Umeå University's logo

Blood-brain barrier (BBB) disruption may contribute to cognitive decline, but questions remain whether this association is more pronounced for certain brain regions, such as the hippocampus, or represents a whole-brain mechanism. Further, whether human BBB leakage is triggered by excessive vascular pulsatility, as suggested by animal studies, remains unknown. In a prospective cohort (N = 50; 68-84 years), we used contrast-enhanced MRI to estimate the permeability-surface area product (PS) and fractional plasma volume ( formula presented ), and 4D flow MRI to assess cerebral arterial pulsatility. Cognition was assessed by the Montreal Cognitive Assessment (MoCA) score. We hypothesized that high PS would be associated with high arterial pulsatility, and that links to cognition would be specific to hippocampal PS. For 15 brain regions, PS ranged from 0.38 to 0.85 (·10-3 min-1) and formula presented from 0.79 to 1.78%. Cognition was related to PS (·10-3 min-1) in hippocampus (β = - 2.9; p = 0.006), basal ganglia (β = - 2.3; p = 0.04), white matter (β = - 2.6; p = 0.04), whole-brain (β = - 2.7; p = 0.04) and borderline-related for cortex (β = - 2.7; p = 0.076). Pulsatility was unrelated to PS for all regions (p > 0.19). Our findings suggest PS-cognition links mainly reflect a whole-brain phenomenon with only slightly more pronounced links for the hippocampus, and provide no evidence of excessive pulsatility as a trigger of BBB disruption.

White matter hyperintensities (WMH), perivascular spaces (PVS) and lacunes are common MRI features of small vessel disease (SVD). However, no shared underlying pathological mechanism has been identified. We investigated whether SVD burden, in terms of WMH, PVS and lacune status, was related to changes in the cerebral arterial wall by applying global cerebral pulse wave velocity (gcPWV) measurements, a newly described marker of cerebral vascular stiffness. In a population-based cohort of 190 individuals, 66–85 years old, SVD features were estimated from T1-weighted and FLAIR images while gcPWV was estimated from 4D flow MRI data. Additionally, the gcPWV’s stability to variations in field-of-view was analyzed. The gcPWV was 10.82 (3.94) m/s and displayed a significant correlation to WMH and white matter PVS volume (r = 0.29, p < 0.001; r = 0.21, p = 0.004 respectively from nonparametric tests) that persisted after adjusting for age, blood pressure variables, body mass index, ApoB/A1 ratio, smoking as well as cerebral pulsatility index, a previously suggested early marker of SVD. The gcPWV displayed satisfactory stability to field-of-view variations. Our results suggest that SVD is accompanied by changes in the cerebral arterial wall that can be captured by considering the velocity of the pulse wave transmission through the cerebral arterial network.

The use of synthetic CT (sCT) in the radiotherapy workflow would reduce costs and scan time while removing the uncertainties around working with both MR and CT modalities. The performance of deep learning (DL) solutions for sCT generation is steadily increasing, however most proposed methods were trained and validated on private datasets of a single contrast from a single scanner. Such solutions might not perform equally well on other datasets, limiting their general usability and therefore value. Additionally, functional evaluations of sCTs such as dosimetric comparisons with CT-based dose calculations better show the impact of the methods, but the evaluations are more labor intensive than pixel-wise metrics.

To improve the generalization of an sCT model, we propose to incorporate a pre-trained DL model to pre-process the input MR images by generating artificial proton density, T1 and T2 maps (i.e. contrast-independent quantitative maps), which are then used for sCT generation. Using a dataset of only T2w MR images, the robustness towards input MR contrasts of this approach is compared to a model that was trained using the MR images directly. We evaluate the generated sCTs using pixel-wise metrics and calculating mean radiological depths, as an approximation of the mean delivered dose. On T2w images acquired with the same settings as the training dataset, there was no significant difference between the performance of the models. However, when evaluated on T1w images, and a wide range of other contrasts and scanners from both public and private datasets, our approach outperforms the baseline model. Using a dataset of T2w MR images, our proposed model implements synthetic quantitative maps to generate sCT images, improving the generalization towards other contrasts. Our code and trained models are publicly available.

Purpose: To mitigate the problem of noisy parameter maps with high uncertainties by casting parameter mapping as a denoising task based on Deep Image Priors.

Methods: We extend the concept of denoising with Deep Image Prior (DIP) into parameter mapping by treating the output of an image-generating network as a parametrization of tissue parameter maps. The method implicitly denoises the parameter mapping process by filtering low-level image features with an untrained convolutional neural network (CNN). Our implementation includes uncertainty estimation from Bernoulli approximate variational inference, implemented with MC dropout, which provides model uncertainty in each voxel of the denoised parameter maps. The method is modular, so the specifics of different applications (e.g., T1 mapping) separate into application-specific signal equation blocks. We evaluate the method on variable flip angle T1 mapping, multi-echo T2 mapping, and apparent diffusion coefficient mapping.

Results: We found that deep image prior adapts successfully to several applications in parameter mapping. In all evaluations, the method produces noise-reduced parameter maps with decreased uncertainty compared to conventional methods. The downsides of the proposed method are the long computational time and the introduction of some bias from the denoising prior.

Conclusion: DIP successfully denoise the parameter mapping process and applies to several applications with limited hyperparameter tuning. Further, it is easy to implement since DIP methods do not use network training data. Although time-consuming, uncertainty information from MC dropout makes the method more robust and provides useful information when properly calibrated.

PURPOSE: During the acquisition of MRI data, patient-, sequence-, or hardware-related factors can introduce artefacts that degrade image quality. Four of the most significant tasks for improving MRI image quality have been bias field correction, super-resolution, motion-, and noise correction. Machine learning has achieved outstanding results in improving MR image quality for these tasks individually, yet multi-task methods are rarely explored.

METHODS: In this study, we developed a model to simultaneously correct for all four aforementioned artefacts using multi-task learning. Two different datasets were collected, one consisting of brain scans while the other pelvic scans, which were used to train separate models, implementing their corresponding artefact augmentations. Additionally, we explored a novel loss function that does not only aim to reconstruct the individual pixel values, but also the image gradients, to produce sharper, more realistic results. The difference between the evaluated methods was tested for significance using a Friedman test of equivalence followed by a Nemenyi post-hoc test.

RESULTS: Our proposed model generally outperformed other commonly-used correction methods for individual artefacts, consistently achieving equal or superior results in at least one of the evaluation metrics. For images with multiple simultaneous artefacts, we show that the performance of using a combination of models, trained to correct individual artefacts depends heavily on the order that they were applied. This is not an issue for our proposed multi-task model. The model trained using our novel convolutional loss function always outperformed the model trained with a mean squared error loss, when evaluated using Visual Information Fidelity, a quality metric connected to perceptual quality.

CONCLUSION: We trained two models for multi-task MRI artefact correction of brain, and pelvic scans. We used a novel loss function that significantly improves the image quality of the outputs over using mean squared error. The approach performs well on real world data, and it provides insight into which artefacts it detects and corrects for. Our proposed model and source code were made publicly available.

Concomitant fields are the unwanted transverse components that arise when spatial encoding gradients are applied in MRI. We measured the changing gradient magnetic field at multiple locations inside the scanner and examined the internal distribution and linearity of the three vector components of the field. Our results illustrate some not-so-obvious spatial characteristics of the gradient field, which can seem unintuitive at first glance, but are quite reasonable when considering electromagnetic theory and MRI-scanner physics constraints.

