EchoNet Cardiac Analysis Tutorial

📖 Tutorial Contents

  • 1. Introduction
    • 1.1. What this tutorial covers
    • 1.2. Background: what the models do
      • 1.2.1. Left-ventricle segmentation
      • 1.2.2. Ejection fraction (EF)
    • 1.3. The end-to-end workflow
    • 1.4. How the scripts are configured
    • 1.5. What you need before starting
  • 2. Installation & Setup
    • 2.1. Create a Python environment
    • 2.2. Install PyTorch
    • 2.3. Install the remaining dependencies
      • 2.3.1. Installing the echonet package
    • 2.4. Obtain the pretrained weights
    • 2.5. The project layout
  • 3. Data Preparation
    • 3.1. Accepted input formats
    • 3.2. How each script scans the folder
      • 3.2.1. Segmentation
      • 3.2.2. EF prediction
    • 3.3. Image / video assumptions
      • 3.3.1. .npy frame handling (segmentation only)
    • 3.4. Normalisation constants
    • 3.5. Project folder layout
  • 4. Computing Normalization Statistics
    • 4.1. Configure the paths
    • 4.2. Two modes: training-only vs full scan
    • 4.3. Run the script
    • 4.4. Use the result
  • 5. Left-Ventricle Segmentation
    • 5.1. Configure the paths
    • 5.2. Run the script
    • 5.3. What happens under the hood
      • 5.3.1. Model
      • 5.3.2. Module A — .npy frames
      • 5.3.3. Module B — videos
    • 5.4. Outputs
      • 5.4.1. Example outputs
      • 5.4.2. video_lv_area.csv columns
      • 5.4.3. image_lv_area.csv columns
  • 6. Ejection-Fraction Prediction
    • 6.1. Configure the paths
    • 6.2. Run the script
    • 6.3. What happens under the hood
      • 6.3.1. Model
      • 6.3.2. Clip sampling (test-time augmentation)
      • 6.3.3. Prediction and averaging
    • 6.4. Output
  • 7. Results & Troubleshooting
    • 7.1. Validating against the EchoNet-Dynamic ground truth
      • 7.1.1. EF — compare against FileList.csv
      • 7.1.2. Segmentation — compare against VolumeTracings.csv
    • 7.2. Common errors
    • 7.3. Performance tips
    • 7.4. Reproducibility checklist
  • 8. Downloads
    • 8.1. Scripts
    • 8.2. Pretrained weights
    • 8.3. Sample data (demo)
    • 8.4. Ground-truth labels (for validation)
    • 8.5. After downloading

📚 Appendices

  • Glossary
  • FAQ — Frequently Asked Questions
    • Do I need a GPU?
    • Do I have to use the command line?
    • Can I process a whole folder at once?
    • What is the difference between the two scripts?
    • Where do I get the weight files?
    • Why are predictions on my data poor?
    • What does CalculateStats.py do?
    • Can I change clip length / sampling for EF?
    • How is “systole” decided in the segmentation script?
    • Is the Status column a medical diagnosis?
EchoNet Cardiac Analysis Tutorial
  • Search

© Copyright 2026, Zhuoqun Zhao.

Built with Sphinx using a theme provided by Read the Docs.