{
  "id": 14362894,
  "title": "Pan-cancer estimation of prognostic immune biomarkers from histopathology using artificial intelligence",
  "url": "https://urgent.news/2026/10/13/pan-cancer-estimation-of-prognostic-immune-biomarkers-from",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-13T00:00:00.000Z",
  "source": {
    "name": "bioRxiv",
    "slug": "biorxiv",
    "url": "https://www.biorxiv.org/content/10.64898/2026.10.06.757083v1?rss=1"
  },
  "original_language": "en",
  "account": "A new artificial intelligence model, named HistoProfile, has been developed to estimate immune biomarkers in cancer using routine histopathology images. Multiplex immunofluorescence assays, such as ImmunoProfile, offer standardized quantification of these markers but are costly and not commonly used in clinical practice. HistoProfile was trained on a diverse cohort of cancers with both histopathology and multiplex imaging data. The AI model accurately discriminated between tumors with high and low levels of key immune biomarkers, including CD8, FOXP3, PD-1, and PD-L1, as well as the PD-L1 tumor proportion score. This discrimination was consistent across different tumor types in separate samples and even in specific cancer subgroups. Importantly, the estimated immune biomarkers maintained their prognostic value in subsequent survival analyses. Furthermore, the H&E-based estimates provided cancer-specific survival associations, even in cases where multiplex imaging data was not available. These results suggest that H&E-stained whole-slide images could be utilized for large-scale, scalable immune profiling and risk stratification in cancer patients.",
  "summary": "Multiplex immunofluorescence (mIF) assays such as ImmunoProfile provide standardized quantification of prognostic immune markers but are costly and not routinely used in clinical settings. We developed a weakly-supervised AI model, HistoProfile, to estimate intratumoral cell densities of key immune biomarkers (CD8, FOXP3, PD-1, and PD-L1) and the PD-L1 tumor proportion score from routine…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}