3D regression neural network for the quantification of enlarged perivascular spaces in brain MRI

A Survey on Explainable Artificial Intelligence (XAI) Techniques for Visualizing Deep Learning Models in Medical Imaging

The combination of medical imaging and deep learning has significantly improved diagnostic and prognostic capabilities in the healthcare domain. Nevertheless, the inherent complexity of deep learning models poses challenges in understanding their decision-making processes. Interpretability and visualization techniques have emerged as crucial tools to unravel the black-box nature of these models, providing insights into their inner workings and enhancing trust in their predictions. This survey paper comprehensively examines various interpretation and visualization techniques applied to deep learning models in medical imaging. The paper reviews methodologies, discusses their applications, and evaluates their effectiveness in enhancing the interpretability, reliability, and clinical relevance of deep learning models in medical image analysis.

Systematic review and meta-analysis of automated methods for quantifying enlarged perivascular spaces in the brain

Research into magnetic resonance imaging (MRI)-visible perivascular spaces (PVS) has recently increased, as results from studies in different diseases and populations are cementing their association with sleep, disease phenotypes, and overall health indicators. With the establishment of worldwide consortia and the availability of large databases, computational methods that allow to automatically process all this wealth of information are becoming increasingly relevant. Several computational approaches have been proposed to assess PVS from MRI, and efforts have been made to summarise and appraise the most widely applied ones. We systematically reviewed and meta-analysed all publications available up to September 2023 describing the development, improvement, or application of computational PVS quantification methods from MRI. We analysed 67 approaches and 60 applications of their implementation, from 112 publications. The two most widely applied were the use of a morphological filter to enhance PVS-like structures, with Frangi being the choice preferred by most, and the use of a U-Net configuration with or without residual connections. Older adults or population studies comprising adults from 18 years old onwards were, overall, more frequent than studies using clinical samples. PVS were mainly assessed from T2-weighted MRI acquired in 1.5T and/or 3T scanners, although combinations using it with T1-weighted and FLAIR images were also abundant. Common associations researched included age, sex, hypertension, diabetes, white matter hyperintensities, sleep and cognition, with occupation-related, ethnicity, and genetic/hereditable traits being also explored. Despite promising improvements to overcome barriers such as noise and differentiation from other confounds, a need for joined efforts for a wider testing and increasing availability of the most promising methods is now paramount.

Diffusion Tensor Image Analysis ALong the Perivascular Space (DTI-ALPS): Revisiting the Meaning and Significance of the Method

More than 5 years have passed since the Diffusion Tensor Image Analysis ALong the Perivascular Space (DTI-ALPS) method was proposed with the intention of evaluating the glymphatic system. This method is handy due to its noninvasiveness, provision of a simple index in a straightforward formula, and the possibility of retrospective analysis. Therefore, the ALPS method was adopted to evaluate the glymphatic system for many disorders in many studies. The purpose of this review is to look back and discuss the ALPS method at this moment.The ALPS-index was found to be an indicator of a number of conditions related to the glymphatic system. Thus, although this was expected in the original report, the results of the ALPS method are often interpreted as uniquely corresponding to the function of the glymphatic system. However, a number of subsequent studies have pointed out the problems on the data interpretation. As they rightly point out, a higher ALPS-index indicates predominant Brownian motion of water molecules in the radial direction at the lateral ventricular body level, no more and no less. Fortunately, the term "ALPS-index" has become common and is now known as a common term by many researchers. Therefore, the ALPS-index should simply be expressed as high or low, and whether it reflects a glymphatic system is better to be discussed carefully. In other words, when a decreased ALPS-index is observed, it should be expressed as "decreased ALPS-index" and not directly as "glymphatic dysfunction". Recently, various methods have been proposed to evaluate the glymphatic system. It has become clear that these methods also do not seem to reflect the entirety of the extremely complex glymphatic system. This means that it would be desirable to use various methods in combination to evaluate the glymphatic system in a comprehensive manner.

