Improving cardiac magnetic resonance imaging with deep-learning image reconstruction in patients with cardiomyopathy

Not Applicable

Recruiting

Conditions: I42
Complications and ill-defined descriptions of heart disease
I51
Cardiomyopathy

Registration Number: DRKS00026721

Lead Sponsor: niversitätsklinikum Tübingen

Brief Summary: Not available

Detailed Description: Not available

Recruitment & Eligibility

Status: Recruiting

Sex: All

Target Recruitment: 320

Inclusion Criteria

For healthy subjects:
- Age =18 years,
- Written informed consent, including consent to report incidental findings.

For patients:
- Suspicion of cardiomyopathy and / or myocardial fibrosis,
- Clinical indication for cardiac MRI by treating cardiologist,
- Age =18 years,
- Written consent of the patient.

Exclusion Criteria

For healthy subjects:
- Subjects who are not capable of giving consent,
- Presence of non-MR-compatible implants or any kind of metal in and on the body (e.g. pacemakers, artificial heart valves, implanted magnetic metal parts, etc. that are not MR-compatible),
- Increased sensitivity to loud noises,
- Claustrophobia,
- Obesity with >150 kg body weight.

For patients:
- Presence of non-MR compatible implants or any type of metal in and on the body (e.g. pacemakers, artificial heart valves, implanted magnetic metal parts, etc. that are not MR compatible),
- Increased sensitivity to loud noises,
- Claustrophobia,
- Obesity with >150 kg body weight,
- Contraindication to MRI-contrast agent,
- Limited capacity to give consent.

Study & Design

Study Type: interventional

Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
The primary objective is to investigate the feasibility of valid cardiac MRI imaging with deep learning image reconstruction in patients with cardiomyopathy. <br>In healthy volunteers, the possible acceleration factor for cardiac MRI will first be narrowed down using MR sequences with different acceleration levels, in order to use the selected sequence modifications in the patients in a second step. <br>

Secondary Outcome Measures

Name	Time	Method
- Review of artefact susceptibility and identification of causes of artefacts in CMR,<br>- Improve CMR image quality through deep learning image reconstruction,<br>- Predictability of target areas for electrophysiological mapping and ablation based on CMR.