Quality assurance of segmentation results

Posted by Mara Lampert, on 13 April 2023

This blog post revolves around determining and improving the quality of segmentation results. A common problem is that this step is often omitted and done rather by the appearance of the image segmentation than by actually quantifying it. This blogpost aims to show different ways to achieve this quantification as this leads to reproducibility. Therefore,

TrackMate-Oneat: Auto Track correction using deep learning networks

Posted by varun kapoor, on 4 July 2022

During the tracking of motile cells, solving the problem of linking objects between two consecutive timepoints becomes even more complicated, if the cells divide or undergo cell death. In the terms of trajectories, this means the addition of trajectory branches and terminations. However, dividing and dying cells are characteristic in their shape, and leveraging this