Foundation models have emerged as a driving force in computational pathology, with the potential to transform cancer diagnosis, prognosis, and treatment selection by learning transferable representations from large-scale histopathology data. A growing landscape of pathology foundation models now spans diverse data sources, architectures, and downstream applications. However, most pretrained models operate only at the image-tile level, use restrictive licenses, and remain computationally expensive, limiting large-scale slide-level clinical and research use. Here, we introduce GigaPath-Flash and GigaTIME-Flash, efficient models for whole-slide pathology AI and spatial proteomics prediction. GigaPath-Flash combines a 22M-parameter ViT-S tile encoder with a 21M-parameter LongNet slide encoder, both pretrained on large-scale real-world histopathology data. Its compact tile encoder is distilled from the billion-parameter GigaPath (ViT-g) teacher and shared by both models. GigaPath-Flash retains 97% of GigaPath's average slide-level performance with 50x less compute. GigaTIME-Flash extends this backbone to predict the tumor immune microenvironment directly from routine H&E images. It surpasses the original CNN-based GigaTIME in prediction quality while running 6x faster and using 8x less GPU memory. Together with GigaPath and GigaTIME, these models form an open-weight, Apache-2.0-licensed family pretrained on large-scale real-world clinical data. By releasing all models and weights, we provide accessible building blocks for computational pathology, immuno-oncology, and precision health.
N. Usuyama, Jeya Maria Jose Valanarasu, Sicong Yao et al.· arXiv.org· 0 citations
The tumor microenvironment (TME) of pancreatic ductal adenocarcinoma (PDAC) is characterized by restrained function of effector T cells that drives resistance to immunotherapy. While tumor-extrinsic stroma and myeloid cells have been shown to mediate PDAC immune evasion, the role of tumor-intrinsic post-transcriptional gene regulation in driving tumor-immune crosstalk has been relatively unexplored. Here, we report that the RNA-binding protein HuR (ELAVL1) is enriched in human PDAC and negatively correlates with T-cell infiltration. In two immunocompetent, murine models of PDAC, we found that genetic disruption of HuR impaired tumor growth without significantly impacting in vivo proliferation. Comprehensive spatial and flow cytometry profiling of the PDAC TME revealed that genetic disruption of HuR in PDAC enhanced both T-cell number and functional state. Moreover, T-cell depletion abrogated the growth difference caused by HuR loss. Mechanistically, RNA immunoprecipitation sequencing, single-cell RNA sequencing, and orthogonal functional assays in vitro and in vivo showed that HuR stabilized mTOR pathway transcripts critical for metabolic adaptation in PDAC. HuR-driven metabolic reprogramming promoted tumor nutrient dominance and limited nutrient consumption by neighboring tumor-reactive T cells. Accordingly, HuR depletion sensitized PDAC tumors to immune checkpoint blockade and allowed for the expansion of tumor-specific T-cell populations, suggesting that HuR-mediated nutrient dominance and immune evasion have translational relevancy. Overall, we found that the post-transcriptional regulator HuR facilitates immune evasion in PDAC by constraining T-cell function, identifying HuR blockade as a promising therapeutic strategy in combination with immunotherapies.
Yi-Fei Guo, Jennifer M. Finan, Alexandra Q. Bartlett et al.· Cancer immunology research· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
