Team, Visitors, External Collaborators
Overall Objectives
Research Program
Highlights of the Year
New Software and Platforms
New Results
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
XML PDF e-pub
PDF e-Pub

Section: New Results

Tumor cell tracking for automatic detection of cell death time, and classification of its type

Participants : Deborah Cottais, Eric Debreuve.

This work was made in collaboration with Jérémie Roux (IRCAN, Nice, France).

The available data were multi-channel videos acquired in fluorescence microscopy. We first performed cell segmentation on the channel in which the geometrical information was predominant. Then we performed tracking of the segmented cells. More precisely, we refer to tracking as the construction of cell trajectories along the video (see Fig. 9). By transferring this cell tracking onto the channel in which the radiometric information of the cells is the richest (mean intensity, variance, texture), we were able to extract characteristics for each cell, and study their temporal evolution to deduce the moment of cell death. Next, we are planning to develop a method of classification of the cell deaths into predefined types.

Figure 9. From left to right: two channels of a video frame and tracking trajectories of the segmented cells.