Noninvasive Magnetic Resonance Imaging Measures of Glymphatic System Activity

The comprehension of the glymphatic system, a postulated mechanism responsible for the removal of interstitial solutes within the central nervous system (CNS), has witnessed substantial progress recently. While direct measurement techniques involving fluorescence and contrast agent tracers have demonstrated success in animal studies, their application in humans is invasive and presents challenges. Hence, exploring alternative noninvasive approaches that enable glymphatic research in humans is imperative. This review primarily focuses on several noninvasive magnetic resonance imaging (MRI) techniques, encompassing perivascular space (PVS) imaging, diffusion tensor image analysis along the PVS, arterial spin labeling, chemical exchange saturation transfer, and intravoxel incoherent motion. These methodologies provide valuable insights into the dynamics of interstitial fluid, water permeability across the blood-brain barrier, and cerebrospinal fluid flow within the cerebral parenchyma. Furthermore, the review elucidates the underlying concept and clinical applications of these noninvasive MRI techniques, highlighting their strengths and limitations. It addresses concerns about the relationship between glymphatic system activity and pathological alterations, emphasizing the necessity for further studies to establish correlations between noninvasive MRI measurements and pathological findings. Additionally, the challenges associated with conducting multisite studies, such as variability in MRI systems and acquisition parameters, are addressed, with a suggestion for the use of harmonization methods, such as the combined association test (COMBAT), to enhance standardization and statistical power. Current research gaps and future directions in noninvasive MRI techniques for assessing the glymphatic system are discussed, emphasizing the need for larger sample sizes, harmonization studies, and combined approaches. In conclusion, this review provides invaluable insights into the application of noninvasive MRI methods for monitoring glymphatic system activity in the CNS. It highlights their potential in advancing our understanding of the glymphatic system, facilitating clinical applications, and paving the way for future research endeavors in this field. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 5.

The glymphatic system in migraine and other headaches

Glymphatic system is an emerging pathway of removing metabolic waste products and toxic solutes from the brain tissue. It is made of a network of perivascular spaces, filled in cerebrospinal and interstitial fluid, encompassing penetrating and pial vessels and communicating with the subarachnoid space. It is separated from vessels by the blood brain barrier and from brain tissue by the endfeet of the astrocytes rich in aquaporin 4, a membrane protein which controls the water flow along the perivascular space. Animal models and magnetic resonance (MR) studies allowed to characterize the glymphatic system function and determine how its impairment could lead to numerous neurological disorders (e.g. Alzheimer's disease, stroke, sleep disturbances, migraine, idiopathic normal pressure hydrocephalus). This review aims to summarize the role of the glymphatic system in the pathophysiology of migraine in order to provide new ways of approaching to this disease and to its therapy.

The Rotterdam Study. Design update and major findings between 2020 and 2024

The Rotterdam Study is a population-based cohort study, started in 1990 in the district of Ommoord in the city of Rotterdam, the Netherlands, with the aim to describe the prevalence and incidence, unravel the etiology, and identify targets for prediction, prevention or intervention of multifactorial diseases in mid-life and elderly. The study currently includes 17,931 participants (overall response rate 65%), aged 40 years and over, who are examined in-person every 3 to 5 years in a dedicated research facility, and who are followed-up continuously through automated linkage with health care providers, both regionally and nationally. Research within the Rotterdam Study is carried out along two axes. First, research lines are oriented around diseases and clinical conditions, which are reflective of medical specializations. Second, cross-cutting research lines transverse these clinical demarcations allowing for inter- and multidisciplinary research. These research lines generally reflect subdomains within epidemiology. This paper describes recent methodological updates and main findings from each of these research lines. Also, future perspective for coming years highlighted.

