Giter VIP home page Giter VIP logo

3dcnn-vis's Introduction

Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer’s Disease Classification

This repo implements the methods proposed in paper https://arxiv.org/abs/1803.02544, including Sensitivity Analysis by 3D Ultrametric Contour Map (SA-3DUCM), 3D Class Activation Mapping (3D-CAM), and 3D Gradient-Weighted Class Activation Mapping (3D-Grad-CAM).

This implemented paper is based on the work Residual and Plain Convolutional Neural Networks for 3D Brain MRI Classification and its implementation in this repo. Please cite properly if you are using code in this repo.

Build and run docker running environment

git clone [email protected]:west-gates/3DCNN-Vis.git

cd 3DCNN-Vis

[sudo] docker build -t 3dcnnvis:repo -f Dockerfile .

[sudo] nvidia-docker run -it -p 8809:8888 -v ~/path/to/3DCNN-Vis:/scripts/ 3dcnnvis:repo jupyter notebook --no-browser

Open http://localhost:8809 on your local machine.

Train 3DCNNs for Alzheimer’s Disease Classification

You need to train 3DCNNs from your MRIs similar to this repo. Some example pre-trained 3DCNNs are provided.

Sensitivity Analysis by 3D Ultrametric Contour Map (SA-3DUCM)

You need to run the 3DUCM code in this repo to segment your MRI images first. The segmentation for the example image is provided. Then run vgg_3d_ucm.ipynb and resnet_3d_ucm.ipynb to get the visual explanations.

3D Class Activation Mapping (3D-CAM)

Run resnet_3d_cam.ipynb. Note that with 3D-CAM you need to re-train your 3DCNN. An example pre-trained one is provided.

3D Gradient-Weighted Class Activation Mapping (3D-Grad-CAM)

Run vgg_3d_grad_cam.ipynb and resnet_3d_grad_cam.ipynb. You can change the convolutional layer that you want to visulize by setting from which layer activations and gradients are calculated.

3dcnn-vis's People

Contributors

west-gates avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.