Journal: Diagnostics
Article Title: RL-Cervix.Net: A Hybrid Lightweight Model Integrating Reinforcement Learning for Cervical Cell Classification
doi: 10.3390/diagnostics15030364
Figure Lengend Snippet: Representative images from each category in three open-access datasets: ( a ) The HErlev dataset comprises seven distinct categories of cervical cells, ranging from normal to abnormal. This dataset contains 917 single-cell images, primarily used for developing and evaluating diagnostic models. ( b ) The SipaKMeD dataset includes five cytological cell types—parabasal, superficial-intermediate, koilocytotic, dyskeratotic, and metaplastic—captured from 966 full-slide images. ( c ) The Mendeley dataset, based on liquid-based cytology (LBC) techniques, categorizes cervical lesions into normal and abnormal cases, including Negative for Intraepithelial Lesion or Malignancy (NILM), Low-grade Squamous Intraepithelial Lesion (LSIL), High-grade Squamous Intraepithelial Lesion (HSIL), and Squamous Cell Carcinoma (SCC). It contains 963 images derived from 460 patient samples.
Article Snippet: The Mendeley LBC dataset [ ] contains 963 liquid-based cytology (LBC) images derived from the Pap smears of 460 patients.
Techniques: Diagnostic Assay, Derivative Assay