CDD-CESM-Dataset

This is a helper repository for the CDD-CESM Mammogram Dataset containing all the tools for pre-processing and segmentation model

Dataset Link: here

Paper Link: here

Thesis link here.

Installation & Usage

The project was tested on a virtual environment of python 3.7, pip 23.2.1, and MacOS

pip install -r full_requirements.txt (or pip install -r requirements.txt if there are errors because of using a different operating system, as requirements.txt only contains the main dependencies and pip will fetch the compatible sub-dependencies, but it will be slower)
Download dataset
Put the images inside dataset/images
split annotations into dataset/train_set.csv and dataset/test_set.csv
edit configs.py to configure the training process
run train.py to train a classification model
run test.py to test a classification model
run parse_reports.py to parse the full reports and convert them to csv
run clean_images_names.py to remove any spaces from the images' names
run parse_reports.py to parse the full reports and convert them to csv
run draw_activations.py to draw gradcam activations from a trained model
run evaluate_segmentation_model.py to evaluate the segmentations from a trained classification model using the method in the paper and save the images
run draw_real_segmentations.py to draw the segmentations from the segmentation annotations

If you use this dataset, please cite the following:

Khaled R., Helal M., Alfarghaly O., Mokhtar O., Elkorany A., El Kassas H., Fahmy A. Categorized Digital Database for Low energy and Subtracted Contrast Enhanced Spectral Mammography images [Dataset]. (2021) The Cancer Imaging Archive. DOI: 10.7937/29kw-ae92
Khaled, R., Helal, M., Alfarghaly, O., Mokhtar, O., Elkorany, A., El Kassas, H., & Fahmy, A. Categorized contrast enhanced mammography dataset for diagnostic and artificial intelligence research. (2022) Scientific Data, Volume 9, Issue 1. DOI: 10.1038/s41597-022-01238-0
Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P, Moore S, Phillips S, Maffitt D, Pringle M, Tarbox L, Prior F. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository, Journal of Digital Imaging, Volume 26, Number 6, December, 2013, pp 1045-1057. DOI: 10.1007/s10278-013-9622-7

Name		Name	Last commit message	Last commit date
Latest commit History 14 Commits
pretrained_models		pretrained_models
.gitignore		.gitignore
LICENCE.md		LICENCE.md
README.md		README.md
augmenter.py		augmenter.py
auroc.py		auroc.py
clean_images_names.py		clean_images_names.py
configs.py		configs.py
dense_classifier.py		dense_classifier.py
downscaling_cnn.py		downscaling_cnn.py
draw_activations.py		draw_activations.py
draw_real_segmentations.py		draw_real_segmentations.py
evaluate_segmentation_model.py		evaluate_segmentation_model.py
full_requirements.txt		full_requirements.txt
generator.py		generator.py
gradcam.py		gradcam.py
merge_images.py		merge_images.py
parse_reports.py		parse_reports.py
requirements.txt		requirements.txt
split_train_test.py		split_train_test.py
test.py		test.py
train.py		train.py
utils.py		utils.py
visual_model_selector.py		visual_model_selector.py