• Home
  • Search
  • DUDA: Deep Unsupervised Domain Adaptation Learning for Multi-sequence Cardiac MR Image Segmentation
  • Cite Icon2
  • https://doi.org/10.1007/978-3-030-60633-6_42Copy DOI Icon

DUDA: Deep Unsupervised Domain Adaptation Learning for Multi-sequence Cardiac MR Image Segmentation

  • Jan 1, 2020
  • Yueguo Liu +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Automatic segmentation of ventricles and myocardium in late gadolinium-enhanced (LGE) cardiac images is an important assessment for the clinical diagnosis of myocardial infarction. The most segmentation methods rely on the annotation of ventricles and myocardium. However, pathological myocardium in LGE images makes its annotation difficult to be obtained. In this paper, we propose a new deep unsupervised domain adaptation (DUDA) framework, which can effectively solve the segmentation problem of LGE images without any annotations through cross domain based adversarial learning. A CycleGAN network is used to construct the LGE image training set, meanwhile, a encoder and classier is used as a segmentor to generate the prediction mask. To keep our domain adaption model segmentation results consistent, a new loss function named cross-domain consistency loss is introduced. We tested our method on the dataset of the MICCAI2019 Multi-Sequence cardiac MR image Segmentation Challenge. The average dice of the myocardium, left ventricle, and right ventricle segmentation is 0.762, 0.857, and 0.841, respectively. Compared with other domain adaptation methods, our method can well segment myocardium and right ventricle structures in LGE images. Experimental results prove the superiority of our proposed framework and it can effectively help doctors diagnose myocardial infarction faster without any manual intervention in the clinic.

Similar Papers
  • Research Article
  • Citations1

Persistence of Microvascular Obstruction From Early to Late Gadolinium Enhancement Images on Cardiac MRI: Prognostic Utility After STEMI-Analysis of EARLY-MYO-CMR Registry Data.

  • Oct 01, 2025
  • AJR. American journal of roentgenology
  • Jin-Yi Xiang +9
  • Research Article
  • Citations141

How to image cardiac amyloidosis.

  • May 01, 2014
  • Circulation: Cardiovascular Imaging
  • Rodney H Falk +2
  • PDF
  • Abstract
  • Citations4

T1 and T2 mapping CMR to quantify focal myocardial injury in patients with myocarditis

  • Feb 01, 2015
  • Journal of Cardiovascular Magnetic Resonance
  • Ulf K Radunski +8
  • Discussion

The Role of Cardiac Imaging in the Evaluation of Newly Diagnosed Heart Failure

  • Dec 02, 2015
  • The American Journal of Cardiology
  • Pairoj Rerkpattanapipat
  • Book Chapter
  • Citations14

Segmentation of Multimodal Myocardial Images Using Shape-Transfer GAN

  • Jan 01, 2020
  • Xumin Tao +3
  • Research Article
  • Citations3

Functional LGE Imaging: Cardiac Phase-Resolved Assessment of Focal Fibrosis.

  • Jul 01, 2019
  • Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
  • Sebastian Weingartner +5
  • Research Article
  • Citations226

Native T1-mapping detects the location, extent and patterns of acute myocarditis without the need for gadolinium contrast agents

  • May 23, 2014
  • Journal of Cardiovascular Magnetic Resonance
  • Vanessa M Ferreira +11
  • PDF
  • Research Article

Late Gadolinium Enhancement in Repaired Tetralogy of Fallot May Overestimate Right Ventricular Myocardial Fibrosis.

  • Feb 21, 2026
  • Pediatric cardiology
  • Martin Johansson +5
  • Research Article

Optimal timing of late gadolinium enhancement imaging in patients undergoing CMR for suspected pericarditis: the later the better?

  • Jun 19, 2023
  • European Heart Journal - Cardiovascular Imaging
  • G Moutzoukis +4
  • Research Article
  • Citations10

Impact of Wideband Late Gadolinium Enhancement Cardiac Magnetic Resonance Imaging on Device-Related Artifacts in Different Implantable Cardioverter-Defibrillator Types.

  • Mar 19, 2021
  • Journal of Magnetic Resonance Imaging
  • Amita Singh +10
  • Abstract

Visual detection and characterization of chronic myocardial infarctions in patients using native T1 maps at 3T

  • Feb 01, 2015
  • Journal of Cardiovascular Magnetic Resonance
  • Avinash Kali +13
  • Research Article
  • Citations13

Feasibility study of a single breath-hold, 3D mDIXON pulse sequence for late gadolinium enhancement imaging of ischemic scar.

  • Dec 31, 2018
  • Journal of Magnetic Resonance Imaging
  • James R.J Foley +10
  • Research Article

506 TECHNIQUES OF ARTIFICIAL INTELLIGENCE FOR THE DETERMINATION OF THE OPTIMAL INVERSION TIME: THE THAITI PROJECT

  • Dec 15, 2022
  • European Heart Journal Supplements
  • Camilla Torlasco +10
  • PDF
  • Research Article
  • Citations10

Synthetic late gadolinium enhancement cardiac magnetic resonance for diagnosing myocardial scar

  • Mar 16, 2018
  • Scandinavian Cardiovascular Journal
  • Goran Abdula +6
  • PDF
  • Research Article
  • Citations16

A clinical combined gadobutrol bolus and slow infusion protocol enabling angiography, inversion recovery whole heart, and late gadolinium enhancement imaging in a single study

  • Jan 01, 2016
  • Journal of Cardiovascular Magnetic Resonance
  • Animesh Tandon +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.