{"id":20182367,"url":"https://github.com/mohammad95labbaf/brain-tumor-transferlearning","last_synced_at":"2026-04-29T14:02:44.356Z","repository":{"id":240914448,"uuid":"783407467","full_name":"mohammad95labbaf/Brain-Tumor-TransferLearning","owner":"mohammad95labbaf","description":"The Brain Tumor MRI Dataset from Kaggle is employed for automated brain tumor detection and classification research. Investigated methods include using pre-trained models (VGG16, ResNet50, and ViT). 🧠🔍","archived":false,"fork":false,"pushed_at":"2024-05-21T11:06:48.000Z","size":764,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-25T08:02:17.532Z","etag":null,"topics":["cnn","cnn-keras","deep-learning","deep-neural-networks","deeplearning","kaggle-dataset","keras","keras-tensorflow","neural-network","neural-networks","pretrained-models","resnet-50","transfer-learning","tumor-classification","tumor-detection","vgg16","vision","vision-transformer","vit"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/mohammad95labbaf.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":"2024-04-07T19:56:32.000Z","updated_at":"2024-11-09T10:25:42.000Z","dependencies_parsed_at":"2024-05-21T12:36:49.999Z","dependency_job_id":"0357d75a-218e-4ff2-8b83-e868da903163","html_url":"https://github.com/mohammad95labbaf/Brain-Tumor-TransferLearning","commit_stats":null,"previous_names":["mohammad95labbaf/brain-tumor-transferlearning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mohammad95labbaf/Brain-Tumor-TransferLearning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohammad95labbaf%2FBrain-Tumor-TransferLearning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohammad95labbaf%2FBrain-Tumor-TransferLearning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohammad95labbaf%2FBrain-Tumor-TransferLearning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohammad95labbaf%2FBrain-Tumor-TransferLearning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mohammad95labbaf","download_url":"https://codeload.github.com/mohammad95labbaf/Brain-Tumor-TransferLearning/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mohammad95labbaf%2FBrain-Tumor-TransferLearning/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261832612,"owners_count":23216493,"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":["cnn","cnn-keras","deep-learning","deep-neural-networks","deeplearning","kaggle-dataset","keras","keras-tensorflow","neural-network","neural-networks","pretrained-models","resnet-50","transfer-learning","tumor-classification","tumor-detection","vgg16","vision","vision-transformer","vit"],"created_at":"2024-11-14T02:38:25.048Z","updated_at":"2026-04-29T14:02:39.325Z","avatar_url":"https://github.com/mohammad95labbaf.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Brain-Tumor-TransferLearning\n\n### Dataset:\n- The dataset utilized for this study is the **Brain Tumor MRI Dataset** sourced from Kaggle.\n- It consists of a carefully curated collection of brain MRI scans specifically chosen to facilitate research in automated brain tumor detection and classification using the Keras library.\n- The dataset aims to enhance diagnostic accuracy and includes a randomized subset (20% of the original data) categorized into 'yes' (tumor present) and 'no' (healthy) tumor classes for both training and validation purposes.\n\n### Investigated Approaches:\n\n1. **VGG16 + FC (VGG16 with Fully Connected Layers)**:\n   - VGG16 is a deep CNN architecture comprising 16 weight layers.\n   - It was pre-trained on the ImageNet dataset.\n   - Additional fully connected layers are incorporated for classification.\n\n2. **VGG + CNN2D (VGG16 with Additional Convolutional Layers)**:\n   - This approach extends VGG16 by introducing more convolutional layers for enhanced feature extraction.\n\n3. **ResNet50 + FC (ResNet50 with Fully Connected Layers)**:\n   - ResNet50, a deep residual network with 50 layers, addresses the vanishing gradient problem using skip connections.\n   - Fully connected layers are added for classification.\n\n4. **ResNet50 + CNN2D (ResNet50 with Additional Convolutional Layers)**:\n   - Building upon ResNet50, this variant incorporates additional convolutional layers.\n\n5. **ViT (Vision Transformer) + FC (Fully Connected Layers)**:\n   - Originally designed for natural language processing, ViT is a transformer-based architecture.\n   - It has been adapted for image classification by treating images as sequences of patches.\n   - Fully connected layers are employed for classification⁷.\n\n### Investigation Objectives:\n- Evaluate the effectiveness of transfer learning using pre-trained models (VGG16, ResNet50, and ViT) for brain tumor classification.\n- Compare the performance of different architectures in terms of accuracy, sensitivity, specificity, and other relevant metrics.\n- Gain insights into how transfer learning impacts model convergence, generalization, and robustness.\n\n\n## Instructions for Kaggle API\n1. **Download Kaggle API**:\n    - Install the Kaggle API by running `pip install kaggle`.\n\n2. **Kaggle API Token**:\n    - Go to your Kaggle account settings and generate an API token.\n    - Save the token as `kaggle.json` in the root directory of this repository.\n\n3. **Download Dataset**:\n    - Use the Kaggle API to download the dataset:\n        ```\n        kaggle datasets download -d  preetviradiya/brian-tumor-dataset\n        ```\n\n4. **Upload Kaggle API Token to Colab/Notebook**:\n    - If using Colab or Jupyter Notebook, upload the `kaggle.json` token to your environment.\n    - Use the following code snippet:\n        ```python\n        from google.colab import files\n        files.upload()\n        ```\n\n5. **Unzip Dataset**:\n    - Unzip the downloaded dataset:\n        ```\n        unzip brian-tumor-dataset.zip\n        ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohammad95labbaf%2Fbrain-tumor-transferlearning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmohammad95labbaf%2Fbrain-tumor-transferlearning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmohammad95labbaf%2Fbrain-tumor-transferlearning/lists"}