Magnification-Scheduled Tile Routing for Whole-Slide Tumor Grading

Whole-slide pathological images contain gigapixel-level visual information, but only a small proportion of tissue regions are directly relevant to tumor grading. Processing all tiles at the same magnification creates heavy computational burden and may delay clinical screening. This study investigates efficient whole-slide tumor grading through magnification-scheduled tile routing. We propose HistoRoute, a tile-level routing model that assigns different magnification paths according to tissue foreground ratio, nuclear density, glandular boundary irregularity, and tumor-region uncertainty. Low-risk stromal and background regions are processed at low magnification, suspicious epithelial regions are examined at medium magnification, and high-uncertainty tumor margins are retained for high-magnification transformer encoding. A multiple-instance learning classifier then aggregates routed tile features into slide-level predictions. The study used 7,840 whole-slide images from breast, colorectal, and gastric cancer cohorts, including 3.2 million annotated tissue tiles and 18,600 pathologist-marked tumor regions. HistoRoute examined only 28.4% of all candidate high-resolution tiles while maintaining slide-level diagnostic performance. For tumor grading, the macro-AUC reached 0.914, compared with 0.919 for the full-tile transformer and 0.872 for a uniform low-resolution model. In external testing across two hospitals, grade-level agreement with pathologist labels improved from 0.781 to 0.836 Cohen’s kappa compared with random tile sampling. The average slide-processing time decreased from 96.5 seconds to 38.7 seconds, and disk read volume was reduced by 52.1%. Small invasive foci below 0.5 mm were still detected with 89.3% sensitivity. These findings suggest that magnification-aware tile routing can reduce computational cost while preserving clinically important pathological structures.

1. Butt, N. A., Sarwat, D., Noya, I. D., Tutusaus, K., Samee, N. A., & Ashraf, I. (2026). Benchmarking multiple instance learning architectures from patches to pathology for prostate cancer detection and grading using attention-based weak supervision. Scientific Reports, 16(1), 11535.
2. Jiao, Y., Shi, T., Zhao, B., & Wang, A. (2026). Retrieval-Guided Structured Reasoning and Interpretable Representation Learning for Large-Scale Video–Language Models.
3. Liang, S., Du, Y., Chen, W., & Liu, Z. (2026). Order Allocation and Emergency Transportation Decisions Amid Multi-Source Procurement Disruptions.
4. Zhang, Z., Wang, J., Li, Z., Wang, Y., & Zheng, J. (2025). Anncoder: A mti-agent-based code generation and optimization model. Symmetry, 17(7), 1087.
5. Kavitha, A. (2026, June). Cross-Domain Transfer Learning and Self-Supervised Representation Learning for Automated Histopathological Image Classification in Colorectal Cancer Grading System. In 2026 7th International Conference on Inventive Research in Computing Applications (ICIRCA) (pp. 2044-2050). IEEE.
6. Bao, Y., Qiu, Y., & Wang, H. (2026). FLARE: A Real-Time Framework for Detecting Malicious Account Activities at Internet Scale. Available at SSRN 7185659.
7. Wang, S., Feng, Y., & Fang, X. (2026, May). A Large Language Model-Enabled Multi-Agent Collaboration Method for Complex Task Solving. In 2026 6th International Symposium on Computer Technology and Information Science (ISCTIS) (pp. 253-256). IEEE.
8. Brunet, E. (2026). Contributions to Resource-Efficient HPC: A Data-Centric Approach (Doctoral dissertation, Institut polytechnique de Paris).
9. Yang, Q., & Du, Y. (2026). Predicting Rollback Risks and Controlling Gradual Rollout Traffic for Online Ranking Feature Deployments.
10. Zhao, Z., & Welsch, R. E. (2026). Point-in-Time Financial RAG with Frozen LLMs and Market-Feedback Adaptive Retrieval. arXiv preprint arXiv:2605.31201.
11. Yuan, Y., Huang, J., Yin, J., & Xu, T. (2026). Confidence Calibration and Semantic Error Analysis for Ambiguous Coreference Resolution in User-generated Social Media Text. Available at SSRN 7393238.
