In a groundbreaking study published in BME Frontiers, researchers from the University of California, Los Angeles (UCLA), in collaboration with international partners, have developed a deep learning-based virtual multiplexed immunostaining (mIHC) method. This novel approach enables the simultaneous generation of ERG, PanCK, and H&E images from label-free tissue sections, significantly enhancing the accuracy and efficiency of vascular invasion assessment in thyroid cancer.
Traditional immunohistochemistry (IHC) techniques, which are pivotal in diagnosing various cancers, require separate tissue sections for each stain, leading to increased costs, labor, and potential tissue loss. Moreover, these methods exhibit section-to-section variability, compromising diagnostic precision. Multiplexed IHC (mIHC) technologies, although capable of simultaneous staining with multiple antibodies, are complex and not widely available in routine pathology labs.
The research team, led by Aydogan Ozcan and Nir Pillar from UCLA, addressed these challenges by introducing a virtual mIHC framework that leverages deep learning algorithms. This technique utilizes autofluorescence microscopy images of unstained tissue sections to generate virtual stains that closely match their histochemically stained counterparts. The virtual stains include ERG for endothelial cells, PanCK for epithelial cells, and H&E for general tissue morphology.
The virtual mIHC method was trained and validated using a dataset comprising paired autofluorescence and histochemically stained images from thyroid tissue microarrays. By employing conditional generative adversarial networks (cGANs) and a digital staining matrix, the framework successfully converted label-free images into virtually stained ones, achieving high concordance with traditional staining methods.
Blind evaluations by board-certified pathologists confirmed the efficacy of the virtual mIHC staining, with strong agreement in staining patterns, intensity, and cellular localization. The virtual stains accurately highlighted epithelial and endothelial cells, facilitating the identification and localization of vascular invasion—a critical step in cancer metastasis.
The virtual mIHC technique represents a significant advancement in histopathological evaluation, offering a cost-effective, efficient, and accurate alternative to conventional IHC and mIHC methods. By streamlining the diagnostic workflow and preserving valuable tissue samples, this innovation has the potential to transform clinical practice, improving patient outcomes in thyroid cancer and beyond. The research team's future work will focus on further validating the technology across diverse tissue types and multi-site cohorts, paving the way for broader clinical adoption.
