RACR-MIL: Rank-aware contextual reasoning for weakly supervised grading of squamous cell carcinoma using whole slide images
This addresses the challenge of SCC grading for pathologists, offering a clinically viable assistant with improved efficiency in 60% of cases, though it is incremental as it builds on existing attention-based MIL frameworks.
The paper tackled the problem of grading squamous cell carcinoma from whole slide images by proposing RACR-MIL, a weakly-supervised method that achieved 3-9% higher grading accuracy and up to 16% improved tumor localization across multiple anatomies.
Squamous cell carcinoma (SCC) is 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 reliable protocol and substantial tissue heterogeneity. We propose RACR-MIL, the first weakly-supervised SCC grading approach achieving robust generalization across multiple anatomies (skin, head and neck, lung). RACR-MIL is an attention-based multiple-instance learning framework that enhances grade-relevant contextual representation learning and addresses tumor heterogeneity through two key innovations: (1) a hybrid WSI graph that captures both local tissue context and non-local phenotypical dependencies between tumor regions, and (2) a rank-ordering constraint in the attention mechanism that consistently prioritizes higher-grade tumor regions, aligning with pathologists diagnostic process. Our model achieves state-of-the-art performance across multiple SCC datasets, achieving 3-9% higher grading accuracy, resilience to class imbalance, and up to 16% improved 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.