{"id":19237666,"url":"https://github.com/adamouization/breast-cancer-detection-code","last_synced_at":"2025-02-23T13:51:09.636Z","repository":{"id":78089119,"uuid":"274148697","full_name":"Adamouization/Breast-Cancer-Detection-Code","owner":"Adamouization","description":"Common deep learning pipeline for the Breast Cancer Detection Dissertation","archived":false,"fork":false,"pushed_at":"2020-08-06T22:17:55.000Z","size":1187,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-01-05T01:43:05.822Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://doi.org/10.5281/zenodo.3975093","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Adamouization.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-06-22T13:44:40.000Z","updated_at":"2021-01-25T18:35:59.000Z","dependencies_parsed_at":"2023-06-11T06:30:26.340Z","dependency_job_id":null,"html_url":"https://github.com/Adamouization/Breast-Cancer-Detection-Code","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Adamouization%2FBreast-Cancer-Detection-Code","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Adamouization%2FBreast-Cancer-Detection-Code/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Adamouization%2FBreast-Cancer-Detection-Code/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Adamouization%2FBreast-Cancer-Detection-Code/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Adamouization","download_url":"https://codeload.github.com/Adamouization/Breast-Cancer-Detection-Code/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240324060,"owners_count":19783453,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-09T16:27:47.589Z","updated_at":"2025-02-23T13:51:09.614Z","avatar_url":"https://github.com/Adamouization.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Breast Cancer Detection in Mammograms using Deep Learning Techniques - Common Pipeline Code [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3975093.svg)](https://doi.org/10.5281/zenodo.3975093) [![GitHub license](https://img.shields.io/github/license/Adamouization/Breast-Cancer-Detection-Code)](https://github.com/Adamouization/Breast-Cancer-Detection-Code/blob/master/LICENSE)\n\nRepository containing the code written in common for the **Breast Cancer Detection in Mammograms using Deep Learning Techniques** dissertation. This code was further extended individually by each group member to get results by testing new deep learning techniques.\n\n## Usage on a GPU lab machine\n\nClone the repository:\n\n```\ncd ~/Projects\ngit clone https://github.com/Adamouization/Breast-Cancer-Detection-Code\n```\n\nCreate a repository that will be used to install Tensorflow 2 with CUDA 10 for Python and activate the virtual environment for GPU usage:\n\n```\ncd libraries/tf2\ntar xvzf tensorflow2-cuda-10-1-e5bd53b3b5e6.tar.gz\nsh build.sh\n```\n\nActivate the virtual environment:\n\n```\nsource /cs/scratch/\u003cusername\u003e/tf2/venv/bin/activate\n```\n\nCreate `output`and `save_models` directories to store the results:\n\n```\nmkdir output\nmkdir saved_models\n```\n\n`cd` into the `src` directory and run the code:\n\n```\npython main.py [-h] -d DATASET -m MODEL [-r RUNMODE] [-i IMAGESIZE] [-v]\n```\n\nwhere:\n* `-h` is a  flag for help on how to run the code.\n* `DATASET` is the dataset to use. Must be either `mini-MIAS` or `CBIS-DDMS`.\n* `MODEL` is the model to use. Must be either `basic` or `advanced`.\n* `RUNMODE` is the mode to run in (`train` or `test`). Default value is `train`.\n* `IMAGESIZE` is the image size to feed into the CNN model (`small` - 512x512px; or `large` - 2048x2048px). Default value is `small`.\n* `-v` is a flag controlling verbose mode, which prints additional statements for debugging purposes.\n\n## Dataset usage\n\n### mini-MIAS dataset\n\n* This example will use the [mini-MIAS](http://peipa.essex.ac.uk/info/mias.html) dataset. After cloning the project, travel to the `data/mini-MIAS` directory (there should be 3 files in it).\n\n* Create `images_original` and `images_processed` directories in this directory: \n\n```\ncd data/mini-MIAS/\nmkdir images_original\nmkdir images_processed\n```\n\n* Move to the `images_original` directory and download the raw un-processed images:\n\n```\ncd images_original\nwget http://peipa.essex.ac.uk/pix/mias/all-mias.tar.gz\n```\n\n* Unzip the dataset then delete all non-image files:\n\n```\ntar xvzf all-mias.tar.gz\nrm -rf *.txt \nrm -rf README \n```\n\n* Move back up one level and move to the `images_processed` directory. Create 3 new directories there (`benign_cases`, `malignant_cases` and `normal_cases`):\n\n```\ncd ../images_processed\nmkdir benign_cases\nmkdir malignant_cases\nmkdir normal_cases\n```\n\n* Now run the python script for processing the dataset and render it usable with Tensorflow and Keras:\n\n```\npython3 ../../../src/dataset_processing_scripts/mini-MIAS-initial-pre-processing.py\n```\n\n### DDSM and CBIS-DDSM datasets\n\nThese datasets are very large (exceeding 160GB) and more complex than the mini-MIAS dataset to use. Downloading and pre-processing them will therefore not be covered by this README. \n\nOur generated CSV files to use these datasets can be found in the `/data/CBIS-DDSM` directory, but the mammograms will have to be downloaded separately. The DDSM dataset can be downloaded [here](http://www.eng.usf.edu/cvprg/Mammography/Database.html), while the CBIS-DDSM dataset can be downloaded [here](https://wiki.cancerimagingarchive.net/display/Public/CBIS-DDSM#5e40bd1f79d64f04b40cac57ceca9272).\n\n## Authors\n\n* Adam Jaamour\n* Ashay Patel\n* Shuen-Jen Chen\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadamouization%2Fbreast-cancer-detection-code","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadamouization%2Fbreast-cancer-detection-code","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadamouization%2Fbreast-cancer-detection-code/lists"}