RAA-MIL: A Novel Framework for Classification of Oral Cytology

2025-11-15

AI Summary

To address the low efficiency and high subjectivity of manual interpretation of whole-slide images (WSIs) in early screening of oral squamous cell carcinoma (OSCC), this paper proposes RAA-MIL—the first weakly supervised deep learning framework tailored for oral cytology. Built upon multiple-instance learning (MIL), RAA-MIL introduces a novel Region-Aware Affinity attention mechanism (RAA) that explicitly models spatial relationships among patches within WSIs, enabling patient-level automated diagnosis. We establish the first patient-level weakly supervised benchmark for oral cytology and evaluate RAA-MIL on a held-out test set, achieving 72.7% mean accuracy and a weighted F1 score of 0.69—substantially outperforming existing MIL baselines. This work advances the clinical deployment of AI in digital pathology and offers a new paradigm to reduce reliance on expert pathologists and improve accessibility of OSCC screening.

Technology Category

• Machine Learning: Active Learning
• Computer Vision: Other Foundations of Computer Vision
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Cytology is a valuable tool for early detection of oral squamous cell carcinoma (OSCC). However, manual examination of cytology whole slide images (WSIs) is slow, subjective, and depends heavily on expert pathologists. To address this, we introduce the first weakly supervised deep learning framework for patient-level diagnosis of oral cytology whole slide images, leveraging the newly released Oral Cytology Dataset [1], which provides annotated cytology WSIs from ten medical centres across India. Each patient case is represented as a bag of cytology patches and assigned a diagnosis label (Healthy, Benign, Oral Potentially Malignant Disorders (OPMD), OSCC) by an in-house expert pathologist. These patient-level weak labels form a new extension to the dataset. We evaluate a baseline multiple-instance learning (MIL) model and a proposed Region-Affinity Attention MIL (RAA-MIL) that models spatial relationships between regions within each slide. The RAA-MIL achieves an average accuracy of 72.7%, weighted F1-score of 0.69 on an unseen test set, outperforming the baseline. This study establishes the first patient-level weakly supervised benchmark for oral cytology and moves toward reliable AI-assisted digital pathology.

Problem

• Automating oral cancer detection from cytology slides to reduce manual analysis
• Addressing subjectivity in pathology diagnosis through deep learning models
• Developing weakly supervised classification for oral cytology whole slide images

Innovation

• Weakly supervised deep learning for oral cytology diagnosis
• Region-Affinity Attention MIL models spatial slide relationships
• Patient-level classification using cytology patches with weak labels