README.md

---
title: Pcam Project
emoji: 🧬
colorFrom: green
colorTo: red
sdk: gradio
sdk_version: 5.34.1
app_file: app.py
pinned: false
license: gpl-3.0
python_version: 3.12.10
short_description: 'PCam Dataset: Tumor Detection Image Binary Classification'
---

# 🧬 PCam Dataset: Tumor Detection via Binary Image Classification
[![Hugging Face Spaces](https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/eloise54/pcam_project)
[![Kaggle Notebook](https://img.shields.io/badge/Kaggle-Notebook-blue?logo=kaggle)](https://www.kaggle.com/code/eloisedai/pcam-tumor-detection-full-pytorch-pipeline)
[![View](https://img.shields.io/badge/View-Notebook-blue?style=flat&logo=jupyter)](https://gitlab.com/nn_projects/pcam_project/-/blob/main/PCAM-pipeline.ipynb?ref_type=heads)
[![License: GPL-3.0](https://img.shields.io/badge/License-GPLv3-blue.svg)](LICENSE)

## ⚡ Try it now ! With gradio ⚡ 

On Hugging Face Spaces:

[![Hugging Face Spaces](https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/eloise54/pcam_project)

Or start the local gradio app

```python app.py```

## The full pytorch training jupter notebook is here:

You can view it here :

[![View](https://img.shields.io/badge/View-Notebook-blue?style=flat&logo=jupyter)](https://gitlab.com/nn_projects/pcam_project/-/blob/main/PCAM-pipeline.ipynb?ref_type=heads)

Or execute it on kaggle:

[![Kaggle Notebook](https://img.shields.io/badge/Kaggle-Notebook-blue?logo=kaggle)](https://www.kaggle.com/code/eloisedai/pcam-tumor-detection-full-pytorch-pipeline)


## 📊 Dataset Overview

https://github.com/basveeling/pcam

The **PatchCamelyon (PCam)** benchmark is a challenging image classification dataset designed for breast cancer detection tasks.

- 📦 **Total images**: 327,680 color patches  
- 🖼️ **Image size**: 96 × 96 pixels
- 🧪 **Source**: Histopathologic scans of lymph node sections  
- 🏷️ **Labels**: Binary — A positive (1) label indicates that the center 32x32px region of a patch contains at least one pixel of tumor tissue. Tumor tissue in the outer region of the patch does not influence the label.

```
B. S. Veeling, J. Linmans, J. Winkens, T. Cohen, M. Welling. "Rotation Equivariant CNNs for Digital Pathology". arXiv:1806.03962
```

```
Ehteshami Bejnordi et al. Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer. JAMA: The Journal of the American Medical Association, 318(22), 2199–2210. doi:jama.2017.14585
```

Under CC0 License

## Results

The submission on kaggle with the model trained on this notebook is 

```Public score: 0.9733```