Histopathological examination is a powerful method for prognosis of major diseases such as breast cancer. Analysis medical images largely remains the work human experts. Current virtual microscope systems are mainly an emulation real microscopes with annotation and some image analysis capabilities. However, lack effective knowledge management prevents from being computer-aided platforms. The cognitive microscopic framework, through extended modeling use knowledge, has capacity to analyse...
Most research works focus on pattern recognition within a small sample images but strategies for running efficiently these algorithms over large are rarely if ever specifically considered. In particular, the new generation of satellite and microscopic acquired at very high resolution daily rate. We propose an efficient, generic strategy to explore by combining computational geometry tools with local signal measure relevance in dynamic sampling framework. An application breast cancer grading...
Range image segmentation has many applications in computer vision areas such as graphics and robotic vision. A generic methodology for 3D point set analysis which planar structures play an important role is defined. It consists mainly of a specific K-means algorithm able to process different shapes cluster. At the same time, within geometric topologic considerations, application-driven heuristics designed. This helps find out right number sets order give good visualization representation...
The aim of the work presented in this paper is to develop a method for automatic identification tree species using Terrestrial Light Detection and Ranging (T-LiDAR) data. approach that we propose analyses depth images built from 3D point clouds corresponding 30 cm segment trunk order extract characteristic shape features used classifying different Random Forest classifier. We will present transform cloud image region based segmentation before are computed on segmented images. Our has been...
Human perception is routinely assessing the similarity between images, both for decision making and creative thinking. But underlying cognitive process not really well understood yet, hence difficult to be mimicked by computer vision systems. State-of-the-art approaches using deep architectures are often based on comparison of images described as feature vectors learned image categorization task. As a consequence, such features powerful compare semantically related but efficient visually...
New imaging devices provide image data at very high spatial resolution acquisition and throughput rate. In satellite or medical two-dimensional images, high-content large issues plead for more semantic level interactions between the computer vision systems end-users in order to leverage cognitive symbiosis both practical tasks such as clinical disease grading practices based on visual inspection. Within mathematical morphology framework, this seminal paper proposes new theoretical tools...
2D or 3D dataset transformations, interpolations and resampling operations are essential techniques that able to display graphical models in several fields such as medical visualization engineering. In this study, an overview of interpolation approaches the last ten years was given a application for magnetic resonance images implemented using free form cubic b-spline deformation model based transformed images. addition, registration error shown grid view nonrigid registration.