Trending...
- AI Visibility: The Key to Beating Google's AI Overviews and Regaining Traffic
- New Mobile Car Detailing Platform Connects Drivers with On-Demand Local Pros
- Cal State LA secures funding for two artificial intelligence projects from CSU
LOS ANGELES - Californer -- Deep learning has achieved benchmark results for various imaging tasks, including holographic microscopy, where an essential step is to recover the phase information of samples using intensity-only measurements. By training on well-designed datasets, deep neural networks have proven to outperform classical phase retrieval and hologram reconstruction algorithms in terms of accuracy and computational efficiency. However, model generalization, which refers to extending the neural networks' capabilities to new types of samples never seen during the training, remains a challenge for existing deep learning models.
UCLA researchers have recently created a novel neural network architecture, termed Fourier Imager Network (FIN), which demonstrated unprecedented generalization to unseen sample types, also achieving superior computational speed in phase retrieval and holographic image reconstruction tasks. In this new approach, they introduced spatial Fourier transform modules that enable the neural network to take advantage of the spatial frequencies of the whole image. UCLA researchers trained their FIN model on human lung tissue samples and demonstrated its superior generalization by reconstructing the holograms of human prostate and salivary gland tissue sections, and Pap smear samples, which were never seen in the training phase.
More on The Californer
Published in Light: Science & Applications, a journal of Springer Nature, this new deep learning-based framework is reported to achieve higher image reconstruction accuracy compared to the classical hologram reconstruction algorithms and the state-of-the-art deep learning models, while shortening the reconstruction time by ~50 times. This new deep learning framework can be broadly used to create highly generalizable neural networks for various microscopic imaging and computer vision tasks.
This research was led by Dr. Aydogan Ozcan, Chancellor's Professor and Volgenau Chair for Engineering Innovation at UCLA and HHMI Professor with the Howard Hughes Medical Institute. The other authors of this work include Hanlong Chen, Luzhe Huang, and Tairan Liu, all from the Electrical and Computer Engineering department at UCLA. Prof. Ozcan also has UCLA faculty appointments in the bioengineering and surgery departments and is an associate director of the California NanoSystems Institute.
See article: https://www.nature.com/articles/s41377-022-00949-8
UCLA researchers have recently created a novel neural network architecture, termed Fourier Imager Network (FIN), which demonstrated unprecedented generalization to unseen sample types, also achieving superior computational speed in phase retrieval and holographic image reconstruction tasks. In this new approach, they introduced spatial Fourier transform modules that enable the neural network to take advantage of the spatial frequencies of the whole image. UCLA researchers trained their FIN model on human lung tissue samples and demonstrated its superior generalization by reconstructing the holograms of human prostate and salivary gland tissue sections, and Pap smear samples, which were never seen in the training phase.
More on The Californer
- Blake Harris the Leading Authority in International Asset Protection Joins Tom Hegna on "Financial Freedom with Tom Hegna"
- Wise Business Plans Emerges as a Go-To Partner for Angel Investors, VCs, Family Offices and Private
- Psychedelics for Vets? CCHR Cites History of Exploitation and Failed Science
- Neurocrine Biosciences Presents One-Year Data Showing Sustained Efficacy of CRENESSITY® (crinecerfont) in Adult Patients, at ENDO 2025
- Mike Diamond Offers $775 Off Full Heating & A/C Installation for a Limited Time
Published in Light: Science & Applications, a journal of Springer Nature, this new deep learning-based framework is reported to achieve higher image reconstruction accuracy compared to the classical hologram reconstruction algorithms and the state-of-the-art deep learning models, while shortening the reconstruction time by ~50 times. This new deep learning framework can be broadly used to create highly generalizable neural networks for various microscopic imaging and computer vision tasks.
This research was led by Dr. Aydogan Ozcan, Chancellor's Professor and Volgenau Chair for Engineering Innovation at UCLA and HHMI Professor with the Howard Hughes Medical Institute. The other authors of this work include Hanlong Chen, Luzhe Huang, and Tairan Liu, all from the Electrical and Computer Engineering department at UCLA. Prof. Ozcan also has UCLA faculty appointments in the bioengineering and surgery departments and is an associate director of the California NanoSystems Institute.
See article: https://www.nature.com/articles/s41377-022-00949-8
Source: UCLA ITA
Filed Under: Science
0 Comments
Latest on The Californer
- Montana-Inspired Music Team Scores Multiple International Nominations
- Mike Diamond Offers Free Sewer Camera Inspections to Help Homeowners Catch Problems Early
- Mike Diamond Offers $99 Priority & Premium Air Conditioning Protection in Anaheim, CA
- Garmin Approach R50: Redefining Home Golf Simulation
- California: Governor Newsom statement on the court temporarily blocking the Trump Administration's unlawful immigration tactics in the Los Angeles area
- Governor Newsom urges Californians to take precautions as state endures triple digit heat, smoky conditions
- Yvette Kendall Secures $6 Million Deal with The Sessions Studios for Horror Thriller, "NORTH"
- Buy The Crave Launches Premium Creatine and Natural Wellness Supplements for Modern Lifestyles
- Long Beach Parks, Recreation and Marine's Homeland Cultural Center Presents DanceFest at Cesar Chavez Park Amphitheater on August 16
- Sisu, a Portrait of Grit, Connection and Triumph, Premieres on Documentary Showcase
- New Liz Taylor Book Coming Soon: Chasing Elizabeth Taylor
- City of Long Beach Experienced a 4% Decrease in Fireworks-Related Reports on July 4
- The Blue Luna Encourages Local Schools to Take Steps to Enhance Safety for Students and Staff
- Wise Business Plans Launches Turnkey Startup Packages to Help Entrepreneurs Start and Scale
- CarSeek Re-Launch: A New Look, A Better Experience for Car Buyers
- California: Governor Newsom provides $11 million to organizations helping underserved job seekers find training and employment
- For Artificial Intelligence Appreciation Day: Celebrate it with a poem about AI called "Robot Love"
- City of Long Beach Shares Federal Funding Updates and Local Impacts
- The Sessions Studios Secures $300 Million Commitment to Launch World-Class Studio and 15-Film Global Slate
- Fortrea Holdings Inc. (FTRE) Investors Who Lost Money Have Opportunity to Lead Securities Fraud Lawsuit