2026-07-06 スタンフォード大学
＜関連情報＞
- https://news.stanford.edu/stories/2026/07/ai-platform-canvas-tumor-pathology
- https://www.cell.com/cell/fulltext/S0092-8674(26)00590-8
組織病理学に基づく細胞構造と近隣情報を考慮した仮想空間腫瘍プロファイリング Cellular architecture and neighborhood-informed virtual spatial tumor profiling from histopathology
Yuchen Li ∙ Zhe Li ∙ Ryan Quinton ∙ … ∙ Joel Neal ∙ Maximilian Diehn ∙ Ruijiang Li
Cell Published: June 16, 2026
DOI:https://doi.org/10.1016/j.cell.2026.05.031
Highlights
- Single-cell spatial proteomics atlas identifies cellular neighborhoods
- CANVAS predicts CNs from standard histology
- CANVAS enables virtual spatial profiling at the population level
- CANVAS identifies H&E-based spatial signature of immunotherapeutic outcome
Summary
The tumor microenvironment (TME) critically shapes disease progression and therapeutic resistance. However, a comprehensive understanding of its spatial architecture remains elusive, and clinical translation is challenging. Here, we present cellular architecture and neighborhood-informed virtual AI-driven spatial profiling (CANVAS), an artificial intelligence platform that infers tumor ecological habitats from hematoxylin and eosin (H&E) histopathology. Built on an atlas of over 18 million cells profiled by 41-plex spatial proteomics across 457 patients with non-small cell lung cancer, CANVAS establishes 10 reproducible cellular neighborhoods (CNs) capturing conserved spatial organization of the TME. Through multimodal alignment and foundation-model-based morphological encoding, CANVAS predicts CN-anchored habitat structures from H&E slides and enables clinical evaluation in over 5,000 patients spanning 9 cancer types. Across patient cohorts, CANVAS supports prognostic modeling, spatial ecotype stratification, and immunotherapy outcome prediction. These results establish CANVAS as a clinically scalable platform for spatial profiling, bridging single-cell analysis to population-level insight and enabling precision oncology.