Overview of the Current Knowledge and Conventional MRI Characteristics of Peri- and Para-Vascular Spaces

Brain spaces around (perivascular spaces) and alongside (paravascular or Virchow-Robin spaces) vessels have gained significant attention in recent years due to the advancements of in vivo imaging tools and to their crucial role in maintaining brain health, contributing to the anatomic foundation of the glymphatic system. In fact, it is widely accepted that peri- and para-vascular spaces function as waste clearance pathways for the brain for materials such as ß-amyloid by allowing exchange between cerebrospinal fluid and interstitial fluid. Visible brain spaces on magnetic resonance imaging are often a normal finding, but they have also been associated with a wide range of neurological and systemic conditions, suggesting their potential as early indicators of intracranial pressure and neurofluid imbalance. Nonetheless, several aspects of these spaces are still controversial. This article offers an overview of the current knowledge and magnetic resonance imaging characteristics of peri- and para-vascular spaces, which can help in daily clinical practice image description and interpretation. This paper is organized into different sections, including the microscopic anatomy of peri- and para-vascular spaces, their associations with pathological and physiological events, and their differential diagnosis.

Clearance dysfunction of trans-barrier transport and lymphatic drainage in cerebral small vessel disease: Review and prospect

Cerebral small vessel disease (CSVD) causes 20%-25% of stroke and contributes to 45% of dementia cases worldwide. However, since its early symptoms are inconclusive in addition to the complexity of the pathological basis, there is a rather limited effective therapies and interventions. Recently, accumulating evidence suggested that various brain-waste-clearance dysfunctions are closely related to the pathogenesis and prognosis of CSVD, and after a comprehensive and systematic review we classified them into two broad categories: trans-barrier transport and lymphatic drainage. The former includes blood brain barrier and blood-cerebrospinal fluid barrier, and the latter, glymphatic-meningeal lymphatic system and intramural periarterial drainage pathway. We summarized the concepts and potential mechanisms of these clearance systems, proposing a relatively complete framework for elucidating their interactions with CSVD. In addition, we also discussed recent advances in therapeutic strategies targeting clearance dysfunction, which may be an important area for future CSVD research.

Correlation between enlarged perivascular space and brain white matter hyperintensities in patients with recent small subcortical infarct

BACKGROUND

This study aimed to investigate the correlation between enlarged perivascular space (EPVS) and white matter hyperintensities (WMH) at different locations in patients with recent small subcortical infarct (RSSI).

METHODS

Data were collected from patients with RSSI who were hospitalized at Changzhou Second People's Hospital between October 2020 and December 2021. All patients underwent cranial magnetic resonance imaging, and the grades of EPVS and WMH were assessed, including basal ganglia EPVS (BG-EPVS), centrum semiovale EPVS (CSO-EPVS), deep WMH (DWMH), and periventricular WMH (PWMH). The volumes of EPVS and WMH at different locations were quantified using 3D Slicer software. Patients were grouped according to the severity of BG-EPVS and CSO-EPVS. Univariate and multivariate analyses were used to analyze the relationship between EPVS and WMH.

RESULTS

A total of 215 patients with RSSI were included in the analysis. Patients with moderate-to-severe BG-EPVS had higher DWMH and PWMH severity than those with mild BG-EPVS, both in terms of volume and grade. There was no significant difference in WMH severity between patients with mild CSO-EPVS and those with moderate-to-severe CSO-EPVS. Multivariate analysis indicated that after adjustments were made for confounding factors, DWMH volume (β = 0.311; 95% CI, 0.089-0.400; p = .002) and PWMH volume (β = 0.296; 95% CI, 0.083-0.424; p = .004) were independently associated with BG-EPVS. Pearson correlation showed that PWMH volume (r = .589; p < .001) and DWMH volume (r = .596; p < .001) were positively related to BG-EPVS volume.

CONCLUSION

DWMH and PWMH are closely related to BG-EPVS in patients with RSSI.

