{"id":29167305,"url":"https://github.com/jerryblessed/breathsafe2","last_synced_at":"2025-07-01T09:09:32.593Z","repository":{"id":301600123,"uuid":"1009773297","full_name":"Jerryblessed/breathsafe2","owner":"Jerryblessed","description":null,"archived":false,"fork":false,"pushed_at":"2025-06-27T17:57:46.000Z","size":94,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-27T18:35:25.833Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","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/Jerryblessed.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,"zenodo":null}},"created_at":"2025-06-27T17:28:14.000Z","updated_at":"2025-06-27T17:58:26.000Z","dependencies_parsed_at":"2025-06-27T18:48:03.855Z","dependency_job_id":null,"html_url":"https://github.com/Jerryblessed/breathsafe2","commit_stats":null,"previous_names":["jerryblessed/breathsafe2"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Jerryblessed/breathsafe2","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jerryblessed%2Fbreathsafe2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jerryblessed%2Fbreathsafe2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jerryblessed%2Fbreathsafe2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jerryblessed%2Fbreathsafe2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Jerryblessed","download_url":"https://codeload.github.com/Jerryblessed/breathsafe2/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jerryblessed%2Fbreathsafe2/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262933326,"owners_count":23386785,"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":"2025-07-01T09:09:31.508Z","updated_at":"2025-07-01T09:09:32.569Z","avatar_url":"https://github.com/Jerryblessed.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🫁 Breath Safe ungraded\n\n[Presentation](https://docs.google.com/presentation/d/1r_a98Et5a3CCOZtHDk0O5rNGh_tOkeDCvzrJvdH8OQA/edit?usp=sharing)\n🔗 **View the project pitch deck**\n\n[Use webapp](https://gibbon-clever-bream.ngrok-free.app/breathsafe)\n🌐 **View web site**\n\n# 📈 Architectural diagram\n\n![BreathSafe Architecture Diagram](https://github.com/Jerryblessed/breathsafe/blob/main/static/AI%20Lung%20Cancer%20Diagnosis%20Flowchart.png?raw=true)\n\n# ⭐️ Web screen\n\n![Breath Safe Landing Page](https://github.com/Jerryblessed/breathsafe/blob/main/static/landingpage.png?raw=true)\n\n**Breath Safe** is a lightweight Flask application that democratizes AI-powered lung cancer diagnosis using both deep learning and no-code tools. Built for low-resource settings, the platform enables non-technical health workers to upload CT or histopathology images via a simple web UI for instant predictions and guidance.\n\n---\n\n## 🚀 Features\n\n* 🖼️ **Dual Image Upload**\n\n  * Supports both CT and histopathology images.\n  * Upload via drag-and-drop interface on the web app.\n* 🧠 **High-Fidelity Deep Learning**\n\n  * Backend runs a DenseNet121 model trained on **16,000+ images** for accurate, offline-ready inference.\n* 💡 **No-Code Azure Option**\n\n  * For clinics with limited technical capacity, 800 pre-labeled lung images were trained on **Azure Custom Vision** for an easy plug-and-play interface.\n* 🤖 **AI Chatbot Assistant**\n\n  * Integrated with Azure OpenAI to explain results, answer lung-health questions, and guide users through uploads.\n* 🔐 **Secure Viewer Access**\n\n  * Azure Custom Vision access managed via viewer lists—no exposed secrets.\n\n---\n\n## 🎯 Uniqueness\n\n1. **Dual Training Paths**\n\n   * A powerful deep learning model (DenseNet121) trained locally on 16K lung images.\n   * A parallel no-code model trained on 800 curated samples using Azure Custom Vision for accessible cloud-based use.\n2. **Two Modalities, One Platform**\n\n   * Handles both CT scans and histopathology slides with equal ease.\n3. **Offline-Ready Architecture**\n\n   * Local model designed for containerized inference in remote clinics.\n4. **Embedded AI Agent**\n\n   * Helps interpret model outputs and provides clinical context in plain English.\n\n---\n\n## 🌍 Social Good\n\n* **Bridging diagnostic gaps** in rural clinics (currently \u003c15% imaging coverage).\n* **Advancing SDG 3.4**: Early detection could help save over 600,000 lives annually.\n* **Empowering non-specialists**: AI helps community health workers participate in diagnosis and triage.\n* **Fostering collaboration**: Viewer access and open-source codebase encourage transparency and feedback.\n\n---\n\n## 🛠️ Getting Started\n\n### Step 1: Download and install files\n\n```bash\n# Clone the repo\ngit clone https://github.com/Jerryblessed/breathsafe.git\ncd breathsafe\n\n# Create virtual environment\npython3 -m venv venv\nsource venv/bin/activate\n\n# Install dependencies\npip install -r requirements.txt\n```\n\n### Step 2: Download models from Google Drive\n\n[Download models here](https://drive.google.com/drive/folders/17am-HyZ2R7SoCi9Rpfu5uK71XAWWI1ff?usp=drive_link)\n🔗 **Download both CT Scan and Histopathology Models**\n\n```bash\n# Place both models in the root directory of the Flask app (same level as app.py)\n```\n\n### Step 3: Run the Flask app\n\n```bash\n# Run the app\npython app.py\n```\n\n---\n\n## 📁 Project Structure\n\nMake sure your folder looks like this:\n\n```\n📁 breathsafe/\n│\n├── app.py                          # Flask main application\n├── ctscan_densenet121.keras       # Trained CT scan model\n├── histo_densenet121_model.keras  # Trained histopathology model\n├── requirements.txt               # Python dependencies\n├── README.md                      # Project documentation\n├── static/                        # Static files (e.g., images, CSS)\n├── templates/                     # HTML templates for Flask\n└── train/                         # Model training scripts\n```\n\nVisit `http://localhost:5000` in your browser to explore.\n\n---\n\n## ✅ Training Models for Breath Safe\n\n[🧠 Model Training Guide](https://github.com/Jerryblessed/breathsafe/tree/main/train)\n🧩 **Learn how to train your own model for this project**\n\n---\n\n© 2025 Breath Safe Initiative\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjerryblessed%2Fbreathsafe2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjerryblessed%2Fbreathsafe2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjerryblessed%2Fbreathsafe2/lists"}