Impact of deep-learning image reconstruction on multiplexed sensitivity encoding diffusion-weighted imaging in the female pelvis
Elaine Yuen Phin Lee, Chia-Wei Li, Grace Ho, Chien-Yuan Lin, Andy Cheuk Nam Hwang, Rahul Singh, Patricia Lan, Xinzeng Wang · 2026
Read Impact of deep-learning image reconstruction on multiplexed sensitivity encoding diffusion-weighted imaging in the female pelvis by Elaine Yuen Phin Lee, Chia-Wei Li, Grace Ho, Chien-Yuan Lin, Andy Cheuk Nam Hwang, Rahul Singh, Patricia Lan, Xinzeng Wang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13350632.txt.
Description
Elaine Yuen Phin Lee and co-authors tested in 2026 whether deep-learning rebuild lifts multiplexed sensitivity encoding diffusion-weighted MRI of the female pelvis, where artefacts often spoil image quality. Diffusion imaging helps characterise pelvic lesions. Yet motion and susceptibility artefacts curb its trustworthiness.
Patients booked for pelvic MRI with two-shot MUSE diffusion imaging were enrolled prospectively, with a subset also getting paired four-shot scans. Two radiologists rated overall quality, artefacts, lesion visibility, and sharpness on a five-point scale, with and with no deep-learning rebuild, while signal, contrast, and apparent diffusion coefficients were weighed quantitatively. The rebuild lifted quality with no distortion of quantitative measures, backing its use in pelvic MRI.
Catalog record
| CREATOR | Elaine Yuen Phin Lee, Chia-Wei Li, Grace Ho, Chien-Yuan Lin, Andy Cheuk Nam Hwang, Rahul Singh, Patricia Lan, Xinzeng Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 20 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |