[Submitted on 27 Sep 2025 (v1), last revised 11 Oct 2026 (this version, v4)]
Abstract:Foundation models (FM) have transformed computational pathology but remain computationally prohibitive for clinical deployment due to their massive parameter counts and high-magnification processing requirements. Here, we introduce XMAG, a lightweight FM developed through corss-magnification distillation that transfers knowledge from state-of-the-art 20x magnification teacher to an efficient 5x magnification student architecture. XMAG employs a compact backbone and operates entirely at 5x, requiring 11.3 times fewer patches per whole slide image (WSI) compared to existing approaches. Our Novel distillation framework incorporates dual-level knowledge transfer, aligning both global image representations and local spatial token mapping. We trained XMAG on 3.49 million images curated from publicly available datasets and evaluated performance across six clinically relevant histopathology analysis tasks spanning multiple cancer types. XMAG achieved diagnostic accuracy within 1% of substantially larger foundation models while delivering 30-fold processing acceleration, reaching 8.8 WSIs per minute processing speed. Our cross-institutional validation confirmed robust generalization. Further, we developed an end-to-end training strategy to further boost our model’s performance to approach the larger FMs’ performance. These results establish cross-magnification distillation as a viable approach for deploying FM capabilities in resource-constrained clinical environments, potentially enabling real-time pathology AI integration.
Submission history
From: Ziyu Su [view email]
[v1] Sat, 27 Sep 2025 04:11:53 UTC (1,320 KB)
[v2] Wed, 1 Oct 2025 13:30:22 UTC (1,472 KB)
[v3] Wed, 11 Mar 2026 22:12:49 UTC (1,450 KB)
[v4] Sun, 11 Oct 2026 16:44:10 UTC (3,038 KB)
