Medical specialty dedicated to analyzing tissues and cells
In 2025, 95% of cancer diagnosis rely on surgical pathology.
As demand grows, pathologists are under increasing pressure to deliver faster results while maintaining exceptional accuracy.
Despite recent advances in digital pathology and AI tools, two bottlenecks remain:Â staining samples and interpreting them efficiently.
Infrared imaging for enhanced digital staining
MIRStain uses infrared light to caracterize biological tissues. Our deep learning model then use these data to digitaly stain samples. This allows to skip chemical staining processes, cuting down on cost and time-to-result. This process can also be used for diagnosis and metabolomics.
Duraffourg, L., Borges, H., Fernandes, M., Beurrier-Bousquet, M., Baraillon, J., Vianey, K., et al. (2025). Pre-print.
In this work, we introduce a fast, large-field bimodal imaging platform that combines conventional brightfield microscopy with a lensless infrared imaging scanner capable of acquiring whole-slide IR image stacks within minutes. Leveraging a dedicated deep learning model, we implement…
In a few pages, get a full overview of the context of our work and the ambitions of ADMIR regarding Anatomic Pathology.