A Cytology Dataset for Early Detection of Oral Squamous Cell Carcinoma

2025-06-11

AI Summary

Early diagnosis of oral squamous cell carcinoma (OSCC) in resource-limited settings faces challenges including invasive procedures, heavy reliance on scarce pathology expertise, and insufficient infrastructure for histopathological analysis. Method: We introduce the first large-scale, multicenter, multistain (Papanicolaou/May–Grunwald–Giemsa) benchmark dataset for oral exfoliative cytology, comprising samples from 10 tertiary care centers across India and annotated at the cellular level by expert pathologists. Contribution/Results: This dataset is the first publicly released resource enabling domain-generalizable AI modeling across institutions and staining protocols—addressing a critical gap in oral cytology AI research. It supports training of CNNs, Vision Transformers (ViTs), and integration with domain adaptation and weakly supervised learning frameworks. Our approach significantly reduces dependence on expert pathologists and inter-observer variability, offering a deployable, low-cost, non-invasive AI-assisted screening solution for low-resource settings—potentially improving early OSCC detection rates and patient survival.

Technology Category

• Humans and AI: Crowd Sourcing and Human Computation
• Computer Vision: Other Foundations of Computer Vision
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Oral squamous cell carcinoma OSCC is a major global health burden, particularly in several regions across Asia, Africa, and South America, where it accounts for a significant proportion of cancer cases. Early detection dramatically improves outcomes, with stage I cancers achieving up to 90 percent survival. However, traditional diagnosis based on histopathology has limited accessibility in low-resource settings because it is invasive, resource-intensive, and reliant on expert pathologists. On the other hand, oral cytology of brush biopsy offers a minimally invasive and lower cost alternative, provided that the remaining challenges, inter observer variability and unavailability of expert pathologists can be addressed using artificial intelligence. Development and validation of robust AI solutions requires access to large, labeled, and multi-source datasets to train high capacity models that generalize across domain shifts. We introduce the first large and multicenter oral cytology dataset, comprising annotated slides stained with Papanicolaou(PAP) and May-Grunwald-Giemsa(MGG) protocols, collected from ten tertiary medical centers in India. The dataset is labeled and annotated by expert pathologists for cellular anomaly classification and detection, is designed to advance AI driven diagnostic methods. By filling the gap in publicly available oral cytology datasets, this resource aims to enhance automated detection, reduce diagnostic errors, and improve early OSCC diagnosis in resource-constrained settings, ultimately contributing to reduced mortality and better patient outcomes worldwide.

Problem

• Early detection of oral squamous cell carcinoma globally
• Overcoming limitations of traditional histopathology in low-resource settings
• Addressing lack of large labeled datasets for AI solutions

Innovation

• Large multicenter oral cytology dataset
• AI-driven cellular anomaly classification
• PAP and MGG stained slides