RACR-MIL: Rank-aware contextual reasoning for weakly supervised grading of squamous cell carcinoma using whole slide images
Squamous cell carcinoma (SCC) is one of the most common cancer subtype, with an increasing incidence and a significant impact on cancer-related mortality. SCC grading using whole slide images is inherently challenging due to the lack of a standardized grading protocol and substantial tissue heterogeneity. We propose RACR-MIL, a weakly-supervised SCC grading approach that achieves robust generalization across multiple anatomies (skin, head & neck, lung). RACR-MIL is an attention-based multiple-instance learning framework that introduces two key innovations for learning grade-specific contextual representations: (1) a hybrid WSI graph that captures both local tissue context and non-local phenotypic dependencies between tumor regions, and (2) rank-ordering constraints on the attention mechanism that encourage consistent prioritization of higher-grade tumor regions and improve region-level grade confidence, aligning with pathologist's diagnostic process. Our model achieves state-of-the-art performance across multiple SCC datasets, achieving 3-9% improvements over existing methods and up to 10% improvement in tumor localization. In a pilot study, pathologists reported that RACR-MIL improved grading efficiency in 60% of cases, underscoring its potential as a clinically viable cancer diagnosis and grading assistant.