This repository contains the source code and documentation for the final project titled "Dicentric chromosomes detection in metaphasic plates images", created by me.
The main goal of this project is to automate the detection of dicentric chromosomes in metaphase plates using deep learning and computer vision. Dicentric chromosome counting is a critical technique in biological dosimetry for estimating radiation exposure.
- Overview
- Installation
- Usage
- Model Architecture
- Results
- Technologies Used
- Future Work
- Acknowledgments
The detection of dicentric chromosomes, which occur due to exposure to ionizing radiation, is traditionally done manually by experts in biological dosimetry. This project aims to automate that process using convolutional neural networks (CNNs) to reduce time and minimize operator bias.
The model was trained on a dataset of metaphase plate images provided by REAC/TS (Radiation Emergency Assistance Center/Training Site) and the Hospital La Fe in Valencia. Various preprocessing techniques were applied to improve the model's performance.
- Clone this repository:
git clone https://github.com/yourusername/dicentric-chromosome-detection.git cd dicentric-chromosome-detection