Neural networks improve repeatability of intravoxel incoherent motion (IVIM) parameter estimation in pancreatic diffusion-weighted MRI
Nitzan Avidan-Pearl, Daphna Link-Sourani, Ram Weiss, Moti Freiman · 2026
Read Neural networks improve repeatability of intravoxel incoherent motion (IVIM) parameter estimation in pancreatic diffusion-weighted MRI by Nitzan Avidan-Pearl, Daphna Link-Sourani, Ram Weiss, Moti Freiman (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/PMC13635040.txt.
Description
Nitzan Avidan-Pearl and three colleagues published this 2026 study on making a special MRI measurement steadier in the pancreas. The method, called IVIM, reads how water moves in tissue to reveal structure and blood flow without injection. Its numbers wobble with the math used to fit them, which has held back clinical use. The team scanned twelve volunteers twice, including two with type 1 diabetes, and compared four neural network fitting methods against two classic ones.
Every neural network method repeated the key blood-flow measure more faithfully than the classic fits. One network scored the steadiest readings, while another balanced steadiness across all measures. A shortened protocol kept or improved that steadiness, which matters for patient comfort. In a small extra group, both approaches sensed changes after a glucose drink. The authors caution that networks disagree on exact values, so accuracy checks must precede clinical trust.
Catalog record
| CREATOR | Nitzan Avidan-Pearl, Daphna Link-Sourani, Ram Weiss, Moti Freiman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |