Stain-Free Imaging Platform Matches Standard Cancer Pathology

Conventional staining relies on chemical dyes and multiple preparation steps that add time and may affect image quality. A new study shows that a stain-free platform can generate diagnostic images comparable to standard staining while accelerating workflow and supporting algorithm development.

King Abdullah University of Science and Technology (KAUST; Thuwal, Saudi Arabia) has developed a stain-free imaging platform designed to analyze tissue samples more quickly and consistently. The approach replaces dyes with engineered silicon slides that produce detailed structural color images directly from tissue, enabling immediate microscopic assessment. The images are suitable for pathologist review and generate standardized digital data that could support future AI-assisted diagnosis.

The platform was first validated on colorectal tissue, a priority disease area in Saudi Arabia. In a head-to-head evaluation against conventional pathology, the stain-free method achieved 99% agreement in diagnostic conclusions for colorectal specimens. The study assessed tissue from 120 patients and found strong concordance in identifying healthy and cancerous features, while early results indicated a 40–50% reduction in sample preparation time compared with standard workflows.

The research is published in Advanced Science and aligns with KAUST’s Smart Health mission to advance technologies for cancer prevention, diagnosis, and treatment. KAUST is collaborating with King Faisal Specialist Hospital & Research Centre (KFSHRC) Madinah to further evaluate the platform across broader healthcare settings in Saudi Arabia. 

In addition to colorectal samples, tests on breast, lung, and thyroid tissues captured key histological features comparable to conventionally stained slides, supporting additional validation efforts. The team states the system was developed with practical deployment in mind and will continue to be assessed for clinical and commercial pathways.

“This research focuses on improving one of the most important steps in diagnosis: how tissue samples are prepared and reviewed,” said Qiaoqiang Gan, Professor of Material Science and Engineering at KAUST. “Traditional staining methods can be influenced by preparation steps, reagent quality, and laboratory conditions. By generating consistent digital images without dyes, we can reduce variability and create data that is more reliable for both clinical review and future AI-assisted analysis.”

Related Links
KAUST