Manual segmentation
Prerequisites
Before starting this lesson, you should be familiar with:
Learning Objectives
After completing this lesson, learners should be able to:
Manually segment parts of a 2-D (3-D) image.
Motivation
Manual segmentation is useful in many ways. If the dataset of interest is small, manual segmentation may be faster than designing an automated segmentation workflow, or automated segmentation may be very difficult. In addition, manual segmentation can serve as training and validation data for (deep-learning based) automated segmentation algorithms.
Concept map
graph TD
I("Image") --> MS("Manual segmentation")
MS --> LM("Label mask image")
Figure
Manual segmentation considerations
How to deal with objects that are not fully in the image?
Should objects be separated by background pixels?
Activities
- Open the FIXME
- Perform a manual instance segmentation of FIXME
Show activity for:
ITK-SNAP
- Install ITK-SNAP
- Check out a tutorial
- Open an image and perform a manual segmentation task (see above).
Assessment
Fill in the blanks
- Manual segmentations are often stored as ___.
Solution
- label mask images
Follow-up material
Recommended follow-up modules:
Learn more: