Git Product home page Git Product logo

msk_segmentation's Introduction

Fully-Automated Cartilage and Meniscus Segmentation for Knee MRI

Fully-automated segmentation of MSK tissues from MRI data.

This code is primarily designed to segment cartilage and meniscus from 3D DESS scans from the OAI. The model weights for this network are rather large (400MB) but they can be found by emailing akshaysc at stanford dot edu.

Here are some results from 14 subjects tested from the OAI iMorphics cohort:

KLG Femoral Cartilage Tibial Cartilage Meniscus
2 89.8 ± 2.0 87.9 ± 2.3 76.0 ± 3.5
3 90.0 ± 1.3 85.6 ± 3.8 75.1 ± 4.2
4 90.1 ± 1.8 76.1 ± 1.9 75.8 ± 3.7
Average 89.9 ± 1.6 85.3 ± 4.7 75.4 ± 3.8
Volume CV % 1.7 ± 1.2 6.5 ± 5.8 9.0 ± 5.7

Things Planned For:

  1. A detailed tutorial on how to use the provided code
  2. Pre-processing pipeline (dicom read -> python preprocess -> segmentations in tiff)

If you find any issues with the code or want to contribute, please do let me know!

msk_segmentation's People

Contributors

akshaysc 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.