Research :

Scientific Challenge : Cognitive BioMedical Imaging

The major scope of my researches is to set the bases of cognitive biomedical image analysis, as knowledgeable pervasive exploration of the biomedical image for diagnosis / prognosis, planning and treatment assistance, by actively and continuously include medical implicit knowledge. This challenge deals with a tripolar approach considering the cognitive vision paradigms (in cognito) applied to the medical image / signal / information (in- & ex-vivo) in the framework of the virtual physiological human (in silico) :


Cognitive BioMedical Image Analysis (in Cognito – in Silico – in Vivo)

Multiscale and multimodal bioimage analysis and computer vision supported by medical visual semantics, constitute the core competence necessary to this approach. The exploration concerns high-throughput screening and high resolution macromodalities. Prognosis traceability and uncertainty management are considered as important elements enabling a constant implication of our medical partners and an effective translational approach. Integrating micro and macro modalities in the next generation of PACS and metadata management platforms, necessitates to go from the semiologic approaches towards operational morphogenetic models, by considering morphological, bio-physical and genetic aspects. This necessitates a close collaboration within multidisciplinary teams/projects.

Keywords: Medical Image Analysis, Medical Image Understanding, Multimodal Medical Image Fusion, Content-Based Medical Image Indexing and Retrieval, Diagnosis and Prognosis, Machine Learning

Translational challenges related to the proposed themes

Our scientific challenges can be grouped in three categories, related to partcular clinical challenges, all leaded in collaboration with local hospitals :

  • Integrated Virtual Cognitive Microscopy and Microscopy Mining
    • Related to breast cancer grading and visual reasoning for histopathology images exploration
  • Medical image conceptualization for early detection, diagnosis and prognosis
    • Multimodal image indexing & analysis for early detection of Hyperacute Middle Cerebral Artery Stroke (brain CT) and Parkinson’s Disease prognosis (brain MRI DTI fusion).

These topics will be detailed in the clinical challenges.