Code Monkey home page Code Monkey logo

crocnet's Introduction

Crop and Couple: Cardiac image segmentation using interlinked specialist networks

Introduction

This repository contains the code and resources for the "Cardiovascular Disease Diagnosis through Cardiac Image Segmentation" paper accepted for ISBI 2024 – International Symposium on Biomedical Imaging. https://biomedicalimaging.org/2024/

Abstract

Automated diagnosis of cardiovascular disease relies on cardiac image segmentation, a critical task in medical imaging. Our proposed strategy employs specialist networks focusing on individual anatomies (left ventricle, right ventricle, or myocardium) to achieve accurate segmentation. In the initial stage, a ternary segmentation is performed to identify these anatomical regions, followed by cropping the original image for focused processing. An attention mechanism, facilitated by an additive attention block (E-2A block), interlinks features from different anatomies, serving as a soft relative shape prior. Our approach aims for efficiency and effectiveness in cardiac image segmentation.

Methodology

Overview of the proposed CroCNet pipeline. (a) E-2AUNet architecture for initial segmentation in the first stage. The cropped image and initial binary segmentations are fed into (b) specialist networks (LV-Net, RV-Net, and MYO-Net) to refine the predictions for each cardiac region. We leverage (c) efficient additive attention, including (d) a cross-E2A block that implements cross-attention to intermingle features between the specialist networks. idea2

Results

Comparison of the results obtained from different methods. Methods indicated with the ∗ use of multi-view inputs.

viz ab1

Citation

Abbas Khan, Muhammad Asad, Martin Benning, Caroline Roney, Gregory Slabaugh, 'Crop and Couple: cardiac image segmentation using interlinked specialist networks', https://arxiv.org/abs/2402.09156

Acknowledgments

This work was funded through the mini-Centre for Doctoral Training in AI-based Cardiac Image Computing provided through the Faculty of Science and Engineering, Queen Mary University of London. This paper utilized Queen Mary’s QMUL Research-IT Services support Andrena HPC facility. Caroline Roney acknowledges funding from a UKRI Future Leaders Fellowship (MR/W004720/1).


Note: This paper has been accepted for ISBI 2024 – International Symposium on Biomedical Imaging.

crocnet's People

Contributors

kabbas570 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.