Faculty of Informatics Vienna University of Technology Institute of Computer Aided Automation PRIP Home PRIP Home
Personal tools
You are here: Home Teaching PRIP-Talks Florian Kromp: Automated Detection of Leucemic Populations Based on Minimal Residual Disease (MRD) Diagnostics Using Meanshift-Clustering
Navigation
 

Florian Kromp: Automated Detection of Leucemic Populations Based on Minimal Residual Disease (MRD) Diagnostics Using Meanshift-Clustering

(Abschlussvortrag Projektpraktikum)

What
  • Presentation
When May 12, 2009
from 04:55 pm to 05:15 pm
Add event to calendar vCal
iCal
Identification of leucemic cell populations using Minimal Residual
Disease (MRD) diagnostics has become increasingly important in Acute
Lymphoblastic Leukemia (ALL) diagnostics. Data are generated by mixing
cells with coloured antigens and measuring them with owcytometers using
up to 6 channels. Evaluation is based on operator skills and knowledge.
The procedure involves optical inspection of combinations of two
parametric visualisations. Evaluation based on optical inspection is
however no standardized process. We therefore developed a diagnostical
tool based on Meanshift-Clustering to automatically evaluate the size of
leucemic populations using data generated by Flowcytometry. The feature
space is spanned by the parameters of owcytometric measurement, and
clusters are calculated by using the meanshift algorithm. Leucemic
samples from an international study (BFM ALL 2008, ALLIC 2008) were used
to evaluate the method.
Document Actions