Neural networks speed up holographic imaging

Researchers have developed a holographic technique that can rapidly reconstruct microscopic images of samples with up to 50-fold acceleration compared to existing methods.

Photo
UCLA researchers demonstrated holographic imaging using recurrent neural networks (RNN). A human lung tissue section is imaged with faster and better hologram reconstruction.
Source: UCLA Engineering Institute for Technology Advancement

Digital holographic imaging is a commonly used microscopy technique in biomedical imaging. It reveals rich optical information of the sample, which could be used, for example, to detect pathological abnormalities in tissue slides. Common image sensors only respond to the intensity of the incoming light. Therefore, reconstructing the complete 3D information of a hologram that is digitally recorded by such sensors has been a challenging task involving optical phase retrieval, which is a time-consuming and computationally intensive step in digital holography.

A research team at UCLA has recently developed a novel holographic phase retrieval technique that can rapidly reconstruct microscopic images of samples with up to 50-fold acceleration compared to existing methods. This new technique is taking advantage of recurrent neural networks trained using deep learning and incorporates spatial features from multiple holograms to digitally create holographic microscopy images of samples, such as human tissue slides. This results in better image quality and faster reconstruction speed, while also enhancing the depth-of-field of the reconstructed sample volume.

 UCLA researchers showed the effectiveness of this new holographic imaging method through experiments performed on human lung tissue sections and Pap smears, commonly used for screening of cervical cancer. These results report the first demonstration of the use of recurrent neural networks for holographic imaging and phase recovery, and also open up new opportunities for designing improved holographic microscopes with reduced number of measurements and increased imaging speeds.

"This framework can be broadly applicable to various biomedical imaging modalities, including for example fluorescence microscopy, to efficiently utilize a sequence of acquired images to rapidly and accurately create 3D reconstructions of a sample volume," said Dr. Aydogan Ozcan, the Chancellor's Professor of Electrical and Computer Engineering at UCLA and an associate director of the California NanoSystems Institute, who is the senior corresponding author of the work.

This work was published in ACS Photonics.

Subscribe to our newsletter

Related articles

Using AI to generate 3D holograms in real-time

Using AI to generate 3D holograms in real-time

A new method called tensor holography could enable the creation of holograms for virtual reality, 3D printing, medical imaging, and more — and it can run on a smartphone.

AI, holographic microscopy beat scientists at analyzing immunotherapy​

AI, holographic microscopy beat scientists at analyzing immunotherapy​

AI is helping researchers decipher images from a new holographic microscopy technique needed to investigate a key process in cancer immunotherapy “live” as it takes place.

Deep learning-based holographic point-of-care sensor

Deep learning-based holographic point-of-care sensor

Researchers have developed a rapid and cost-effective particle agglutination based sensor that is powered by holographic imaging and deep learning

Deep learning helps visualize X-ray data in 3D

Deep learning helps visualize X-ray data in 3D

Scientists have leveraged artificial intelligence to train computers to keep up with the massive amounts of X-ray data taken at the Advanced Photon Source.

Deep learning predicts viral infections

Deep learning predicts viral infections

Using fluoresence images from live cells, researchers have trained an artificial neural network to reliably recognize cells that are infected by adenoviruses or herpes viruses.

Deep learning predicts lung cancer risk

Deep learning predicts lung cancer risk

An artificial intelligence (AI) program accurately predicts the risk that lung nodules detected on screening CT will become cancerous, according to a new study.

AI makes great microscopes better than ever

AI makes great microscopes better than ever

Machine learning helps some of the best microscopes to see better, work faster, and process more data.

AI method can detect precursors to cervical cancer

AI method can detect precursors to cervical cancer

Using AI and mobile digital microscopy, researchers hope to create screening tools that can detect precursors to cervical cancer in women in resource-limited settings.

Deep learning tool to revolutionize microscopy

Deep learning tool to revolutionize microscopy

Researchers have developed a deep learning tool that offers new opportunities for analyzing images taken with microscopes.

Popular articles

Subscribe to Newsletter