What does this research mean for the field?

Deep learning super-resolution imaging significantly improves edema visualization in cardiovascular magnetic resonance while reducing scan time by up to 86%. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.SUPPORTS_CONSENSUS.

What question did this study set out to answer?

This study aimed to evaluate the quality of deep learning super-resolution T2-weighted imaging for edema detection in cardiovascular magnetic resonance.

March 10, 2026Open Access

Ultrafast deep learning super-resolution single-shot T2-weighted imaging for robust edema visualization in cardiovascular magnetic resonance

Key Result

Deep learning super-resolution T2-STIR imaging cut scan time by up to 86% and improved edema visibility and diagnostic certainty versus standard T2-STIR in 81 patients.

Key Points

This study aimed to evaluate the quality of deep learning super-resolution T2-weighted imaging for edema detection in cardiovascular magnetic resonance.
Evaluated diagnostic quality of DL super-resolution and standard T2-STIR imaging techniques
Included 81 participants in a cardiomyopathy CMR protocol at 1.5 T
Used a five-point Likert scale for quality assessment by two readers
Performed statistical analysis with Friedman test and one-way ANOVA
No significant difference in edema detection between DL-SSH T2-STIR and reference methods
Scan times reduced by 63% for breath-hold and 86% for free-breathing DL-SSH T2-STIR
DL-SSH T2-STIR improved image contrast and diagnostic certainty compared to standard T2-STIR
Higher inter-rater agreement in edema visibility ratings was noted with DL-SSH imaging
Slice level analysis confirmed superior quality in apical slices using DL-SSH T2-STIR

Structured PICO

Does deep learning super-resolution single-shot T2-STIR imaging improve diagnostic quality and reduce scan time compared to standard T2-STIR in patients undergoing cardiovascular magnetic resonance?

Population

81 participants (mean age: 54 ± 20 years; 50 men) undergoing a standard cardiomyopathy CMR protocol at 1.5 T.

Intervention

Deep learning (DL) super-resolution reconstructed breath-hold (BH) and free-breathing (FB) single-shot (SSH) black-blood T2-weighted short tau inversion recovery (STIR) imaging.

Comparator

Standard breath-hold (BH) T2-STIR imaging.

Outcome

Diagnostic quality and certainty evaluated using a five-point Likert scale, and presence of focal edema.surrogate

Deep learning super-resolution single-shot T2-STIR imaging significantly reduces scan time and improves diagnostic certainty and edema visibility compared to standard T2-STIR in cardiovascular magnetic resonance.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

To compare the diagnostic quality of deep learning (DL) super-resolution reconstructed breath-hold (BH) and free-breathing (FB) single-shot (SSH) black-blood T2-weighted short tau inversion recovery (STIR) imaging with standard BH T2-STIR in cardiovascular magnetic resonance (CMR). In this prospective study, short-axis BH and FB SSH T2-STIR were added to a standard cardiomyopathy CMR protocol at 1.5 T, and DL super-resolution reconstruction were performed. Two readers evaluated diagnostic quality and certainty using a five-point Likert scale. Presence of focal edema was assessed on T2-weighted sequences including standard T2-STIR and T2 mapping (both used for reference clinical assessment) as well as SSH T2 STIR and DL-SSH T2-STIR. Friedman test and one-way ANOVA were performed. 81 participants (mean age: 54 ± 20 years; 50 men) were included. No difference was found in edema detection between reference assessment and DL-SSH T2-STIR (both 21/81 participants 26%). Scan time was reduced by 63% for BH and 86% for FB DL-SSH T2-STIR compared to standard T2-STIR (90±6 sec vs. 35±3 sec vs. 243±16 sec; p<.0001). BH and FB DL-SSH T2-STIR achieved lower artifact burden (5 IQR, 4–5 vs. 4 IQR, 4–5 vs. 4 IQR, 3–5; p<.0001), superior image contrast and sharpness compared to standard T2-STIR, especially in non-cooperative or arrhythmic participants. BH and FB DL-SSH T2-STIR imaging provided higher diagnostic certainty than standard T2-STIR (5 IQR, 5–5 vs. 5 IQR, 5–5 vs. 4 IQR, 4–5; p<.0001). Edema visibility was superior in BH DL-SSH compared to BH-SSH and standard T2-STIR (5 IQR, 4.8–5 vs. 4 IQR, 3.3–5 vs. 4 IQR, 3–4.8; p<.0001). Inter-rater agreement was substantial to excellent in the rating of edema visibility (BH DL-SSH T2-STIR, κ: 0.73 95% CI: 0.44-1.0; BH SSH T2-STIR, κ: 0.79 95% CI: 0.66-0.97; standard T2-STIR, κ: 0.86 95% CI: 0.71-1.0). Slice level-analysis showed that BH DL-SSH T2-STIR consistently provided superior image quality in apical slices compared to BH SSH and standard T2-STIR (4 IQR, 4–5 vs. 4 IQR, 4–4 vs. 4 IQR, 3–4; p<.0001). DL-SSH imaging enabled ultrafast T2-STIR acquisition and robust edema assessment in routine clinical CMR.