IVIM-Morph: Motion-compensated quantitative Intra-voxel Incoherent Motion (IVIM) analysis for functional fetal lung maturity assessment from diffusion-weighted MRI data

TL;DR

This study addresses the challenge of motion artifacts in fetal diffusion-weighted MRI (DWI) that compromise IVIM biomarker estimation of lung maturity. It introduces IVIM-Morph, a self-supervised framework that jointly estimates motion fields and IVIM parameters $(D, D^*, f)$ through a dual-network architecture and a biophysically informed loss that enforces plausible signal decay. The approach, validated on 39 fetal DWI datasets, improves the correlation between the perfusion fraction $f$ and gestational age (GA), particularly during the canalicular phase, and yields smoother, more physically consistent IVIM maps. The method offers a path to non-invasive, motion-robust biomarkers for fetal lung maturity and can be extended to other motion-sensitive quantitative DWI applications.

Abstract

Quantitative analysis of pseudo-diffusion in diffusion-weighted magnetic resonance imaging (DWI) data shows potential for assessing fetal lung maturation and generating valuable imaging biomarkers. Yet, the clinical utility of DWI data is hindered by unavoidable fetal motion during acquisition. We present IVIM-morph, a self-supervised deep neural network model for motion-corrected quantitative analysis of DWI data using the Intra-voxel Incoherent Motion (IVIM) model. IVIM-morph combines two sub-networks, a registration sub-network, and an IVIM model fitting sub-network, enabling simultaneous estimation of IVIM model parameters and motion. To promote physically plausible image registration, we introduce a biophysically informed loss function that effectively balances registration and model-fitting quality. We validated the efficacy of IVIM-morph by establishing a correlation between the predicted IVIM model parameters of the lung and gestational age (GA) using fetal DWI data of 39 subjects. IVIM-morph exhibited a notably improved correlation with gestational age (GA) when performing in-vivo quantitative analysis of fetal lung DWI data during the canalicular phase. IVIM-morph shows potential in developing valuable biomarkers for non-invasive assessment of fetal lung maturity with DWI data. Moreover, its adaptability opens the door to potential applications in other clinical contexts where motion compensation is essential for quantitative DWI analysis. The IVIM-morph code is readily available at: https://github.com/TechnionComputationalMRILab/qDWI-Morph.

Figures (7)

• Figure 1: Fetal DWI data acquired with varying b-values. Fetal motion causes the observed signal (red circles) to deviate from the expected signal decay model (solid line). Fitting the model to the observed signal without accounting for motion may lead to an incorrect estimate of the model parameters (dashed line).
• Figure 2: The architecture of the IVIM-Morph network, comprises two sub-networks: a quantitative IVIM (qIVIM), a convolutional neural network (CNN), and an image registration sub-network. The qIVIM-CNN sub-network extracts IVIM parameters from the DWI data, while the image registration sub-network aligns each b-value image with the corresponding image reconstructed by the IVIM parameters.
• Figure 3: Signal decay along the relaxation axis (b-value) after registration with SyN-Reg to b0, Iterative SyN-TRF, and IVIM-Morph. Although IVIM-Morph yielded a lower Dice score in this case compared to other methods, it better preserved the expected signal decay behavior, reflecting a more physically plausible registration.
• Figure 4: Average dice coefficient computed for lung segmentation between $S_0$ and the deformed lung segmentation in $S_i$ (for $i > 0$), utilizing IVIM-Morph in 10 specifically chosen cases with varying $\alpha_3$ values. The blue line indicates the cases characterized by major motion, whereas the orange line corresponds to the cases with minor motion.
• Figure 5: Results from the Lung Segmentation Evaluation Experiment. The bar plot at the top illustrates the dice coefficients for cases with significant motion, while the bottom bar plot shows the dice coefficients for cases with minimal motion. In both plots, the dashed line and the shaded area indicate the average and standard deviation of the dice scores prior to the application of registration.