Recent Advances in Explainable Artificial Intelligence for Magnetic Resonance Imaging

Advances in artificial intelligence (AI), especially deep learning (DL), have facilitated magnetic resonance imaging (MRI) data analysis, enabling AI-assisted medical image diagnoses and prognoses. However, most of the DL models are considered as "black boxes". There is an unmet need to demystify DL models so domain experts can trust these high-performance DL models. This has resulted in a sub-domain of AI research called explainable artificial intelligence (XAI). In the last decade, many experts have dedicated their efforts to developing novel XAI methods that are competent at visualizing and explaining the logic behind data-driven DL models. However, XAI techniques are still in their infancy for medical MRI image analysis. This study aims to outline the XAI applications that are able to interpret DL models for MRI data analysis. We first introduce several common MRI data modalities. Then, a brief history of DL models is discussed. Next, we highlight XAI frameworks and elaborate on the principles of multiple popular XAI methods. Moreover, studies on XAI applications in MRI image analysis are reviewed across the tissues/organs of the human body. A quantitative analysis is conducted to reveal the insights of MRI researchers on these XAI techniques. Finally, evaluations of XAI methods are discussed. This survey presents recent advances in the XAI domain for explaining the DL models that have been utilized in MRI applications.

Assessment of Risk Factors and Clinical Importance of Enlarged Perivascular Spaces by Whole-Brain Investigation in the Multi-Ethnic Study of Atherosclerosis

Importance

Enlarged perivascular spaces (ePVSs) have been associated with cerebral small-vessel disease (cSVD). Although their etiology may differ based on brain location, study of ePVSs has been limited to specific brain regions; therefore, their risk factors and significance remain uncertain.

Objective

Toperform a whole-brain investigation of ePVSs in a large community-based cohort.

Design, Setting, and Participants

This cross-sectional study analyzed data from the Atrial Fibrillation substudy of the population-based Multi-Ethnic Study of Atherosclerosis. Demographic, vascular risk, and cardiovascular disease data were collected from September 2016 to May 2018. Brain magnetic resonance imaging was performed from March 2018 to July 2019. The reported analysis was conducted between August and October 2022. A total of 1026 participants with available brain magnetic resonance imaging data and complete information on demographic characteristics and vascular risk factors were included.

Main Outcomes and Measures

Enlarged perivascular spaces were quantified using a fully automated deep learning algorithm. Quantified ePVS volumes were grouped into 6 anatomic locations: basal ganglia, thalamus, brainstem, frontoparietal, insular, and temporal regions, and were normalized for the respective regional volumes. The association of normalized regional ePVS volumes with demographic characteristics, vascular risk factors, neuroimaging indices, and prevalent cardiovascular disease was explored using generalized linear models.

Results

In the 1026 participants, mean (SD) age was 72 (8) years; 541 (53%) of the participants were women. Basal ganglia ePVS volume was positively associated with age (β = 3.59 × 10-3; 95% CI, 2.80 × 10-3 to 4.39 × 10-3), systolic blood pressure (β = 8.35 × 10-4; 95% CI, 5.19 × 10-4 to 1.15 × 10-3), use of antihypertensives (β = 3.29 × 10-2; 95% CI, 1.92 × 10-2 to 4.67 × 10-2), and negatively associated with Black race (β = -3.34 × 10-2; 95% CI, -5.08 × 10-2 to -1.59 × 10-2). Thalamic ePVS volume was positively associated with age (β = 5.57 × 10-4; 95% CI, 2.19 × 10-4 to 8.95 × 10-4) and use of antihypertensives (β = 1.19 × 10-2; 95% CI, 6.02 × 10-3 to 1.77 × 10-2). Insular region ePVS volume was positively associated with age (β = 1.18 × 10-3; 95% CI, 7.98 × 10-4 to 1.55 × 10-3). Brainstem ePVS volume was smaller in Black than in White participants (β = -5.34 × 10-3; 95% CI, -8.26 × 10-3 to -2.41 × 10-3). Frontoparietal ePVS volume was positively associated with systolic blood pressure (β = 1.14 × 10-4; 95% CI, 3.38 × 10-5 to 1.95 × 10-4) and negatively associated with age (β = -3.38 × 10-4; 95% CI, -5.40 × 10-4 to -1.36 × 10-4). Temporal region ePVS volume was negatively associated with age (β = -1.61 × 10-2; 95% CI, -2.14 × 10-2 to -1.09 × 10-2), as well as Chinese American (β = -2.35 × 10-1; 95% CI, -3.83 × 10-1 to -8.74 × 10-2) and Hispanic ethnicities (β = -1.73 × 10-1; 95% CI, -2.96 × 10-1 to -4.99 × 10-2).

Conclusions and Relevance

In this cross-sectional study of ePVSs in the whole brain, increased ePVS burden in the basal ganglia and thalamus was a surrogate marker for underlying cSVD, highlighting the clinical importance of ePVSs in these locations.

Automated Methods for Detecting and Quantitation of Enlarged Perivascular spaces on MRI

The brain's glymphatic system is a network of intracerebral vessels that function to remove "waste products" such as degraded proteins from the brain. It comprises of the vasculature, perivascular spaces (PVS), and astrocytes. Poor glymphatic function has been implicated in numerous diseases; however, its contribution is still unknown. Efforts have been made to image the glymphatic system to further assess its role in the pathogenesis of different diseases. Numerous imaging modalities have been utilized including two-photon microscopy and contrast-enhanced magnetic resonance imaging (MRI). However, these are associated with limitations for clinical use. PVS form a part of the glymphatic system and can be visualized on standard MRI sequences when enlarged. It is thought that PVS become enlarged secondary to poor glymphatic drainage of metabolites. Thus, quantitating PVS could be a good surrogate marker for glymphatic function. Numerous manual rating scales have been developed to measure the PVS number and size on MRI scans; however, these are associated with many limitations. Instead, automated methods have been created to measure PVS more accurately in different diseases. In this review, we discuss the imaging techniques currently available to visualize the glymphatic system as well as the automated methods currently available to measure PVS, and the strengths and limitations associated with each technique. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 1.

A critical guide to the automated quantification of perivascular spaces in magnetic resonance imaging

The glymphatic system is responsible for waste clearance in the brain. It is comprised of perivascular spaces (PVS) that surround penetrating blood vessels. These spaces are filled with cerebrospinal fluid and interstitial fluid, and can be seen with magnetic resonance imaging. Various algorithms have been developed to automatically label these spaces in MRI. This has enabled volumetric and morphological analyses of PVS in healthy and disease cohorts. However, there remain inconsistencies between PVS measures reported by different methods of automated segmentation. The present review emphasizes that importance of voxel-wise evaluation of model performance, mainly with the Sørensen Dice similarity coefficient. Conventional count correlations for model validation are inadequate if the goal is to assess volumetric or morphological measures of PVS. The downside of voxel-wise evaluation is that it requires manual segmentations that require large amounts of time to produce. One possible solution is to derive these semi-automatically. Additionally, recommendations are made to facilitate rigorous development and validation of automated PVS segmentation models. In the application of automated PVS segmentation tools, publication of image quality metrics, such as the contrast-to-noise ratio, alongside descriptive statistics of PVS volumes and counts will facilitate comparability between studies. Lastly, a head-to-head comparison between two algorithms, applied to two cohorts of astronauts reveals how results can differ substantially between techniques.

Assessment of perivascular space filtering methods using a three-dimensional computational model

