Skip to content

Tutorial to train a 3D CNN to predict presence of pneumonia from CT scans.

Notifications You must be signed in to change notification settings

hasibzunair/3D-image-classification-tutorial

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

47 Commits
 
 
 
 
 
 

Repository files navigation

Tutorial on 3D Image Classification

Hugging Face Spaces

Learn how to train a 3D convolutional neural network (3D CNN) to predict presence of pneumonia. Now on the Keras docs (Link)!

Dataset

The dataset used in this tutorial is by MosMedData: Chest CT Scans with COVID-19 Related Findings which consists of 200 3D CT scans in total for the two classes. More detail here. Note that the data is public and I've kept it here for easy access/usage.

What is it about?

This tutorial will show the steps needed to build a 3D convolutional neural network (3D CNN) to predict the presence of viral pneumonia in computer tomography (CT) scans. 2D CNNs are commonly used to process RGB images (3 channels). A 3D CNN is simply the 3D equivalent: it takes as input a 3D volume or a sequence of 2D frames (e.g. slices in a CT scan), 3D CNNs are a powerful model for learning representations for volumetric data.

Usage

You can run the entire notebook on Colab! Copy the URL of the notebook here.

Acknowlegements

🤗 Spaces built by Faizan Shaikh.

References

Uniformizing Techniques to Process CT scans with 3D CNNs for Tuberculosis Severity Estimation (Paper, Code).