Code Monkey home page Code Monkey logo

om-net's Introduction

OM-Net

This is the code release for the MICCAI 2018 paper "One-Pass Multi-task Convolutional Neural Networks for Efficient Brain Tumor Segmentation", authored by Chenhong Zhou, Changxing Ding, Zhentai Lu, Xinchao Wang and Dacheng Tao.

This work overcomes the shortcomings of popular model cascade strategy that can lead to undesired system complexity and ignore the relevance among the models due to its multiple separate cascaded models. We propose to adopt multi-task learning to integrate multiple segmentation tasks into a deep model which is called One-pass Multi-task Network (OM-Net).

OM-Net exploits correlation among tasks to achieve superior performance, with only one-third model parameters of model cascade strategy and one-pass computation. It ranks 1st on the BraTS 2015 test set and achieves top performance on BraTS 2017 validation set.

Model

Firstly, we split multi-class brain tumor segmentation into three segmentation tasks: 1) Coarse segmentation to detect complete tumor. 2) Refined segmentation for complete tumor and its intra-tumoral classes. 3) Precise segmentation for enhancing tumor.

For model cascade framework, each task is implemented by an independent basic network. Our basic network used in model cascade framework is a 3D variant of the Fusionnet. See picture below.

img/3D_fusionnet.png

OM-Net integrates three tasks with their respective training data being the same as those in model cascade framework. Its architecture is illustrated in the picture below. Each task owns its task-specific parameters and the shared backbone model is aimed to learn the correlation among the tasks. Specifically, the shared backbone model refers to the network layers outlined by the yellow dashed line in 3D_fusionnet.png.

img/om-net-architecture.png

Usage

All implementations are based on the C3D, which is a 3D modified version of BVLC caffe.

Please clone the C3D repository and add these files.

To be continued.

Contact

eezhouch At mail.scut.edu.cn

om-net's People

Contributors

chenhong-zhou avatar

Watchers

paper2code - bot avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.