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

• Published in: arXiv.org
• Main Authors: Kaandorp, Misha P T, Barbieri, Sebastiano, Klaassen, Remy, Hanneke W M van Laarhoven, Crezee, Hans, While, Peter T, Nederveen, Aart J, Gurney-Champion, Oliver J
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 23.03.2021
• Subjects: Artificial neural networks; Bayesian analysis; Coefficient of variation; Computer architecture; Consistency; Deep learning; Pancreatic cancer; Parameters; Performance evaluation
• ISSN: 2331-8422

\({\bf Purpose}\): 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. \({\bf Method}\): 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 \(\rho\), 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. \({\bf Results}\): 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 (\(\rho\)(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. \({\bf Conclusion}\): IVIM-NET\(_{optim}\) is recommended for IVIM fitting to DWI data.