Saved in:
| Main Authors: | , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.17259913 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>This dataset presents a comparison between the <strong>original Mendeley LBC dataset</strong> and a <strong>reclassified subset</strong> 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:</p> <ul> <li> <p><strong>HSIL</strong> – High-Grade Squamous Intraepithelial Lesion</p> </li> <li> <p><strong>LSIL</strong> – Low-Grade Squamous Intraepithelial Lesion</p> </li> <li> <p><strong>Negative</strong> – Negative for Intraepithelial Lesion or Malignancy</p> </li> <li> <p><strong>SCC</strong> – Squamous Cell Carcinoma</p> </li> </ul> <p>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 <strong>original dataset</strong> to its <strong>corresponding new classification</strong>, if available:</p> <ul> <li> <p>If an image appears in both the original and new datasets, the file lists both its <code>original_class</code> and <code>new_class</code>.</p> </li> <li> <p>If an image is present in the original dataset but not in the reclassified dataset, the <code>new_class</code> field is left empty.</p> </li> </ul> <p>This structure enables researchers to:</p> <ul> <li> <p>Audit which images were excluded.</p> </li> <li> <p>Cross-check consistency between original and reclassified sets.</p> </li> <li> <p>Benchmark new algorithms using either the full original dataset or the curated subset.</p> </li> </ul> <h3> Original Dataset Attribution</h3> <p>The images included in this dataset were originally published as part of the <strong>Mendeley LBC dataset</strong>:</p> <p> <strong>Citation</strong>: Hussain, Elima (2019), <em>“Liquid based cytology pap smear images for multi-class diagnosis of cervical cancer”</em>, <strong>Mendeley Data</strong>, V4. <a target="_new" rel="noopener">https://doi.org/10.17632/zddtpgzv63.4</a></p> <p> <strong>Original dataset repository</strong>: <a href="https://data.mendeley.com/datasets/zddtpgzv63/4" target="_new" rel="noopener">https://data.mendeley.com/datasets/zddtpgzv63/4</a></p> <p>Please ensure that both this reclassification work and the original dataset authors are appropriately cited in any derivative research.</p> <h3> License</h3> <p>This dataset is released under the <strong>Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)</strong> license.</p> <ul> <li> <p>✅ Use for <strong>academic and research purposes</strong> is permitted.</p> </li> <li> <p> <strong>Citation of the dataset authors is mandatory</strong>.</p> </li> <li> <p> <strong>Commercial use, redistribution, or modification is not allowed</strong> without prior written permission.</p> </li> </ul> <p>This dataset is intended <strong>solely for non-clinical, academic research</strong>. Diagnostic labels were provided for research and benchmarking purposes and have not undergone regulatory clinical validation.</p>