Improving Clinical Utility of Fetal Cine CMR Using Deep Learning Super-Resolution
Authors' conclusion
Deep learning super-resolution reconstructions of low-resolution acquisitions shorten acquisition times and achieve diagnostic quality comparable with standard images, while being less sensitive to fetal bulk movements, leading to additional diagnostic findings. Therefore, deep learning super-resolution may improve the clinical utility of fetal cardiovascular magnetic resonance for accurate prenatal assessment of congenital heart disease.
Study context
- Population
- Participants with fetal congenital heart disease undergoing fetal cardiovascular magnetic resonance in the third trimester of pregnancyparticipants (median gestational age, 35.9 weeks [interquartile range (IQR), 35.1–36.4])
- Participants
- 42 participants
- Exposure
- Deep learning super-resolution reconstructions of low-resolution cine (cine DL) vs cine images acquired at normal resolution
- Outcome
- Acquisition time
Main finding
As reported in the abstract
Cine DL
134±9.6
s
Cine images acquired at normal resolution
252±8.8
s
P < 0.001
Observational data: associations, not effects.
Further findings
| Outcome | Cine DL | Cine images acquired at normal resolution | P value |
|---|---|---|---|
| Image quality score: fetal motion (5-point Likert)Median | 4.0 (IQR 4.0–5.0) | 4.0 (IQR 3.0–4.0) | P < 0.001 |
| Nonpatient-related artifacts (eg, backfolding)More pronounced in cine DL | 4.0 (IQR 4.0–5.0) | 5.0 (IQR 3.0–4.0) | P < 0.001 |
- Image quality score: fetal motion (5-point Likert): quantitative image quality metrics and image quality scores for cine DL higher or comparable
Volumetry and functional results
- Comparable
Additional findings with cine DL
- Additional structures
- 10 of 42 fetuses (24%)
- Additional pathologies, including partial anomalous pulmonary venous connection
- 5 of 42 fetuses (12%)
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →