Search

The third trimester of pregnancy is a period of rapid development of fiber bundles in the fetal white matter. Using a recently developed motion‐tracked slice‐to‐volume registration (MT‐SVR) method, we aimed to quantify tract‐specific developmental changes in apparent diffusion coefficient (ADC), fractional anisotropy (FA), and volume in third trimester healthy fetuses. To this end, we reconstructed diffusion tensor images from motion corrected fetal diffusion magnetic resonance imaging data. With an approved protocol, fetal MRI exams were performed on healthy pregnant women at 3 Tesla and included multiple (2–8) diffusion scans of the fetal head (1–2 b = 0 s/mm2 images and 12 diffusion‐sensitized images at b = 500 s/mm2). Diffusion data from 32 fetuses (13 females) with median gestational age (GA) of 33 weeks 4 days were processed with MT‐SVR and deterministic tractography seeded by regions of interest corresponding to 12 major fiber tracts. Multivariable regression analysis was used to evaluate the association of GA with volume, FA, and ADC for each tract. For all tracts, the volume and FA increased, and the ADC decreased with GA. Associations reached statistical significance for: FA and ADC of the forceps major; volume and ADC for the forceps minor; FA, ADC, and volume for the cingulum; ADC, FA, and volume for the uncinate fasciculi; ADC of the inferior fronto‐occipital fasciculi, ADC of the inferior longitudinal fasciculi; and FA and ADC for the corticospinal tracts. These quantitative results demonstrate the complex pattern and rates of tract‐specific, GA‐related microstructural changes of the developing white matter in human fetal brain. [ABSTRACT FROM AUTHOR]

With an aim to increase the capture range and accelerate the performance of state-of-the-art inter-subject and subject-to-template 3-D rigid registration, we propose deep learning-based methods that are trained to find the 3-D position of arbitrarily-oriented subjects or anatomy in a canonical space based on slices or volumes of medical images. For this, we propose regression convolutional neural networks (CNNs) that learn to predict the angle-axis representation of 3-D rotations and translations using image features. We use and compare mean square error and geodesic loss to train regression CNNs for 3-D pose estimation used in two different scenarios: slice-to-volume registration and volume-to-volume registration. As an exemplary application, we applied the proposed methods to register arbitrarily oriented reconstructed images of fetuses scanned in-utero at a wide gestational age range to a standard atlas space. Our results show that in such registration applications that are amendable to learning, the proposed deep learning methods with geodesic loss minimization achieved 3-D pose estimation with a wide capture range in real-time (<100ms). We also tested the generalization capability of the trained CNNs on an expanded age range and on images of newborn subjects with similar and different MR image contrasts. We trained our models on T2-weighted fetal brain MRI scans and used them to predict the 3-D pose of newborn brains based on T1-weighted MRI scans. We showed that the trained models generalized well for the new domain when we performed image contrast transfer through a conditional generative adversarial network. This indicates that the domain of application of the trained deep regression CNNs can be further expanded to image modalities and contrasts other than those used in training. A combination of our proposed methods with accelerated optimization-based registration algorithms can dramatically enhance the performance of automatic imaging devices and image processing methods of the future. [ABSTRACT FROM AUTHOR]

• We propose a method to generate realistic data and parameter maps for fetal DW-MRI. • Our method uses data from fetuses and preterm newborns in a synergistic manner. • We use the generated data to train a deep learning model to predict color-FA. • On fetal test data, our method achieves significantly more accurate predictions. • Predictions of the deep learning model obtain higher scores from neuroanatomists. Diffusion-weighted magnetic resonance imaging (DW-MRI) of fetal brain is challenged by frequent fetal motion and signal to noise ratio that is much lower than non-fetal imaging. As a result, accurate and robust parameter estimation in fetal DW-MRI remains an open problem. Recently, deep learning techniques have been successfully used for DW-MRI parameter estimation in non-fetal subjects. However, none of those prior works has addressed the fetal brain because obtaining reliable fetal training data is challenging. To address this problem, in this work we propose a novel methodology that utilizes fetal scans as well as scans from prematurely-born infants. High-quality newborn scans are used to estimate accurate maps of the parameter of interest. These parameter maps are then used to generate DW-MRI data that match the measurement scheme and noise distribution that are characteristic of fetal data. In order to demonstrate the effectiveness and reliability of the proposed data generation pipeline, we used the generated data to train a convolutional neural network (CNN) to estimate color fractional anisotropy (CFA). We evaluated the trained CNN on independent sets of fetal data in terms of reconstruction accuracy, precision, and expert assessment of reconstruction quality. Results showed significantly lower reconstruction error (n = 100 , p < 0.001) and higher reconstruction precision (n = 20 , p < 0.001) for the proposed machine learning pipeline compared with standard estimation methods. Expert assessments on 20 fetal test scans showed significantly better overall reconstruction quality (p < 0.001) and more accurate reconstruction of 11 regions of interest (p < 0.001) with the proposed method. [ABSTRACT FROM AUTHOR]