Thin-Slice Prostate MRI Enabled by Deep Learning Image Reconstruction
importance 4/10
partially solved
Advanced MRI Techniques and Applications prostate imaging stage: research
Problem
Thin-slice prostate MRI could improve cancer diagnostics but unacceptably prolongs acquisition time.
Why it matters
Better prostate MRI images can improve cancer detection, but longer scans reduce scanner throughput.
What the AI did
Deep learning image reconstruction accelerated thin-slice (2mm) T2-weighted TSE prostate MRI so it was acquired in similar time to conventional 3mm imaging in a 30-patient prospective study.
Results
Axial acquisition time 4:12 min (conventional 3mm) vs 4:37 min (thin-slice 2mm T2DLR)
Impact
Thin-slice imaging achieved with only ~25 seconds additional scan time in a small single-center study.
Record
| Venue | Cancers |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Sebastian Gassenmaier, Verena Warm, Dominik M. Nickel, Elisabeth Weiland, Judith Herrmann, Haidara Almansour, Daniel Wessling, Saif Afat |
| Citations | 26 (OpenAlex, at import time) |
| References | 33 |
| Model or method | deep learning image reconstruction (specific architecture not stated in source) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/cancers15030578 |
| Open access | gold |
| Keywords | deep learning, MRI reconstruction, prostate cancer, thin-slice imaging |
Importance rating
4
real but narrower advance
Real but narrow imaging advance: thin-slice prostate MRI with ~25s extra scan time; single-center 30-patient study, no scale stated.