Improved unsupervised physics‐informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients
Improved unsupervised physics‐informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients
Misha P. T. Kaandorp,S. Barbieri,5 Authors,Oliver J. Gurney-Champion
TLDR
A substantially improved version of IVIM‐NETorig, an unsupervised physics‐informed deep neural network, is presented and its superior performance in pancreatic cancer patients is characterized.
Abstract
Earlier work showed that IVIM‐NETorig, an unsupervised physics‐informed deep neural network, was faster and more accurate than other state‐of‐the‐art intravoxel‐incoherent motion (IVIM) fitting approaches to diffusion‐weighted imaging (DWI). This study presents a substantially improved version, IVIM‐NEToptim, and characterizes its superior performance in pancreatic cancer patients.