Authors:
- Asia Montico, 1966494.
- Andrea Di Vincenzo, 1887012.
- Emanuele Iaccarino, 2192710.
- Mattia Mungo, 1883175.
- Viktoriia Vlasenko, 2088928.
Breast cancer is a leading cause of death among women worldwide. Early and precise diagnosis is critical for effective treatment and improving patient outcomes. Potentialy improve diagnostic tools and assist healthcare professionals in decision-making.
The CBIS-DDSM (Curated Breast Imaging Subset of the Digital Database for Screening Mammography) is a large-scale dataset used for breast cancer diagnosis, particularly focusing on mammography images. It is available on Kaggle, and it provides images along with annotations that are essential for training and evaluating machine learning models for tasks such as tumor classification (benign vs. malignant) and lesion detection in breast tissue.
The CBIS-DDSM dataset is a curated subset of the Digital Database for Screening Mammography (DDSM). It was specifically curated for breast cancer detection using mammography images and contains both mammogram images and corresponding annotations.
├── main.ipynb: Main notebook containing data preparation, EDA, and image preprocessing.
├── merged_notebook.ipynb: Combined and detailed explanation of boosting algorithms and results.
├── Comparison.ipynb: Custom CNN and boosting method application with comparisons.
├── DenseNet121.ipynb: Implementation of DenseNet121 model for classification tasks.
├── EfficientNet-b4.ipynb: Implementation of EfficientNet-b4 model for classification tasks.
├── layer-analysis-densenet finale.ipynb: Finalized layer analysis of DenseNet for results interpretation.
├── planning materials/: Folder containing planning resources for the project.
├── Breast Cancer Presentation.pdf: Presentation summarizing the project methodology and results.
├── README.md: Project documentation and overview.
├── LICENSE: License file for the project.
├── requirements.txt: List of dependencies and libraries required to run the project.
└── .gitignore: File specifying files and directories ignored by Git.
This project is licensed under the MIT License. See the LICENSE file for more details.