Improved unsupervised physics-informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients.

ABSTRACT:

Purpose

Earlier work showed that IVIM-NET_orig , 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-NET_optim , and characterizes its superior performance in pancreatic cancer patients.

Method

In simulations (signal-to-noise ratio [SNR] = 20), the accuracy, independence, and consistency of IVIM-NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root-mean-square error (NRMSE), Spearman's ρ, and the coef

SUBMITTER: Kaandorp MPT 

PROVIDER: S-EPMC8362093 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature