https://github.com/sebp/survival-cnn-estimator

Tutorial on survival analysis using TensorFlow.
https://github.com/sebp/survival-cnn-estimator

convolutional-neural-networks deep-learning notebook survival-analysis tensorflow time-to-event tutorial

Last synced: 26 days ago
JSON representation

Tutorial on survival analysis using TensorFlow.

• Host: GitHub
• URL: https://github.com/sebp/survival-cnn-estimator
• Owner: sebp
• License: gpl-3.0
• Created: 2019-07-28T11:29:19.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2020-05-16T19:59:28.000Z (over 4 years ago)
• Last Synced: 2024-10-03T12:33:12.642Z (about 2 months ago)
• Topics: convolutional-neural-networks, deep-learning, notebook, survival-analysis, tensorflow, time-to-event, tutorial
• Language: Jupyter Notebook
• Size: 397 KB
• Stars: 47
• Watchers: 4
• Forks: 19
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Survival Analysis for Deep Learning

This is a [tutorial on survival analysis](https://k-d-w.org/blog/2019/07/survival-analysis-for-deep-learning/), also referred to as time-to-event analysis or reliability analysis. You will learn how to train a convolutional neural network to predict time to a (generated) event from MNIST images, using a loss function specific to survival analysis.

There are two versions of the tutorial:

1. Using tf.Estimator and TensorFlow 1.X: [tutorial\_tf1.ipynb](https://nbviewer.jupyter.org/github/sebp/survival-cnn-estimator/blob/master/tutorial_tf1.ipynb)

2. Using Keras and TensorFlow 2.X: [tutorial\_tf2.ipynb](https://nbviewer.jupyter.org/github/sebp/survival-cnn-estimator/blob/master/tutorial_tf2.ipynb)

## Getting started

The easiest way to run this notebook is [Google Colaboratory](https://colab.research.google.com/github/sebp/survival-cnn-estimator/blob/master/tutorial_tf2.ipynb). If you want to run this notebook locally, you have to make sure the following dependencies are installed:

- [numpy](https://www.numpy.org/)

- [matplotlib](https://matplotlib.org/)

- [pandas](https://pandas.pydata.org/)

- [scikit-survival](https://github.com/sebp/scikit-survival/)

- [tensorflow](https://www.tensorflow.org/)