THIS REPO IS STILL UNDER DEVELOPMENT, IMPROVEMENT IS WELCOMED!

A UNet++ with MobileNetv2 block based ML model to do automatic CAC scoring This is a repo to develop my Undergraduate Thesis on Biomedical Engineering

• WSL2 Ubuntu Linux 20.04.4 LTS
• Miniconda (for environment management)
• Poetry (for dependencies management)
• Python 3.10.8

• Tensorflow
• Streamlit
• PyDicom
• Numpy

• Paper:
  • Original Paper using COCA Dataset (they use UNET Architecture)
  • Calcium Scoring Method
• Code:
  • keras-unet-collection
  • azcopy install script

The dataset used for this model is provided by Stanford AI COCA Dataset, this dataset can be accessed through this link

This model is using Gated MRI Data from the COCA Dataset consisting of the MRI image saved in a DICOM format and the calcium mask saved in a xml plist format.

Other dataset usage will be developed after the implementation of the COCA Dataset has been done.