Diffusion parameter mapping with the combined intravoxel incoherent motion and kurtosis model using artificial neural networks at 3 T. (28th September 2017)

• Record Type: Journal Article
• Authors: Bertleff, Marco; Domsch, Sebastian; Weingärtner, Sebastian; Zapp, Jascha; O'Brien, Kieran; Barth, Markus; Schad, Lothar R.
• Is Part Of: NMR in biomedicine. Volume 30:Number 12(2017:Dec.)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2017-09-28
• Subjects: artificial neural network -- diffusion -- intravoxel incoherent motion -- kurtosis -- machine learning; Nuclear magnetic resonance -- Periodicals; Magnetic Resonance Spectroscopy -- Periodicals; 574
• DOI: 10.1002/nbm.3833
• Languages: English
• ISSNs: 0952-3480

Abstract

Abstract : Artificial neural networks (ANNs) were used for voxel‐wise parameter estimation with the combined intravoxel incoherent motion (IVIM) and kurtosis model facilitating robust diffusion parameter mapping in the human brain. The proposed ANN approach was compared with conventional least‐squares regression (LSR) and state‐of‐the‐art multi‐step fitting (LSR‐MS) in Monte‐Carlo simulations and in vivo in terms of estimation accuracy and precision, number of outliers and sensitivity in the distinction between grey (GM) and white (WM) matter. Both the proposed ANN approach and LSR‐MS yielded visually increased parameter map quality. Estimations of all parameters (perfusion fraction f, diffusion coefficient D, pseudo‐diffusion coefficient D*, kurtosis K ) were in good agreement with the literature using ANN, whereas LSR‐MS resulted in D* overestimation and LSR yielded increased values for f and D*, as well as decreased values for K . Using ANN, outliers were reduced for the parameters f (ANN, 1%; LSR‐MS, 19%; LSR, 8%), D* (ANN, 21%; LSR‐MS, 25%; LSR, 23%) and K (ANN, 0%; LSR‐MS, 0%; LSR, 15%). Moreover, ANN enabled significant distinction between GM and WM based on all parameters, whereas LSR facilitated this distinction only based on D and LSR‐MS on f, D and K . Overall, the proposed ANN approach was found to be superior to conventional LSR, posing a powerful alternative to the state‐of‐the‐art method LSR‐MS with several advantages in the estimation of IVIM–kurtosis parameters, which might facilitate increased applicability of enhanced diffusion models at clinical scan times. Abstract : Artificial neural networks (ANNs) were used for voxel‐wise parameter estimation with the combined intravoxel incoherent motion (IVIM) and kurtosis model facilitating robust diffusion parameter mapping in the human brain. The results indicate close agreement with the literature and substantial gains in the estimation accuracy and precision, as well as sensitivity to different tissue types, over conventional least‐squares regression. Compared with state‐of‐the‐art multi‐step fitting, the proposed ANN approach further reduces intra‐subject variations and outliers. The robust performance may facilitate increased applicability of the IVIM–kurtosis model at clinically acceptable scan times.