CODAvision

CODAvision is an open-source Python package designed for semantic segmentation of biomedical images through a user-friendly interface.

---

📑 Table of Contents

1. System Requirements
   • Hardware
   • Software
2. Installation Guide
   • Step 1: Install Miniconda
   • Step 2: Create and Activate CODAvision Environment
   • Step 3: Install CUDA Toolkit and cuDNN
   • Step 4: Install CODAvision
   • Step 5: Launch CODAvision GUI
3. Demo
   • Sample Dataset
   • Instructions to Run on Sample Data
   • Expected Output
   • Expected Runtime

---

📋 1. System Requirements

🧰 Hardware

• Minimum Requirements:

  • Computer with ≥16 GB RAM
  • NVIDIA GPU with ≥8 GB VRAM
  • Operating System: Windows 10/11 or macOS 11
  • Storage: ≥2.5 GB free space
  • CUDA Toolkit (≥11.2) and cuDNN (≥8.1) installed

• Tested Configuration:

  • Workstation with 128 GB RAM
  • NVIDIA GeForce RTX 4090 GPU
  • Operating System: Windows 11

🖥️ Software

• CODAvision Repository
• Python IDE (e.g., PyCharm, Visual Studio, Spyder)
• Image Annotation Tool (choose one):

  • Aperio ImageScope

  • QuPath

    ⚠️ Note for QuPath Users:
    To use the GUI-guided workflow in CODAvision with annotations created in QuPath, you must first export the annotations for each image as GeoJSON files via File > Export Objects as GeoJSON.
    These GeoJSON files must then be converted into XML format, which is compatible with CODAvision.
    You can perform this conversion using the scripts provided in the following repository: GeoJSON2XML.

---

⚙️ 2. Installation Guide

📥 Step 1: Install Miniconda

Download and install Miniconda by following the instructions provided here.

🐍 Step 2: Create and Activate CODAvision Environment

  conda create -n CODAvision python=3.9.19
  conda activate CODAvision

🔧 Step 3: Install CUDA Toolkit and cuDNN

Ensure that the CUDA drivers are installed as per the instructions here. Then, install the CUDA Toolkit and cuDNN:

  conda install -c conda-forge cudatoolkit=11.2 cudnn=8.1.0

📦 Step 4: Install CODAvision

Install the CODAvision package using pip:

  pip install -e git+https://github.com/Kiemen-Lab/CODAvision.git#egg=CODAvision

⚠️ Note:
Ensure Git is installed. If not, download it from here.
After installation, restart your IDE and reactivate the environment:

  conda activate CODAvision

⚠️ ### ⚠️ Important Notice for macOS Users

TensorFlow GPU is not natively supported on macOS as it is on Windows or Linux. However, for macOS systems with Apple Silicon chips (M1, M2, M3), you can leverage GPU acceleration by installing tensorflow-macos and tensorflow-metal. Follow one of the two options below based on your setup:

---

✅ Option 1: Using Apple Silicon (M1/M2/M3) with GPU Support

If you're on an Apple Silicon Mac and want to enable GPU acceleration via Metal:

1. Remove version constraints from the pyproject.toml file:
   Change lines like:

   "tensorflow==2.10.1"
   "keras==2.10.0"
   

   to:

   "tensorflow"
   "keras"
   

2. Comment out any tensorflow-gpu entries, for example:

   # "tensorflow-gpu==2.10.0",

3. Install the required Apple-specific TensorFlow packages manually:

   pip install tensorflow-macos tensorflow-metal

4. Install remaining dependencies:

   pip install -e .

   💡 Make sure to run this from the directory containing the CODAvision package.

---

🚫 Option 2: Intel Mac or CPU-only Setup

If you are using an Intel-based Mac or do not require GPU acceleration:

1. Follow steps 1–2 from above to remove version constraints and comment out tensorflow-gpu.

2. Simply install the package dependencies:

   pip install -e .

---

After completing the steps under your chosen option, you should be able to run CODAvision.py successfully on macOS.

🖼️ Step 5: Launch CODAvision GUI

After completing the installation, run the CODAvision.py script to launch the GUI and begin data parameterization.

⏱️ Typical Installation Time: Approximately 10–15 minutes on a standard desktop computer.

---

🎬 3. Demo

📂 Sample Dataset

Access the sample dataset here.

📝 Instructions to Run on Sample Data

Acess the demo instructions here

📊 Expected Output

Acess the expected output here.

⏳ Expected Runtime

• GPU-Powered Workstation: Approximately 2–3 hours for model training and image processing.
• Desktop Computer with no GPU: Image processing and training time may extend up to 10 hours.

---

For a more comprehensive guidance on annotation dataset creation CODAvision Protocol.

---