After After
Before Before

10145 - 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.

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

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].

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”

STAINING PROTOCOL
There is no staining protocol available.

ADDITIONAL INFORMATION
To run the APP, a NVIDIA GPU with minimum 4 GB RAM is required.
The APP utilizes the Visiopharm Engine™, Engine™ AI and Viewer software modules, where Engine™ and Engine™ AI offer an execution platform to expand processing capability and speed of image analysis. The Viewer allows a fast review together with several types of image adjustment properties e.g. outlining of regions, annotations and direct measures of distance, curve length, radius, etc.
By adding the Author™  and/or Author™ AI modules the APP can be customized to fit other purposes. These modules offer a comprehensive and dedicated set of tools for creating new fit-for-purpose analysis APPs, and no programming experience is required.

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.

RUO
FIGURE 1
FIGURE 1
Segmented glomeruli in kidney samples stained with aSMA.
FIGURE 2
FIGURE 2
Segmented glomeruli in kidney samples stained with CD68.
FIGURE 3
FIGURE 3
Segmented glomeruli in kidney samples stained with Col1a1
FIGURE 4
FIGURE 4
Segmented glomeruli in kidney samples stained with ColIV.
FIGURE 5
FIGURE 5
Segmented glomeruli in kidney samples stained with nephrin.
FIGURE 6
FIGURE 6
Segmented glomeruli in kidney samples stained with synaptopodin.
FIGURE 7
FIGURE 7
Segmented glomeruli in kidney samples stained with WT1.