AI-based staining of biological samples
The Californer/10232191

LOS ANGELES - Californer -- Histological staining has been routinely carried out in pathology laboratories to assist in assessing pathophysiology and disease diagnostics. Despite its widespread use, standard histological staining procedures are plagued with drawbacks such as labor-intensive preparation, lengthy turnaround time, high costs, and inconsistent outcomes.

Virtual staining, a deep learning-based method to digitally generate histological stains, has the potential to revolutionize traditional histological staining workflows. By eliminating the need for chemical staining and toxic compounds, virtual staining provides a rapid, cost-effective, and accurate alternative to traditional staining methods, which can potentially improve the accuracy and speed of diagnoses, leading to better patient outcomes and reduced healthcare costs.

The Ozcan group at UCLA has recently published a Review paper on this emerging virtual staining technology. Titled "Deep Learning-enabled Virtual Histological Staining of Biological Samples," this Review paper provides a comprehensive overview of recent advances in the virtual staining field. It covers the basic concepts, the typical development workflow, key results and progress, and the future perspectives of deep learning-enabled virtual staining technology.

More on The Californer

• "Great American Family to Premiere Christmas at Mistletoe Manor
• Demystifying CBD & THC Levels: Ayah Labs' Easy-to-Follow Quantification Guide
• Controversial Vegan Turns Rapper Launches First Song, "Psychopathic Tendencies."
• Inside the Fight for Affordable Housing: Avery Headley Joins Terran Lamp for a Candid Bronx Leadership Conversation
• Queen Sheba Ignites Global Movement with New TEDx Talk: "Reclaim They — The Pronoun of Genius"

Published in Light: Science & Applications, a journal of the Springer Nature, this paper provides a valuable resource for scholars, optical engineers, microscopists, computer scientists, biologists, histologists, and pathologists alike. "We believe this Review paper will serve as an atlas of the technical developments in this research area, providing a top-level understanding of the latest advancements in virtual staining," said Dr. Aydogan Ozcan, "and we hope it will inspire readers from diverse scientific fields to further expand the scope and applications of this exciting field and continue to push the boundaries of what is possible with virtual staining".

The Ozcan group is a research group based at the University of California, Los Angeles, dedicated to developing innovative optical imaging and analysis tools for various applications, including biomedicine, diagnostics, and environmental monitoring. The group is committed to advancing virtual staining technology and bringing this cutting-edge technology to the field of digital pathology using deep learning. The 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 Bijie Bai, Xilin Yang, Yuzhu Li, Yijie Zhang, and Nir Pillar, 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. He co-founded Pictor Labs, a company commercializing virtual staining technology.

More on The Californer

• Canterbury Hotel Group Announces the Opening of the TownePlace Suites by Marriott Portland Airport
• BrassTranscripts Publishes 13 Transcription Guides Covering Workflow-Specific Use Cases
• Unity to End Internal Support for Multiplay Game Server Hosting Service
• Heritage at South Brunswick's Resort-Style Amenities for Any Age and Every Lifestyle
• T-TECH Partners with Japan USA Precision Tools for 2026 US Market Development of the New T-TECH 5-Axis QUICK MILL™

This work was supported by the US National Science Foundation (NSF).

Original article: Bijie Bai, Xilin Yang, Yuzhu Li, Yijie Zhang, Nir Pillar, and Aydogan Ozcan "Deep Learning-enabled Virtual Histological Staining of Biological Samples", Light: Science & Applications (2023) https://www.nature.com/articles/s41377-023-01104-7