Concerns about the reproducibility of deep learning research are more prominent than ever, with no clear solution in sight. The Medical Imaging with Deep Learning (MIDL) conference has made advancements in employing empirical rigor with regards to reproducibility by advocating open access, and recently also recommending authors to make their code public—both aspects being adopted by the majority of the conference submissions. We have evaluated all accepted full paper submissions to MIDL between 2018 and 2022 using established, but adjusted guidelines addressing the reproducibility and quality of the public repositories. The evaluations show that publishing repositories and using public datasets are becoming more popular, which helps traceability, but the quality of the repositories shows room for improvement in every aspect. Merely 22% of all submissions contain a repository that was deemed repeatable using our evaluations. From the commonly encountered issues during the evaluations, we propose a set of guidelines for machine learning-related research for medical imaging applications, adjusted specifically for future submissions to MIDL. We presented our results to future MIDL authors who were eager to continue an open discussion on the topic of code reproducibility.

In magnetic resonance imaging (MRI), bias fields are difficult to correct since they are inherently unknown. They cause intra-volume intensity inhomogeneities which limit the performance of subsequent automatic medical imaging tasks, \eg, tissue-based segmentation. Since the ground truth is unavailable, training a supervised machine learning solution requires approximating the bias fields, which limits the resulting method. We introduce implicit training which sidesteps the inherent lack of data and allows the training of machine learning solutions without ground truth. We describe how training a model implicitly for bias field correction allows using non-medical data for training, achieving a highly generalized model. The implicit approach was compared to a more traditional training based on medical data. Both models were compared to an optimized N4ITK method, with evaluations on six datasets. The implicitly trained model improved the homogeneity of all encountered medical data, and it generalized better for a range of anatomies, than the model trained traditionally. The model achieves a significant speed-up over an optimized N4ITK method—by a factor of 100, and after training, it also requires no parameters to tune. For tasks such as bias field correction - where ground truth is generally not available, but the characteristics of the corruption are known - implicit training promises to be a fruitful alternative for highly generalized solutions.

Intracranial arterial stiffening is a potential early marker of emerging cerebrovascular dysfunction and could be mechanistically involved in disease processes detrimental to brain function via several pathways. A prominent consequence of arterial wall stiffening is the increased velocity at which the systolic pressure pulse wave propagates through the vasculature. Previous non-invasive measurements of the pulse wave propagation have been performed on the aorta or extracranial arteries with results linking increased pulse wave velocity to brain pathology. However, there is a lack of intracranial “target-organ” measurements. Here we present a 4D flow MRI method to estimate pulse wave velocity in the intracranial vascular tree. The method utilizes the full detectable branching structure of the cerebral vascular tree in an optimization framework that exploits small temporal shifts that exists between waveforms sampled at varying depths in the vasculature. The method is shown to be stable in an internal consistency test, and of sufficient sensitivity to robustly detect age-related increases in intracranial pulse wave velocity.

 The contrast settings to select before acquiring magnetic resonance imaging (MRI) signal depend heavily on the subsequent tasks. As each contrast highlights different tissues, automated segmentation tools for example might be optimized for a certain contrast. While for radiotherapy, multiple scans of the same region with different contrasts can achieve a better accuracy for delineating tumours and organs at risk. Unfortunately, the optimal contrast for the subsequent automated methods might not be known during the time of signal acquisition, and performing multiple scans with different contrasts increases the total examination time and registering the sequences introduces extra work and potential errors. Building on the recent achievements of deep learning in medical applications, the presented work describes a novel approach for transferring any contrast to any other. The novel model architecture incorporates the signal equation for spin echo sequences, and hence the model inherently learns the unknown quantitative maps for proton density, 𝑇1 and 𝑇2 relaxation times (𝑃𝐷, 𝑇1 and 𝑇2, respectively). This grants the model the ability to retrospectively reconstruct spin echo sequences by changing the contrast settings Echo and Repetition Time (𝑇𝐸 and 𝑇𝑅, respectively). The model learns to identify the contrast of pelvic MR images, therefore no paired data of the same anatomy from different contrasts is required for training. This means that the experiments are easily reproducible with other contrasts or other patient anatomies. Despite the contrast of the input image, the model achieves accurate results for reconstructing signal with contrasts available for evaluation. For the same anatomy, the quantitative maps are consistent for a range of contrasts of input images. Realized in practice, the proposed method would greatly simplify the modern radiotherapy pipeline. The trained model is made public together with a tool for testing the model on example images.