New end-to-end neural network called Fourier Imager Network (FIN) for rapid phase recovery and hologram reconstruction that achieves superior generalization to unseen sample types over the existing deep learning methods. (IMAGE)

Optica

New end-to-end neural network called Fourier Imager Network (FIN) for rapid phase recovery and hologram reconstruction that achieves superior generalization to unseen sample types over the existing deep learning methods.

Caption

A comparison of the internal and external generalization of FIN and RH-M on lung and salivary gland tissue sections and Pap smear samples. The reconstruction results of MH-PR using the same input holograms (M=3) are also shown for comparison.

Credit

Hanlong Chen, UCLA

Usage Restrictions

N/A

License

Original 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.