Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 17, 2025Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition

Unsupervised whole-heart function assessment

View Full Paper
Ask AI
Bookmark
Share

Authors

YZYundi ZhangDRDaniel RueckertJPJiazhen Pan

Discussion

Loading...

Member takes

Overview

Unsupervised approach enables cardiac function assessment in unlabeled MR images, suggesting advancements in cardiovascular disease screening.

Key Points

  • Strong temporal feature extraction aids in identifying distinct cardiac phenotypes through unsupervised learning.
  • t-SNE visualization and kNN clustering confirm the association between latent space and various cardiac temporal states.
  • A robust latent space is created by reconstructing masked 2D+T planes, enhancing analysis of cardiac function.
  • This scalable method potentially advances cardiovascular disease applications by streamlining cardiac diagnosis.

Cite This Study

Zhang et al. (2025) studied this question.

synapsesocial.com/papers/68d42934713b0b5dfea6e877https://doi.org/10.58530/2025/1031
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Registration-Guided Cardiac Functional Assessment from Limited Annotations in a Single Breath-hold Cine2025
  2. 2Towards cardiac MRI foundation models: Comprehensive visual-tabular representations for whole-heart assessment and beyond2025 · 3 citations
  3. 3Automated Deep Learning Cine MRI Segmentation for Cardiac Function Assessment in Preclinical Models2025
  4. 4Cardiac Function Assessment with Deep-Learning-Based Automatic Segmentation of Free-Running 4D Whole-Heart CMR2025
  5. 5A novel unsupervised machine learning clustering strategy to identify PET/MR biomarkers in arrhythmogenic cardiomyopathy2025