Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
August 1, 2026Magnetic Resonance ImagingOpen Access

Toward self-contained cardiac magnetic resonance elastography: Deep learning-based segmentation of the left ventricular myocardium

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Accurate LV myocardium delineation is essential for cardiac MRE analysis but currently relies on manual annotation and additional structural MRI, leaving it uncertain whether native cardiac MRE data alone suffice for reliable automated segmentation.

Population

16 healthy male volunteers

Comparison

nnU-Net v2 and MedSAM frameworks vs manual annotation benchmarked against inter-reader agreement

Design

Deep learning model development and validation study

Key result

Deep learning models (nnU-Net and MedSAM) achieved accurate left ventricular myocardium segmentation from native cardiac MRE data with Dice scores of 0.82, matching inter-reader agreement (0.79).

Authors

VAVitaliy AtamaniukMAMatthias AndersMOMarzanna Obrzut

Discussion

Loading...

Member takes

Overview

Supports feasibility of automated LV segmentation from native MRE alone; leaves open clinical validation before workflow adoption.

Structured PICO

P
Population
16 healthy male volunteers providing cardiac MRE data for the evaluation of deep learning segmentation frameworks.
E
Exposure
Deep learning approaches for LV myocardium segmentation (nnU-Net v2 and MedSAM) on native cardiac MRE data
C
Comparator
Manual annotation (inter-reader agreement)
O
Outcome
Dice score for LV myocardium segmentationsurrogate

Main Result

Absolute Event Rate: 0.82% vs 0.79%

Deep learning models can accurately segment the left ventricular myocardium directly from native cardiac MRE data, achieving performance comparable to human readers.

Cite This Study

Atamaniuk et al. (2026) studied Healthy (n=16). Deep learning-based segmentation (nnU-Net v2 and MedSAM) vs. Manual annotation (inter-reader agreement) was evaluated on Dice score for LV myocardium segmentation. Deep learning models (nnU-Net and MedSAM) achieved accurate left ventricular myocardium segmentation from native cardiac MRE data with Dice scores of 0.82, matching inter-reader agreement (0.79).

synapsesocial.com/papers/6a7dea7c30df0be8fb5ca0b7https://doi.org/10.1016/j.mri.2026.110768
View Full Paper
Ask AI
Bookmark
Share