IHC, Glomeruli Detection, AI

Developed for automatic segmentation of glomeruli in IHC stained kidney tissue

Glomeruli are the filtering units of the kidney. They are located at the beginning of nephrons and consist of a bundle of capillaries. This APP automatically identifies and segments glomeruli in kidney samples stained with various biomarkers including CD68, COL1A1, COLIV, synaptopodin, nephrin, WT1 and/or aSMA. It utilizes articifical intelligence (AI)/deep learning for a robust segmentation.

Figure 1

Segmented glomeruli in kidney samples stained with aSMA.

Figure 2

Segmented glomeruli in kidney samples stained with CD68.

Figure 3

Segmented glomeruli in kidney samples stained with Col1a1

Figure 4

Segmented glomeruli in kidney samples stained with ColIV.

Figure 5

Segmented glomeruli in kidney samples stained with nephrin.

Figure 6

Segmented glomeruli in kidney samples stained with synaptopodin.

Figure 7

Segmented glomeruli in kidney samples stained with WT1.

Details

Quantitative Output variables

The output variable obtained from this protocol is:

Total Glomeruli Count

Workflow

Step 1: Load an image

Step 2: Load and run the APP “10145 – IHC, Glomeruli Detection, AI”

Methods

The architectural structure of the deep learning network is a U-Net which is popular for medical image segmentation. The neural network uses a cascade of layers of nonlinear processing units for feature extraction and transformation, with each successive layer using the output from the previous layers as input. U-Net uses an encoder-decoder structure with a contracting path and an expansive path. For more information of the network architecture, see [1].

Staining Protocol

There is no staining protocol available.

Additional information

To run the APP, a NVIDIA GPU with minimum 4 GB RAM is required.

Keywords

Immunohistochemistry, IHC, Kidney, Glomerulus, Glomeruli, Artificial Intelligence, AI, Deep Learning, Image Analysis, Digital Pathology

References

LITERATURE

1. Ronneberger, O. et al. U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015, 234-241, DOI.