Segmentation & Classification of Cells

This example looks at red blood cells. All cells will be segmented and classified as normal or burr cells. Burr cells or echinocytes have abnormal membrane characterized by many small, evenly spaced thorny projections.

Separate foreground and background with an automatic threshold.

Segment overlapping and touching blood cells by identifying every cell as a peak in the distance transform and by performing a watershed segmentation to capture the scope of each cell.

Create a mask for all cells.

Highlight the tentacles of burr cells via a morphological top-hat transformation that extracts all shapes pixels.

Extract sickle cells by selecting cells of a certain size that exhibit tentacles of more than 5% of their total area.