Mendeley LBC Image Reclassification Dataset: HSIL, LSIL, Negative, and SCC Labels for AI Research in Cytopathology

This dataset presents a comparison between the original Mendeley LBC dataset and a reclassified subset created for research in automated cytology and cervical cancer screening. The original dataset consists of Liquid-Based Cytology (LBC) smear images divided into four diagnostic categories: HSIL – High-Grade Squamous Intraepithelial Lesion LSIL – Low-Grade Squamous Intraepithelial Lesion Negative – Negative for Intraepithelial Lesion or Malignancy SCC – Squamous Cell Carcinoma In this new version, selected images have been retained and reclassified, while others were excluded based on diagnostic or technical criteria. To facilitate transparency and reproducibility, we provide a comprehensive CSV file that maps every image from the original dataset to its corresponding new classification, if available: If an image appears in both the original and new datasets, the file lists both its original_class and new_class. If an image is present in the original dataset but not in the reclassified dataset, the new_class field is left empty. This structure enables researchers to: Audit which images were excluded. Cross-check consistency between original and reclassified sets. Benchmark new algorithms using either the full original dataset or the curated subset. 🔗 Original Dataset Attribution The images included in this dataset were originally published as part of the Mendeley LBC dataset: 📄 Citation: Hussain, Elima (2019), “Liquid based cytology pap smear images for multi-class diagnosis of cervical cancer”, Mendeley Data, V4. https://doi.org/10.17632/zddtpgzv63.4 📂 Original dataset repository: https://data.mendeley.com/datasets/zddtpgzv63/4 Please ensure that both this reclassification work and the original dataset authors are appropriately cited in any derivative research. 🔒 License This dataset is released under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license. ✅ Use for academic and research purposes is permitted. 📌 Citation of the dataset authors is mandatory. 🚫 Commercial use, redistribution, or modification is not allowed without prior written permission. This dataset is intended solely for non-clinical, academic research. Diagnostic labels were provided for research and benchmarking purposes and have not undergone regulatory clinical validation.