{"id":24662354,"url":"https://github.com/hiranmayikolambe/brain-tumor-detection-using-multiresolution-analysis","last_synced_at":"2026-04-29T07:35:19.455Z","repository":{"id":270997019,"uuid":"912109287","full_name":"hiranmayikolambe/Brain-tumor-detection-using-multiresolution-analysis","owner":"hiranmayikolambe","description":"This project uses Gabor filters and 3D U-Net to detect and segment brain tumors from MRI scans using the BraTS 2020 dataset","archived":false,"fork":false,"pushed_at":"2025-01-04T16:35:44.000Z","size":1447,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-30T23:03:53.114Z","etag":null,"topics":["3d-unet","brain-tumor-detection","brats2020","deep-learning","gabor-filters","medical-imaging","mri","multiresolution","python","segmentation","semantic-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hiranmayikolambe.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-01-04T16:21:55.000Z","updated_at":"2025-04-08T10:22:56.000Z","dependencies_parsed_at":"2025-01-04T17:36:29.757Z","dependency_job_id":null,"html_url":"https://github.com/hiranmayikolambe/Brain-tumor-detection-using-multiresolution-analysis","commit_stats":null,"previous_names":["hiranmayikolambe/brain-tumor-detection-using-multiresolution-analysis"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hiranmayikolambe/Brain-tumor-detection-using-multiresolution-analysis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiranmayikolambe%2FBrain-tumor-detection-using-multiresolution-analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiranmayikolambe%2FBrain-tumor-detection-using-multiresolution-analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiranmayikolambe%2FBrain-tumor-detection-using-multiresolution-analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiranmayikolambe%2FBrain-tumor-detection-using-multiresolution-analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hiranmayikolambe","download_url":"https://codeload.github.com/hiranmayikolambe/Brain-tumor-detection-using-multiresolution-analysis/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiranmayikolambe%2FBrain-tumor-detection-using-multiresolution-analysis/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32416146,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-29T06:29:02.080Z","status":"ssl_error","status_checked_at":"2026-04-29T06:29:00.631Z","response_time":110,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["3d-unet","brain-tumor-detection","brats2020","deep-learning","gabor-filters","medical-imaging","mri","multiresolution","python","segmentation","semantic-segmentation"],"created_at":"2025-01-26T04:14:04.496Z","updated_at":"2026-04-29T07:35:19.437Z","avatar_url":"https://github.com/hiranmayikolambe.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n\n# MRI Brain Tumor Detection Project\n\n## Overview\n\nThis project implements a brain tumor detection system using **Gabor filters** and a **3D U-Net architecture**. The model is trained on the **BraTS 2020 dataset**, which contains multimodal MRI images (FLAIR, T1, T1CE, T2) and corresponding segmentation masks. The goal is to accurately segment brain tumors from MRI scans.\n\n## Table of Contents\n\n1. [Requirements](#requirements)\n2. [Dataset](#dataset)\n3. [Installation](#installation)\n4. [Usage](#usage)\n   - [Gabor Filter Visualization](#gabor-filter-visualization)\n   - [Model Training](#model-training)\n   - [Model Evaluation](#model-evaluation)\n5. [License](#license)\n\n## Requirements\n\nTo run this project, you will need the following Python packages:\n\n- `numpy`\n- `opencv-python`\n- `matplotlib`\n- `nibabel`\n- `tensorflow`\n- `keras`\n- `sklearn`\n- `segmentation-models-3D`\n\nYou can install the required packages using pip:\n\n```bash\npip install numpy opencv-python matplotlib nibabel tensorflow keras scikit-learn segmentation-models-3D\n```\n\n## Dataset\n\nThis project uses the **BraTS 2020 dataset**, which can be downloaded from the BraTS Challenge website. The dataset contains the following modalities:\n\n- FLAIR\n- T1\n- T1CE\n- T2\n- Segmentation masks\n\nMake sure to place the dataset in the appropriate directory as specified in the code.\n\n## Installation\n\n1. Clone this repository or download the notebook file.\n2. Ensure that the BraTS dataset is downloaded and placed in the specified directory.\n3. Open the notebook in **Google Colab** or **Jupyter Notebook**.\n\n## Usage\n\n### Load and Preprocess Data\n\nThe code loads the MRI images and corresponding masks, normalizes the pixel values, and prepares the data for training.\n\n### Gabor Filter Application\n\nThe code applies **Gabor filters** to the MRI images to enhance feature extraction.\n\n### Model Definition\n\nA **3D U-Net** model is defined for semantic segmentation of brain tumors.\n\n### Training\n\nThe model is trained using the training dataset, and the training history is recorded.\n\n### Evaluation\n\nThe model's performance is evaluated using metrics such as **Intersection over Union (IoU)** and accuracy.\n\n## Gabor Filter Visualization\n\nThe project includes a section that visualizes Gabor filters with varying parameters (theta and gamma). This helps in understanding how different filter configurations affect the feature extraction process.\n\nExample code to visualize Gabor filters:\n\n```python\n# Example of creating Gabor filters\nksize = 50\nsigma = 3\nthetas = [0, np.pi/4, np.pi/2, 3*np.pi/4]\ngammas = [1, 0.5, 0.01]\n\n# Code to visualize Gabor filters\n```\n\n## Model Training\n\nThe model is trained using the following parameters:\n\n- **Batch size**: 2\n- **Learning rate**: 0.0001\n- **Number of epochs**: 100\n\nThe training process includes data augmentation and uses a custom loss function that combines **Dice loss** and **focal loss** to handle class imbalance.\n\nExample code for model training:\n\n```python\n# Example of model training\nhistory = model.fit(train_img_datagen,\n                    steps_per_epoch=steps_per_epoch,\n                    epochs=100,\n                    validation_data=val_img_datagen,\n                    validation_steps=val_steps_per_epoch)\n```\n\n## Model Evaluation\n\nAfter training, the model's performance is evaluated on a validation dataset. The code calculates the **Mean IoU** and visualizes the predictions against the ground truth masks.\n\nExample code for model evaluation:\n\n```python\n# Example of model evaluation\nIOU_keras = MeanIoU(num_classes=n_classes)\nIOU_keras.update_state(test_pred_batch_argmax, test_mask_batch_argmax)\nprint(\"Mean IoU =\", IOU_keras.result().numpy())\n```\n\n## License\n\nThis project is licensed under the **MIT License**. See the LICENSE file for more details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiranmayikolambe%2Fbrain-tumor-detection-using-multiresolution-analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhiranmayikolambe%2Fbrain-tumor-detection-using-multiresolution-analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiranmayikolambe%2Fbrain-tumor-detection-using-multiresolution-analysis/lists"}