12. Ferreira, F. R. T., & do Couto, L. M. (2025). Explainable machine learning framework integrating PPPM for automated cytological triage and personalized breast cancer risk stratification. Network Modeling Analysis in Health Informatics and Bioinformatics, 14(1), 167.
13. Liang, S., Hsu, K. H., & Liu, Z. (2026). Rolling Scheduling and Capacity Balancing for Server Assembly Under Engineering Change Disturbances.
14. Bao, Y., & Wang, H. (2026). Large-scale Metrics Migration: A Systematic Approach to Rebuilding Production Measurement Infrastructure. Available at SSRN 7185660.
15. Yuan, Y., Yin, J., Huang, J., & Xu, T. (2026). Weakly Supervised Anomaly Detection and Privacy Risk Scoring in Community Message Threads.
16. Büchel, J., Vasilopoulos, A., Simon, W. A., Boybat, I., Tsai, H., Burr, G. W., ... & Sebastian, A. (2025). Efficient scaling of large language models with mixture of experts and 3D analog in-memory computing. Nature Computational Science, 5(1), 13-26.
17. Xu, D., Gui, H., & Chen, H. (2026, March). Research on Layered Control and Fault Recovery Mechanisms for Fast Charging Safety Diagnosis of High-Voltage Battery Systems Under Charging Network Interoperability Conditions. In 2026 3rd International Conference on Electrical Technology and Automation Engineering (ETAE) (pp. 669-672). IEEE.
18. Zhang, Z. (2026). A Study on the Impact of Cost Presentation on Decision-making Bias and Cancellation Behavior in Online Subscriptions. Available at SSRN 7349839.
19. Qi, C., & Qiao, X. (2026). Building and Operating a Large Scale Multi-Agent System: A Case Study from Industry. Available at SSRN 6795198.
20. Casper, M. J. (2025). Human Brain Optimized Light Sheet Microscopy (HOLiS) for High-Throughput Cell Type Atlasing of Whole Human Brains (Doctoral dissertation, Columbia University).
21. Xiong, W., Guo, Y., & Zeng, Y. (2026). A Study on the Energy Efficiency of MEP Systems and Coordinated Dispatch Mechanisms for Multi-energy Systems in High-density Urban Buildings. Available at SSRN 7120518.
22. Hong, Z., Liang, S., Xu, T., & Chen, H. (2026). A Study on Failover Verification and Recovery Objective Prediction for Cross-Region Cloud Services.
23. Hamza, A., & Damaševičius, R. (2026). Deep learning for brain tumor segmentation and classification: a systematic review of methods and trends. Computers, materials and continua., 86(1), 1-41.
24. Huang, J., Yin, J., Xu, T., & Yang, J. (2026). Quality Assessment and User Adoption Prediction for Enterprise-Level Financial Reporting Data Products. Available at SSRN 7179118.
25. Zheng, J., & Makar, M. (2022). Causally motivated multi-shortcut identification and removal. Advances in Neural Information Processing Systems, 35, 12800-12812.
26. Yao, G., Zheng, J., Wang, Z., Zhang, W., Han, R., Zhao, C., ... & Liu, R. (2026, March). V-pruner: A fast and globally-informed token pruning framework for vision transformer. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 40, pp. 34396-34404).
27. Gensbigler, P. A., Foster, W., Kiemen, A. L., & Bever, G. S. (2025). An optimized, high‐throughput workflow for the collection, processing, and visualization of histology data in comparative vertebrate morphogenesis. Developmental Dynamics.
28. Zhao, J., Fan, J., & Li, L. (2026). A Study on an Explainable Causal-Enhanced LLM Agent for Predicting the Forming Quality of Automotive Component Materials.
29. You, S. (2026). Verifiable Audit Mechanisms in AI Compliance Automation: Scalability. Available at SSRN 6547458.
30. Jimenez, M., Flandes, J., van der Heijden, E. H., Ng, C. S., Iding, J. S., Garcia‐Hierro, J. F., ... & Krimsky, W. S. (2025). Safety and Feasibility of Pulsed Electric Field Ablation for Early‐Stage Non‐Small Cell Lung Cancer Prior to Surgical Resection. Journal of Surgical Oncology, 131(8), 1529-1542.