Deep learning creates virtual multiplexed immunostaining to improve cancer diagnosis
The Californer/10336232

LOS ANGELES - Californer -- Researchers at the University of California, Los Angeles (UCLA), in collaboration with pathologists from Hadassah Hebrew University Medical Center and the University of Southern California, have developed a deep learning–based method that can digitally generate multiple immunohistochemical stains from a single, unstained tissue section. The approach enables accurate assessment of vascular invasion—a key indicator of cancer aggressiveness—without the need for conventional chemical staining procedures.

The study introduces a virtual multiplexed immunostaining (mIHC) framework that transforms autofluorescence microscopy images of label-free tissue into brightfield-equivalent images of hematoxylin and eosin (H&E) staining as well as two clinically important immunohistochemical markers: ERG, which labels endothelial cells, and PanCK, which highlights epithelial tumor cells. These virtual stains are generated simultaneously on the same physical tissue section using a single deep neural network.

More on The Californer

• New Book Reveals The Science Of Predictions
• Governor Newsom calls FCC Chair Brendan Carr a "disgrace," says California will lead more antitrust enforcement to protect consumers from Trump's rising costs
• California doubles down on ocean health with historic investments, following landmark report findings
• New Dosio App Helps GLP-1 Users Track Shots, Side Effects, and Weight Trends
• Rachel Farris, CPA and Founder of Tax Stack AI, Featured on The Big 4 Transparency Podcast

Vascular invasion—defined as the presence of tumor cells within blood or lymphatic vessels—is a critical prognostic factor across many solid tumors, including thyroid cancer. However, its identification in routine pathology can be challenging. Traditional workflows rely on H&E slides followed by immunohistochemical staining on serial tissue sections, a process that is labor-intensive, costly, and prone to tissue loss and section-to-section variability.

The method is based on imaging unstained tissue using autofluorescence microscopy, followed by computational transformation using a conditional generative adversarial network. A digital staining matrix guides the network to generate different virtual stains from the same input image, ensuring precise spatial alignment between H&E and immunohistochemical outputs.

Researchers applied the virtual mIHC framework to thyroid tissue microarrays and compared the digitally generated stains with conventional histochemical staining. Board-certified pathologists evaluated the images in a blinded study and found high concordance between virtual and traditional stains, with virtual staining often demonstrating superior consistency and specificity.

More on The Californer

• Compliance Alert: Maryland, Texas Regulate Use of Artificial Intelligence in Utilization Reviews
• When the Wrong Word Can Cost Everything, You Need a Legal Translation Partner You Can Actually Trust
• News you won't see on Fox News: California revoked over 280 hospice licenses, 300 more providers under investigation since Governor Newsom's hospice moratorium
• Colony Ridge Communities Celebrates Successful Soccer Season Kickoff with Families and Youth
• One Circle Foundation Launches Calm & Connected, a New Youth Mental Health Curriculum

Because the stains are generated computationally, the results are highly reproducible and free from many of the artifacts seen in conventional immunohistochemistry, said Nir Pillar, a pathologist at Hadassah Hebrew University Medical Center and a corresponding author of the study. This has the potential to significantly improve diagnostic accuracy while reducing cost and turnaround time.

The virtual multiplexed immunostaining framework is compatible with existing digital pathology workflows and requires only a single tissue section. After training, the system can generate virtual stains in seconds for individual fields of view and in minutes for whole-slide images, making it suitable for high-throughput clinical environments.

The study was conducted by Yijie Zhang, Çağatay Işıl, Xilin Yang, Yuzhu Li, Anna Elia, Karin Atlan, William Dean Wallace, Nir Pillar, and Aydogan Ozcan. The work was supported by the U.S. National Institutes of Health. Ozcan is also a co-founder of Pictor Labs, a UCLA spin-off company commercializing virtual staining technologies.

Article: https://spj.science.org/doi/10.34133/bmef.0226