Due to the complex anatomy of the heart, heart valves and aorta, blood flow in the aorta is known to be complex and can exhibit a swirling, or helical, flow pattern. The purpose of this thesis is to implement methods to quantify and visualize both the speed of helicity, referred to as the helicity density, and the direction of helicity, which is measured by the localized normalized helicity. Furthermore, the relationship between helicity and geometrical aorta parameters were studied in young and old healthy volunteers. Helicity and geometrical parameters were quantified for 22 healthy volunteers (12 old, 10 young) that were examined using 4D Flow MRI. The relation between helicity and the geometry of the aorta was explored, and the results showed that the tortuosity and the diameter of the aorta are related to the helicity, but the jet angle and flow displacement do not appear to play an important role. This suggests that in healthy volunteers the helical flow is primarily affected by the geometry of the aorta, although further trials should be performed to fully characterize the effects of aortic geometry. The results also show that the helicity changes with age between the two age groups and some of the geometrical parameters also has a significant difference between the age groups.

A personalized cardiovascular lumped parameter model of the left-sided heart and thesystemic circulation has been developed by the cardiovascular medicine research groupat Linköping University. It provides information about hemodynamics, some of whichcould otherwise only have been retrieved by invasive measurements. The framework forpersonalizing the model is made using 4D Flow MRI data, containing volumes describinganatomy and velocities in three directions. Thus far, the inputs to this model have beengenerated manually for each subject. This is a slow and tedious process, unpractical touse clinically, and unfeasible for many subjects.This project aims to develop a tool to calculate the inputs and run the model for mul-tiple subjects in an automatic way. It has its basis in 4D Flow MRI data sets segmentedto identify the locations of left atrium (LA), left ventricle (LV), and aorta, along with thecorresponding structures on the right side.The process of making this tool started by calculation of the inputs. Planes were placedin the relevant positions, at the mitral valve, aortic valve (AV) and in the ascending aortaupstream the brachiocephalic branches, and flow rates were calculated through them. TheAV plane was used to calculate effective orifice area of AV and aortic cross-sectional area,while the LV end systolic and end diastolic volumes were extracted form the segmentation.The tool was evaluated by comparison with manually created inputs and outputs,using 9 healthy volunteers and one patient deemed to have normal left ventricular func-tion. The patient was chosen from a subject group diagnosed with chronic ischemic heartdisease, and/or a history of angina, together with fulfillment of the high risk score ofcardiovascular diseases of the European Society of Cardiology. This data was evaluatedusing coefficient of variation, Bland-Altman plots and sum squared error. The tool wasalso evaluated visually on some subjects with pathologies of interest.This project shows that it is possible to calculate inputs fully automatically fromsegmented 4D Flow MRI and run the cardiovascular avatar in an automatic way, withoutuser interaction. The method developed seems to be in good to moderate agreement withthose obtained manually, and could be the basis for further development of the model.

The purpose of this master thesis was to evaluate the estimation of pulse wave velocity (PWV) in the aorta using 4D flow MRI. PWV is the velocity of the pressure wave generated by the heart during systole and is a marker of arterial stiffness and a predictor of cardiovascular disease (CVD). PWV can in principle be estimated based on the time (travel-time) it takes for the pulse wave to travel a fixed distance (travel-distance), or based on the distance the pulse wave travels during a fixed time. In the commonly used time-to-travel-a-fixed-distance approach, planes are placed at two or more locations along the aorta. The travel-time is found by studying velocity waveforms at these pre-defined locations over time and thereby by estimating the time-difference for the pressure wave to reach each of these locations. In the distance-travelled-in-a-fixed-time approach, the pulse wave is located by studying at the velocity along the aorta at pre-defined instances in time. The travel-distance for the pulse wave between two instances in time is set as the difference in location of the pulse wave, where the location is identified as the location when the velocity has reached a predefined baseline. The specific aims of this thesis was to investigate the effect of using multiple locations as well as the effects of temporal and spatial resolution in the time-to-travel-a-fixed-distance approach, and to evaluate the possibility of using the distance-travelled-in-a-fixed-time approach. Additionally, the possibility of combining the two approaches was investigated. The study of using multiple locations revealed that more planes reduces the uncertainty of PWV estimation. Temporal resolution was found to have a major impact on PWV estimation, whereas spatial resolution had a more minor effect. A method for estimating PWV using 4D flow MRI using the distance-travelled-in-a-fixed-time approach was presented. Values obtained were compared favourably against previous findings and reference values, in the case of healthy young volunteers. The combination of the time-to-travel-a-fixed-distance and distance-travelled-in-a-fixed-time approaches appears feasible.

