IMAGeS team: IMages, leArning, Geometry and Statistics

Difference between revisions of "TIBM: Change detection and prediction"

From IMAGeS team: IMages, leArning, Geometry and Statistics
Jump to navigation Jump to search
Line 4: Line 4:
 
<tr>
 
<tr>
 
<td>
 
<td>
Automatic change detection is a tool with great potential to monitor evolving pathologies.
+
Automatic change detection is a tool of great interest for monitoring evolving pathologies.
 
The aim is is to identify changes over time between two examinations of a given subject.
 
The aim is is to identify changes over time between two examinations of a given subject.
 
This may allow a better care of the patient (personalized medicine), either for diagnosis, prognosis or evaluation of therapeutic response.
 
This may allow a better care of the patient (personalized medicine), either for diagnosis, prognosis or evaluation of therapeutic response.

Revision as of 11:19, 10 October 2016


Automatic change detection is a tool of great interest for monitoring evolving pathologies. The aim is is to identify changes over time between two examinations of a given subject. This may allow a better care of the patient (personalized medicine), either for diagnosis, prognosis or evaluation of therapeutic response.

Thus, novel methods have been developed to analyze longitudinal diffusion MRI sequences:

  • Using statistical tests adapted to different representations of the diffusion process 2-BNHR12
  • Taking into account the positive definite property of diffusion tensor 2-GNHB12
  • or the geometry of the white matter fiber bundles 2-GNBH13.

In addition, work has focused on the temporal modeling of brain maturation 5-PRSS12 and gyrification 2-PRSK16 in the project ERC FBrain.

thumb

PhD thesis


→ Back to Biomedical image processing page