Network architecture of the virtual mIHC staining model. (IMAGE)

BMEF (BME Frontiers)

Network architecture of the virtual mIHC staining model.

Caption

This system used a cGAN architecture to design a virtual mIHC staining model that rapidly transforms label-free AF images (DAPI, FITC, TxRed, and Cy5) of tissue samples into their corresponding BF images for ERG, PanCK, and H&E virtual staining. The cGAN architecture includes 2 subnetworks, namely, a generator (G) and a discriminator (D). To enable the multiplexing feature for this virtual staining model, a DSM is concatenated with the label-free input images.

Credit

Ozcan Lab@UCLA.

Usage Restrictions

News organizations may use or redistribute this image, with proper attribution, as part of news coverage of this paper only.

License

Licensed content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.