4D flow MRI is an imaging technique able to provide relevant information on patients’ cardiac health condition both from a visual and a quantitative point of view. Its applicability is however limited by uncertainty in the data due to the presence of noise. A new class of filters, called divergence free filters, was recently proposed. They incorporate physical knowledge into the filtering of 4D flow data. One way to implement divergence filters is via wavelet transform. The filtering process using the Divergence Free Wavelet Transform can be carried out in a completely automated fashion and was shown to hold promising results. The focus of this thesis was thus put towards assessing the effect produced by these filters on a large cohort of patients. Time-resolved segmentations were incorporated into the filtering process as this was thought to enhance divergence reduction. They were also used to investigate the filtering in every region of the thoracic cardiovascular system. The assessment of the filters was carried out both from a visual and a quantitative perspective. In-house tools were used to compute clinically used parameters on the data before and after the filtering to investigate the introduced change. The results showed that the used method was able to reduce divergence like noise while preserving all the relevant information contained in the original data, in all the regions of the heart. Flow quantifications were essentially unchanged by the filtering suggesting that the method can be safely applied on 4D flow data.

4D Flow Magnet Resonance Imaging (4D Flow MRI) is a novel non-invasive technique for imaging of cardiovascular blood flow. However, when utilized as a stand-alone analysis method, 4D Flow MRI has certain limitations including limited spatial resolution and noise artefacts, motivating the application of dedicated post-processing tools. Learning based super-resolution (SR) has here emerged as a promising utility for such work, however, more often than not, these efforts have been constricted to a narrowly defined cardiovascular domain. Rather, there has been limited exploration of how learned super-resolution models perform across \emph{multiple} cardiovascular compartments, with the wide range of hemodynamic compartments covered by the cardiovasculature as an apparent challenge. To address this, we investigate the generalizability of 4D Flow MRI super-resolution using ensemble learning. Our investigation employs ensemble learning techniques, specifically bagging and stacking, with a convolutional neural network (4DFlowNet) serving as the framework for all base learners. To assist in training, synthetic training data was extracted from patient-specific, physics-based velocity fields derived from computational fluid dynamic (CFD) simulations conducted in three key compartments: the aorta, brain and the heart. Varying base and ensemble networks were then trained on pairs of high-resolution and low-resolution synthetic data, with performance quantitatively assessed as a function of cardiovascular domain, and specific architecture. To ensure clinical relevance, we also evaluated model performance on clinically acquired MRI data from the very same three compartments.  We find that ensemble models improve performance, as compared to isolated equivalents. Our ensemble model \textit{Stacking Block-3}, improves in-silico error rate by $16.22$ points across the average domain. Additionally, performance on the aorta, brain and heart improves by $2.66$, $5.81$ and $2.00$ points respectively. Employing both qualitative and quantitative evaluation methods on the in-vivo data, we find that ensemble models produce super-resolved velocity fields that are quantitatively coherent with ground truth reference data and visually pleasing. To conclude, ensemble learning has shown potential in generalizing 4D Flow MRI across multiple cardiovascular compartments.

Deep convolutional neural networks (CNN’s) have achieved state-of-the-art accuraciesfor multi-class segmentation in biomedical image science. In this thesis, A 3D U-Net isused to segment 4D flow Magnetic Resonance Images that include the heart and its largevessels. The 4 dimensional flow MRI dataset has been segmented and validated using amulti-atlas based registration technique. This multi-atlas based technique resulted in highquality segmentations, with the disadvantage of long computation times typically requiredby three-dimensional registration techniques. The 3D U-Net framework learns to classifyvoxels by transforming the information about the segmentation into a latent feature spacein a contracting path and upsampling them to semantic segmentation in an expandingpath. A CNN trained using a sufficiently diverse set of volumes at different time intervalsof the diastole and systole should be able to handle more extreme morphological differencesbetween subjects. Evaluation of the results is based on metric for segmentation evaluationsuch as Dice coefficient. Uncertainty is estimated using a bayesian implementationof the 3D U-Net of similar architecture. / <p>The presentation was online over zoom due to covid19 restrictions.</p>

The accurate assessment of hemodynamics and its parameters play an important role when diagnosing cardiovascular diseases. In this context, 4D Flow Magnetic Resonance Imaging (4D Flow MRI) is a non-invasive measurement technique that facilitates hemodynamic parameter assessment as well as quantitative and qualitative analysis of three-directional flow over time. However, the assessment is limited by noise, low spatio-temporal resolution and long acquisition times. Consequently, in regions characterized by transient, rapid flow dynamics, such as the aorta and heart, capturing these rapid transient flows remains particularly challenging. Recent research has shown the feasibility of machine learning models to effectively denoise and increase the spatio-temporal resolution of 4D Flow MRI. However, temporal super-resolution networks, which can generalize on unseen domains and are independent on boundary segmentations, remain unexplored.  This study aims to investigate the feasibility of a neural network for temporal super-resolution and denoising of 4D Flow MRI data. To achieve this, we propose a residual convolutional neural network (based on the 4DFlowNet from Ferdian et al.) providing an end-to-end mapping from temporal low resolution space to high resolution space. The network is trained on patient-specific cardiac models created with computational-fluid dynamic (CFD) simulations covering a full cardiac cycle. For clinical contextualization, performance is assessed on clinical patient data. The study shows the potential of the 4DFlowNet for temporal-super resolution with an average relative error of 16.6 % on an unseen cardiac domain, outperforming deterministic methods such as linear and cubic interpolation. We find that the network effectively reduces noise and recovers high-transient flow by a factor of 2 on both in-silico and in-vivo cardiac datasets. The prediction results in a temporal resolution of 20 ms, going beyond the general clinical routine of 30-40 ms. This study exemplifies the performance of a residual CNN for temporal super-resolution of 4D flow MRI data, providing an option to extend evaluations to aortic geometries and to further develop different upsampling factors and temporal resolutions. / En noggrann bedömning av hemodynamiken och dess parametrar spelar en viktig roll vid diagnos av kardiovaskulära sjukdomar. I detta sammanhang är 4D Flow Magnetic Resonance Imaging (4D Flow MRI) en icke-invasiv mätteknik som underlättar bedömning av hemodynamiska parametrar samt kvantitativ och kvalitativ analys av flöde. Bedömningen begränsas av brus, låg spatio-temporal upplösning och långa insamlingstider. I områden som karakteriseras av snabb flödesdynamik, såsom aorta och hjärta, är det därför fortfarande särskilt svårt att fånga dessa snabba transienta flöden. Ny forskning har visat att det är möjligt att använda maskininlärningsmodeller för att effektivt reducera brus och öka den spatio-temporala upplösningen i 4D Flow MRI. Nätverk för temporal superupplösning, som kan generaliseras till osedda domäner och är oberoende av segmentering, är fortfarande outforskade.  Denna studie syftar till att undersöka genomförbarheten av ett neuralt nätverk för temporal superupplösning och brusreducering av 4D Flow MRI-data. För att uppnå detta föreslår vi ett residual faltningsneuralt nätverk (baserat på 4DFlowNet från Ferdian et al.) som tillhandahåller en end-to-end-mappning från temporalt lågupplöst utrymme till högupplöst utrymme. Nätverket tränas på patientspecifika hjärtmodeller som skapats med CFD-simuleringar som spänner över en hel hjärtcykel. För klinisk kontextualisering utvärderas nätverkets prestanda på kliniska patientdata. Studien visar potentialen av 4DFlowNet för temporal superupplösning med ett genomsnittligt relativt fel på 16,6 % på en osedd hjärtdomän, vilket överträffar deterministiska metoder som linjär och kubisk interpolation. Vi konstaterar att nätverket effektivt minskar brus och återställer högtransient flöde med en faktor på 2 på både in-silico ochin-vivo hjärtdataset. Förutsägelsen resulterar i en temporal upplösning på 20 ms, vilket är mer än den allmänna kliniska rutinen på 30-40 ms. Denna studie exemplifierar prestandan hos en residual CNN för temporal superupplösning av 4D-flödes-MRI-data, vilket ger möjlighet att utvidga utvärderingarna till aortageometrier och att vidareutveckla olika uppsamplingsfaktorer och temporala upplösningar.

Magnetic resonance imaging (MRI), is a noninvasive medical imaging testing techniquewhich is used to produce detailed images of internal structure of the human body, includingbones, muscles, organs, and blood vessels. MRI scanners use large magnets and radiowaves to create images of the body. Cardiac MRI scan helps doctors to detect and monitorcardiac diseases like blood clots, artery blockages, and scar tissue etc. Cardiovasculardisease is a type of disease that affects the heart or the blood vessels.This thesis aims to explore the reconstruction of accelerated cardiovascular MRI datato reconstruct under-sampled MRI data acquired after applying accelerated techniques.The focus of this research is to study and implement deep learning techniques to overcomethe aliasing artifacts caused by accelerated imaging. The results of this study will becompared with fully sampled data acquired with traditional existing techniques such asParallel Imaging (PI) and Compressed Sensing (CS).The primary findings of this study show that the proposed deep learning network caneffectively reconstruct under-sampled cardiovascular MRI data acquired using acceleratedimaging techniques. Many experiments were performed to handle 4D Flow data with limitedmemory for training the network. The network’s performance was found to be comparableto the fully sampled data acquired using traditional imaging techniques such asPI and CS. It is also important to note that this study also aimed to investigate the generalizabilityof the proposed deep learning network, specifically FlowVN, when appliedto different datasets. To explore this aspect, two different models were employed: a pretrainedmodel using previous research data and configurations, and a model trained fromscratch using CMIV data with experiments performed to address limited memory issuesassociated with 4D Flow data.