Recently, many advancements have been made in accelerated MRI reconstruction with the use of neural networks. Such deep learning methods learn a suitable MRI prior distribution from large sets of training data. For MRI images acquired with an uncommon scanning sequence, large datasets required for training are not available. Additionally, deep learning methods do not generalize well to unseen data. Therefore, in this research, a framework is proposed for accelerated MRI reconstruction trained with simulated data. The framework uses a Recurrent Inference Machine (RIM). The RIM is a deep learning framework that learns an iterative inference process. The RIM framework has been chosen as it is designed to learn the inversion process itself rather than the image statistics. Therefore, RIMs have a low tendency to overfit, and a high capacity to generalize to unseen data. The framework is evaluated by reconstructing undersampled data of in-vivo brain MRI images and comparing them with zero-filled reconstructions, reconstructions of an identical framework trained with in-vivo data and ESPIRiT reconstructions. The comparison shows that the framework does partly learn the inference process; however, the reconstructions still contain artefacts and the reconstruction of the framework trained with in-vivo data and the ESPIRiT method are of higher quality. For simulated data to replace in-vivo data for the training of the RIM, the simulated data has to be more similar to the in-vivo data.

Long acquisition times impede the routine clinical use of quantitative magnetic resonance imaging (qMRI). qMRI quantifies meaningful tissue parameters in T1-, T2-, and PD-maps, as opposed to conventional (qualitative) weighted MRI (wMRI), which only visualises contrast between tissues. Although methods exist that generate synthetic wMRI from qMRI, the inverse problem has not been thoroughly studied yet. A method to generate qMRI from wMRI would be beneficial as it does not change current clinical workflows and enables retrospective quantitative analysis. This thesis investigates to what extent fully convolutional networks are successful in generating qMRI from T1-weighted, T2-weighted, PD-weighted and T2-weighted-FLAIR scans. A set of synthetic wMRI scans from 97 healthy volunteers was split into training, validation and test sets for development of our models. We varied model architectures, loss functions and learning rates during training, in order to find the best performing models. These were able to predict qMRI with median errors of approximately 5% on the test set. Additionally, we determined the amount of information contained in the input scans by training models using different combinations of the input. These results showed that T1-weighted, T2-weighted and PD-weighted scans were the most important. Models trained on synthetic wMRI were tested on an additional dataset of real wMRI. This resulted in higher median errors of 27.4%, 12.0% and 8.7% for T1-, T2- and PD-maps respectively. Furthermore, the same models were tested on a third dataset of synthetic tumour scans and mainly showed errors around the tumour core. These results show that more research is necessary in order to improve the performances of models generating qMRI to a clinical standard.

Perivascular spaces (PVS) visible on MRI are currently emerging as an important potential neuroimaging marker for several pathologies in the brain like Alzheimer’s disease and cerebral small vessel disease. PVS are fluid-filled spaces surrounding vessels as they enter the brain. Although PVS are normally not noticeable on MRI scans acquired at clinical field strengths, when these spaces increase in size they become increasingly visible and quantifiable. To study these spaces it is important to have a robust method for quantifying PVS. Manual quantification of PVS is challenging, time-consuming and subject to observer bias due to the difficulty of distinguishing PVS from mimics and the large number of PVS that can occur in MRI scans. Many promising (semi-)automated methods have been proposed recently to decrease annotation time and intra- and inter-observer variability while providing more information about EPVS. However there are still various limitations in the current methods that need to be overcome.
An important limitation is that most of the methods are based on elaborate preprocessing steps, feature extraction and heuristic fine-tuning of parameters, making the use of these methods on new datasets cumbersome. Furthermore the majority of the currently proposed methods have been evaluated on small sets of barely 30 images, as most of these methods aim to segment PVS and require voxel-wise annotations for evaluation. In this thesis we propose a method for automated detection of perivascular spaces that combines a convolutional neural network and geodesic distance transform (GDT). We propose to use dot annotations instead of voxel-wise segmentations as this is less time-consuming than fully segmenting PVS while still providing the location of PVS. This enables us to use a considerably larger dataset with ground truth locations than is used in all previously proposed (semi-)automatic methods that provide the location of PVS. We investigated two approaches of using geodesic distance transform to optimize the CNN to detect PVS. The first approach focuses on optimizing the CNN for voxel-wise regression of the geodesic distance map (GDM) computed from the dots and the intensity image. The second approach aims to predict segmentations of the PVS using a CNN that is trained on approximated segmentations obtained by thresholding GDMs. We use 1202 proton density-weighted (PDw) MRI scans to develop our methods and 1000 other scans are used to evaluate the performance of the methods. We show that our methods match human intra-rater performance on detecting PVS without the need for any user interaction. Additionally we show that GDMs are extremely useful for capturing complex morphologies when computed from dot annotations. Our experiments indicate that GDMs can be used to provide valuable additional information to CNNs during training.

Cardiovascular diseases and stroke are currently the leading causes of death worldwide. Atherosclerotic plaque is a mostly asymptotic vascular disease, but rupture of an atherosclerotic plaque in the carotid artery could lead to stroke. Automated segmentation of plaque components could help improve risk assessment by producing fast and reliable results while saving costs.

In this thesis two extensive comparisons have been made. First supervised classifiers are compared in the pixel-wise segmentation task of plaque components. In this comparison five conventional machine learning techniques and one deep learning architecture have been evaluated: linear and quadratic Bayes normal classifiers, linear logistic classifier, random forest and a U-net architecture. In the second comparison classifiers are evaluated in a detection task for their ability to learn with weakly labelled data. This is done within the multiple instance learning (MIL) framework. In addition to conventional multiple instance learning algorithms, a new MIL adaptation of the deep learning architecture, MIL U-net, is proposed and evaluated.

In the pixel-wise segmentation tasks the U-net architecture was the best overall classifier after the addition of 93 extra training patients to the original 20 training patients. A good inter-rater agreement was found for the haemorrhage class (ICC = 0.684) and the calcification class (ICC = 0.627). In the detection task the supervised methods, trained with one-sided noise, outperformed multiple instance classifiers such as MIL-Boost and the proposed MIL U-net. In this task both random forest and the linear logistic classifier obtained a fair Cohen's kappa (0.419 and 0.445 respectively) for detection of calcification per slice. The same classifiers obtained good correlation (Cohen's kappa 0.717 and 0.666 respectively) for haemorrhage detection per slice.