DICOM Preprocessing for Medical Imaging

This repository contains Jupyter notebooks for preprocessing various medical imaging modalities in DICOM format. It's designed to support lectures and practical work in medical image analysis.

Repository Structure

The repository is organized into two main folders, each corresponding to a specific lecture:

1. cxr_data_preprocessing/: Preprocessing techniques for Chest X-rays
2. embed_data_preprocessing/: Preprocessing methods for breast imaging modalities
   • Mammograms
   • Digital Breast Tomosynthesis (DBT)
   • Breast MRIs

Contents

Each folder contains Jupyter notebooks that demonstrate various preprocessing techniques specific to the imaging modality. These may include:

• Presentation State Transformations
• Image normalization
• Noise reduction
• Contrast enhancement
• Segmentation

Getting Started

Prerequisites

• Python 3.7+
• Jupyter Notebook or JupyterLab
• Required Python libraries

Installation

1. Clone this repository:

   git clone https://github.com/theodapamede/dicom_preprocessing.git
   

2. Navigate to the repository folder:

   cd dicom_preprocessing
   

3. Install required dependencies:

   pip install -r requirements.txt
   

Usage

1. Start Jupyter Notebook or JupyterLab
2. Navigate to the desired lecture folder
3. Open and run the notebooks to learn about and apply preprocessing techniques

Contributing

Contributions to improve existing notebooks or add new preprocessing techniques are welcome. Please feel free to submit pull requests or open issues for discussion.

Contact

Theo Dapamede ([email protected])

---

We hope these notebooks prove useful in your medical imaging preprocessing tasks. For any questions or suggestions, please open an issue in this repository.