Segmentation

Prerequisites

Before starting this lesson, you should be familiar with:

Learning Objectives

After completing this lesson, learners should be able to:

  • Understand the difference between instance and semantic segmentation

Motivation

Bioimage analysis very often is concerned with the measurement of features (intensity, shape, …) of individual objects (cells, nuclei, …) or regions (mesoderm, inter-cellular space, …) in images. The process of partitioning an image into objects and regions is called “image segmentation” and due to its prevalence is of central importance to bioimage analysis.

Concept map

graph TD I[Image] --> S(Semantic segmentation) I --> O(Instance segmentation) O --- IO(Individual objects) S --- R(Regions of same type)



Figure


Left - Semantic segmentation of nuclei, membranes and mitochondria; Right - Instance segmentation of cells. Data from Martinez, Pape et al., Whole body integration of gene expression and single-cell morphology, Cell 2021.







Explanations




Follow-up material

Recommended follow-up modules:

Learn more: