Visualization of the image segmentation and labeling pipeline for the first frame of an example movie.

<p>(A) Grayscale raw image. (B) Grayscale image showing the output of DeepCad. (C) Probability map generated by ilastik. (D) Binarized image obtained (from (C)) using thresholding via Li’s iterative Minimum Cross Entropy Method. (E) Smoothed binarized image. (F) Integrated movie over all time...

Full description

Saved in:
Bibliographic Details
Main Author: Miriam Schnitzerlein (21446136) (author)
Other Authors: Eric Greto (21446139) (author), Anja Wegner (10643774) (author), Anna Möller (18076549) (author), Oliver Aust (21446142) (author), Oumaima Ben Brahim (21446145) (author), David B. Blumenthal (11838270) (author), Vasily Zaburdaev (504665) (author), Stefan Uderhardt (21446148) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:<p>(A) Grayscale raw image. (B) Grayscale image showing the output of DeepCad. (C) Probability map generated by ilastik. (D) Binarized image obtained (from (C)) using thresholding via Li’s iterative Minimum Cross Entropy Method. (E) Smoothed binarized image. (F) Integrated movie over all time frames. (G) Fixed area of the integrated movie by using a threshold of 0.97 on (F). (H) Label seeds obtained from (G) by coloring all distinct objects. (I) Overlay of label seeds (H) and binary segmented cells (D). (J) Labeling all distinct objects in (I) using the watershed algorithm to be used as new seed labels. (K) Dilating the cells from (E) and using the labeled cells from (J) as seed labels for the watershed algorithm to achieve the labeling as shown in (L). (M) Using the labels from (L) to correctly label the pre-processed binary images from (E). (N) Final labelled image.</p>