Differential Interference Contrast (DIC) Image Segmentation and Quantification using Deep Learning
This workflow uses deep learning to segment images obtained by Differential Interference Contrast (DIC) microscopy. Nuclei and mitochondria are segmented and counted cell per cell.
DIC images are obtained by Differential Interference Contrast (DIC) microscopy. All DIC images have the appearance of a three-dimensional object under very oblique illumination, causing strong light and dark shadows on the corresponding faces, and leading to difficulties to apply automatic segmentation.
The workflow demonstrated here uses the deep learning approach for the DIC image segmentation of cells. The other channels, corresponding to nuclei and mitochondria, are then segmented and quantified using dedicated recipes. The number of mitochondria in each cell is computed.
If you are not familiar with the deep learning features of Amira-Avizo, please refer to Amira-Avizo user's guide.