Accurate estimation of intravoxel incoherent motion parameters based on implicit neural representation

Yunxiang Li, Yen‐Peng Liao, Yan Dai, Jie Deng, You Zhang · 2026

Read Accurate estimation of intravoxel incoherent motion parameters based on implicit neural representation by Yunxiang Li, Yen‐Peng Liao, Yan Dai, Jie Deng, You Zhang (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/PMC13411821.txt.

Description

Li and colleagues offer a way to extract measures from an MRI scan. The method uses a neural network that learns a scan as a function rather than crunching voxels one by one. The scan type, IVIM, separates water diffusion from blood microflow without dyes, but fitting is noise prone and ignores neighboring tissue. Their 2026 method works in two stages. A first network cleans the signal. A second fits the IVIM values, guided by coordinates and 3D patches.

On brain data the method's errors in tumor regions undercut every rival tested. On a breast imaging challenge set of one hundred cases, its error for the blood flow fraction fell by over half against a network baseline. In glioblastoma scans it gave the most repeatable readings, key for tracking treatment response. Steadier numbers from noisy scans, the authors argue, are what this technique needs to earn a clinical place.

Catalog record

CREATORYunxiang Li, Yen‐Peng Liao, Yan Dai, Jie Deng, You Zhang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE52 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13411821

Browse the full library · About the Tower of Babel