Improved unsupervised physics-informed deep learning for intravoxel incoherent motion modeling and evaluation in pancreatic cancer patients
Misha P. T. Kaandorp, Sebastiano Barbieri, Remy Klaassen, Hanneke W. M. van Laarhoven, Hans Crezee, Peter T. While, Aart J. Nederveen, Oliver J. Gurney-Champion
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/oliverchampion/IVIMNETOfficialIn paperpytorch★ 26
Abstract
Purpose: Earlier work showed that IVIM-NET_orig, an unsupervised physics-informed deep neural network, was more accurate than other state-of-the-art intravoxel-incoherent motion (IVIM) fitting approaches to DWI. This study presents an improved version: IVIM-NET_optim, and characterizes its superior performance in pancreatic ductal adenocarcinoma (PDAC) patients. Method: In simulations (SNR=20), the accuracy, independence and consistency of IVIM-NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, # hidden layers, dropout, batch normalization, learning rate), by calculating the NRMSE, Spearman's , and the coefficient of variation (CV_NET), respectively. The best performing network, IVIM-NET_optim was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM-NET_optim's performance was evaluated in 23 PDAC patients. 14 of the patients received no treatment between scan sessions and 9 received chemoradiotherapy between sessions. Intersession within-subject standard deviations (wSD) and treatment-induced changes were assessed. Results: In simulations, IVIM-NET_optim outperformed IVIM-NET_orig in accuracy (NRMSE(D)=0.18 vs 0.20; NMRSE(f)=0.22 vs 0.27; NMRSE(D*)=0.39 vs 0.39), independence ((D*,f)=0.22 vs 0.74) and consistency (CV_NET (D)=0.01 vs 0.10; CV_NET (f)=0.02 vs 0.05; CV_NET (D*)=0.04 vs 0.11). IVIM-NET_optim showed superior performance to the LS and Bayesian approaches at SNRs<50. In vivo, IVIM-NET_optim sshowed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM-NET_optim detected the most individual patients with significant parameter changes compared to day-to-day variations. Conclusion: IVIM-NET_optim is recommended for IVIM fitting to DWI data.