Deep Learning Super-Resolution Single-Beat CMR (DL-SB-CMR)

Clinical Evaluation of Deep Learning-Enhanced Super-Resolution Single-Beat CMR: Prospective Comparison Study

Deep learning super-resolution reconstruction is an emerging technique that enhances the resolution of cardiac magnetic resonance (CMR) scans beyond the original acquisition through post-processing. This study investigates whether a deep learning-based single-beat super-resolution CMR protocol-including cine, T2-STIR, and LGE sequences-can provide diagnostic equivalence to a standard segmented CMR protocol. Total scan time, diagnostic confidence, and diagnostic interchangeability are compared between protocols, with particular focus on wall motion abnormalities, myocardial edema, pericardial effusion, late gadolinium enhancement and final diagnosis. The goal is to assess diagnostic interchangeability while improving efficiency and motion robustness.

Study Overview

• Status: Completed
• Conditions: Heart Diseases; Myocardial Disease

Detailed Description

Cardiac magnetic resonance (CMR) is the gold standard for non-invasive assessment of myocardial diseases, providing comprehensive information through e.g. cine imaging, T2-weighted sequences, and late gadolinium enhancement (LGE). Conventional CMR protocols typically rely on segmented (multi-shot) acquisitions over multiple heartbeats and require repeated breath-holds, which can limit patient comfort and compliance. While these segmented sequences offer high spatial resolution, they are prone to motion and respiratory artifacts-particularly in patients with arrhythmias or dyspnea-and contribute to long total examination times.

Recent advances in deep learning (DL) reconstruction techniques have enabled substantial acceleration of segmented CMR sequences, particularly for cine and LGE imaging. These approaches effectively reduce acquisition time but still rely on regular cardiac rhythm and adequate breath-holding capacity, limiting their applicability in more challenging patient populations. In contrast, single beat (or: single-shot) imaging acquires data within a single heartbeat, offering a motion-robust alternative, though at the cost of lower spatial resolution.

Efforts to streamline CMR are ongoing, with some studies proposing to reduce comprehensive exam times to 30 minutes or less. In parallel, full DL-based reconstruction MRI protocols are being increasingly explored across MRI domains, including neuroimaging and musculoskeletal imaging. Applying deep learning super-resolution to CMR, particularly in combination with single-beat acquisitions with the option of free-breathing acquisition, may enhance both speed and robustness.

This prospective investigates whether a deep learning-based single-beat super-resolution CMR protocol - including single-shot cine, T2-STIR, and LGE sequences in both short- and long-axis views - can provide diagnostic interchangeability to a standard segmented protocol. All participants undergo both protocols during the same exam session. Total scan times are compared between protocols using Student's t-test. Three blinded readers evaluate predefined diagnostic categories including wall motion abnormalities, pericardial effusion, myocardial edema, LGE, and the final CMR diagnosis. Generalized estimating equations with bootstrapped 95% confidence intervals and a predefined equivalence margin of ±5% was used for the interchangeability analysis. Agreement in categorical ratings was evaluated using Cohen's Kappa and Fleiss' Kappa, as appropriate. Diagnostic confidence was rated on a 5-point Likert scale.

• Study Type: Observational
• Enrollment (Actual): 107

Contacts and Locations

Study Locations

• Germany
  • NRW
    • Bonn, NRW, Germany, 53123
      • University Hospital Bonn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients with clinical indication for CMR

Description

Inclusion Criteria:

• Clinical indication for CMR
• Aged 18 years or older.
• Willing to participate in the study.
• Able and willing to provide signed informed consent.

Exclusion Criteria:

• Pregnant or breastfeeding women
• Non-removable magnetic metallic implants, prosthetic devices, or extensive tattoos covering large areas of the body
• Presence of a non-MRI safe pacemaker or neurostimulator

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort
Patient cohort; suspected myocardial disease with clinical indication for CMR; undergoing one CMR with two integrated protocols (standard and DL single beat protocol)

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic interchangeability	Assessment of diagnostic interchangeability between the deep learning-based single-beat SuperRes CMR protocol and the standard segmented CMR protocol. Diagnostic categories include wall motion abnormalities, pericardial effusion, myocardial edema, late gadolinium enhancement, and the final CMR diagnosis. Interchangeability was evaluated using generalized estimating equations with bootstrapped 95% confidence intervals and a predefined equivalence margin of ±5%. For each category, the outcome is expressed as an individual equivalence index (%), defined as the difference in agreement probabilities.	May - December 2024

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Scan time	Comparison of total scan duration between the deep learning-based single-beat SuperRes CMR protocol and the standard segmented CMR protocol.	May - December 2024

Collaborators and Investigators

• Sponsor: University Hospital, Bonn
• Investigators: Principal Investigator: Alexander Isaak, PD Dr., University Hospital Bonn, Germany; Study Director: Julian Luetkens, Prof., University Hospital Bonn, Germany

Study record dates

Study Major Dates

• Study Start (Actual): May 1, 2024
• Primary Completion (Actual): December 31, 2024
• Study Completion (Actual): December 31, 2024

Study Registration Dates

• First Submitted: June 3, 2025
• First Submitted That Met QC Criteria: June 11, 2025
• First Posted (Actual): June 19, 2025

Study Record Updates

• Last Update Posted (Actual): June 26, 2025
• Last Update Submitted That Met QC Criteria: June 20, 2025
• Last Verified: June 1, 2025

More Information

Terms related to this study

• Keywords: deep learning; cardiovascular magnetic resonance; cardiac imaging techniques; image reconstructions; single-beat; super-resolution; accelerated imaging
• Additional Relevant MeSH Terms: Cardiovascular Diseases; Heart Diseases; Cardiomyopathies
• Other Study ID Numbers: 2024-379-BO

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No