DeepRespNet

A Deep Learning Model to classify Respiratory Diseases

• DeepRespNet is a deep learning model specifically designed to analyze respiratory sounds and assess the respiratory health of patients.

• By leveraging deep learning techniques, our model classifies respiratory sounds into categories such as healthy, chronic, and acute conditions.

• The DeepRespNet web application offers an intuitive platform for both individuals and healthcare professionals to evaluate respiratory health through audio recordings.

• Our primary goal is to facilitate the early detection of respiratory conditions, enabling timely and accurate medical intervention to improve patient outcomes.

Prerequisites

• Python 3.10
• UV package manager (recommended) or pip

Setup

Method 1: Quick Setup with UV (Recommended)

UV is a fast Python package manager that makes dependency management easier and more reliable.

1. Install UV (if not already installed):

   # macOS using Homebrew (recommended)
   brew install uv
   
   # macOS/Linux using installer
   curl -LsSf https://astral.sh/uv/install.sh | sh
   
   # Windows
   powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
   
   # Using pip
   pip install uv

2. Clone the repository:

   git clone https://github.com/Mohammed-Khubaib/DeepRespNet.git

3. Navigate to the project directory:

   cd DeepRespNet

4. Create virtual environment and install dependencies:

   # Create virtual environment with Python 3.10
   uv venv --python 3.10
   
   # Activate virtual environment
   source .venv/bin/activate  # On macOS/Linux
   # or
   .venv\Scripts\activate     # On Windows
   
   # Install dependencies
   uv pip install -r requirements.txt

5. Run the application:

   streamlit run app.py

   or

   uv run streamlit run app.py

Method 2: Using pyproject.toml with UV (Advanced)

For a more robust setup, you can use a pyproject.toml file:

1. Follow steps 1-3 from Method 1

2. Create pyproject.toml in the project root with your project dependencies

3. Setup and run with UV:

   # Install dependencies and create environment
   uv sync
   
   # Run the application
   uv run streamlit run app.py

Method 3: Traditional Setup with pip

If you prefer using pip:

1. Clone the repository:

   git clone https://github.com/Mohammed-Khubaib/DeepRespNet.git

2. Navigate to the project directory:

   cd DeepRespNet

3. Create virtual environment (recommended):

   python3.10 -m venv venv
   source venv/bin/activate  # On macOS/Linux
   # or
   venv\Scripts\activate     # On Windows

4. Install the required dependencies:

   pip install -r requirements.txt

Running the Application

The main application can be launched using app.py. This file utilizes pieChart.py and linechart.py internally.

streamlit run app.py

The application will be available at http://localhost:8501 in your web browser.

Dataset Source

The dataset used in this project is the Respiratory Sound Database available on Kaggle.

Web Application User Interface

webapp.mov

Project Structure

.
├── README.MD
├── animations
│   ├── DeepRespNet Architecture.png
│   ├── Lungs.json
│   ├── SoundRecordingAnimation.json
│   ├── Stethoscope.json
│   └── dashboard animation.json
├── app.py
├── diagnosis_GRU_CNN_5.keras
├── linechart.py
├── model5accuracy.yaml
├── pieChart.py
├── requirements.txt
└── pyproject.toml          # Optional: for UV-based setup

Team

1. Mohammed Khubaib
2. Ashish Kumar Pandia
3. Airla Snehith