口腔鳞状细胞癌早期检测的口腔细胞学数据集

本数据集由印度10个三级医疗中心收集，包含用Papanicolaou和May-Grünwald-Giemsa协议染色的注释幻灯片，旨在推动基于人工智能的诊断方法。数据集包含234名患者的368张全切片图像，覆盖了广泛的年龄和性别范围。该数据集由专家病理学家进行注释，用于细胞异常分类和检测，旨在提高自动化检测的效率，减少诊断错误，并改善资源有限环境中的口腔鳞状细胞癌早期诊断。数据集已在Kaggle和Google Drive上公开，方便研究人员使用。

This dataset was collected from 10 tertiary care centers across India. It contains annotated slides stained using the Papanicolaou and May-Grünwald-Giemsa protocols, aiming to advance AI-driven diagnostic approaches. The dataset includes 368 whole-slide images from 234 patients, covering a broad spectrum of ages and genders. Annotated by expert pathologists, this dataset is intended for cellular abnormality classification and detection, with the goals of improving automated detection efficiency, reducing diagnostic errors, and enhancing early diagnosis of oral squamous cell carcinoma in resource-limited settings. The dataset has been publicly released on Kaggle and Google Drive to facilitate researchers' access and utilization.