---
license: cc-by-nc-4.0
---

## An Ensemble-based Two-step Framework for Classification of Pap Smear Cell Images

### Code repository

The project source code: [GitHub Repository](https://github.com/theodpzz/ps3c).

### Available resources

Train weights for **Step 1** and **Step 2**, as well as the **per-class final predicted probabilities**, are provided in this repository.

### PS3C

This project was developed as part of the **PS3C Challenge** at **ISBI 2025**.  

Kaggle Challenge: [Kaggle Link](https://www.kaggle.com/competitions/pap-smear-cell-classification-challenge).

APACC Dataset original paper: [Paper access](https://www.nature.com/articles/s41597-024-03596-3).

### Citation

If you use this model or related resources, we would appreciate the following citation:

```BibTeX
@inproceedings{dipiazza2025ps3c,
  author    = {Di Piazza Theo and Loic Boussel},
  title     = {An Ensemble-based Two-step Framework for Classification of Pap Smear Cell Images},
  booktitle = {Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI)},
  year      = {2025},
  organization = {IEEE},
}
```