Growing interest surrounds the assessment of perivascular spaces (PVS) on magnetic resonance imaging (MRI) and their validation as a clinical biomarker of adverse brain health. Nonetheless, the limits of validity of current state-of-the-art segmentation methods are still unclear. Here, we propose an open-source three-dimensional computational framework comprising 3D digital reference objects and evaluate the performance of three PVS filtering methods under various spatiotemporal imaging considerations (including sampling, motion artefacts, and Rician noise). Specifically, we study the performance of the Frangi, Jerman and RORPO filters in enhancing PVS-like structures to facilitate segmentation. Our findings were three-fold. First, as long as voxels are isotropic, RORPO outperforms the other two filters, regardless of imaging quality. Unlike the Frangi and Jerman filters, RORPO's performance does not deteriorate as PVS volume increases. Second, the performance of all "vesselness" filters is heavily influenced by imaging quality, with sampling and motion artefacts being the most damaging for these types of analyses. Third, none of the filters can distinguish PVS from other hyperintense structures (e.g. white matter hyperintensities, stroke lesions, or lacunes) effectively, the area under precision-recall curve dropped substantially (Frangi: from 94.21 [IQR 91.60, 96.16] to 43.76 [IQR 25.19, 63.38]; Jerman: from 94.51 [IQR 91.90, 95.37] to 58.00 [IQR 35.68, 64.87]; RORPO: from 98.72 [IQR 95.37, 98.96] to 71.87 [IQR 57.21, 76.63] without and with other hyperintense structures, respectively). The use of our computational model enables comparing segmentation methods and identifying their advantages and disadvantages, thereby providing means for testing and optimising pipelines for ongoing and future studies.

Computer-Aided Extraction of Select MRI Markers of Cerebral Small Vessel Disease: A Systematic Review

Cerebral small vessel disease (CSVD) is a major vascular contributor to cognitive impairment in ageing, including dementias. Imaging remains the most promising method for in vivo studies of CSVD. To replace the subjective and laborious visual rating approaches, emerging studies have applied state-of-the-art artificial intelligence to extract imaging biomarkers of CSVD from MRI scans. We aimed to summarise published computer-aided methods for the examination of three imaging biomarkers of CSVD, namely cerebral microbleeds (CMB), dilated perivascular spaces (PVS), and lacunes of presumed vascular origin. Seventy classical image processing, classical machine learning, and deep learning studies were identified. Transfer learning and weak supervision techniques have been applied to accommodate the limitations in the training data. While good performance metrics were achieved in local datasets, there have not been generalisable pipelines validated in different research and/or clinical cohorts. Future studies could consider pooling data from multiple sources to increase data size and diversity, and evaluating performance using both image processing metrics and associations with clinical measures.

Enlarged Perivascular Spaces Are Negatively Associated With Montreal Cognitive Assessment Scores in Older Adults

Emerging evidence suggests that enlarged perivascular spaces (ePVS) may be a clinically significant neuroimaging marker of global cognitive function related to cerebral small vessel disease (cSVD). We tested this possibility by assessing the relationship between ePVS and both a standardized measure of global cognitive function, the Montreal Cognitive Assessment (MoCA), and an established marker of cSVD, white matter hyperintensity volume (WMH) volume. One hundred and eleven community-dwelling older adults (56-86) underwent neuroimaging and MoCA testing. Quantification of region-specific ePVS burden was performed using a previously validated visual rating method and WMH volumes were computed using the standard ADNI pipeline. Separate linear regression models were run with ePVS as a predictor of MoCA scores and whole brain WMH volume. Results indicated a negative association between MoCA scores and both total ePVS counts (P ≤ 0.001) and centrum semiovale ePVS counts (P ≤ 0.001), after controlling for other relevant cSVD variables. Further, WMH volumes were positively associated with total ePVS (P = 0.010), basal ganglia ePVS (P ≤ 0.001), and centrum semiovale ePVS (P = 0.027). Our results suggest that ePVS burden, particularly in the centrum semiovale, may be a clinically significant neuroimaging marker of global cognitive dysfunction related to cSVD.

Perivascular Spaces, Glymphatic System and MR

The importance of the perivascular space (PVS) as one of the imaging markers of cerebral small vessel disease (CSVD) has been widely appreciated by the neuroradiologists. The PVS surrounds the small blood vessels in the brain and has a signal consistent with the cerebrospinal fluid (CSF) on MR. In a variety of physio-pathological statuses, the PVS may expand. The discovery of the cerebral glymphatic system has provided a revolutionary perspective to elucidate its pathophysiological mechanisms. Research on the function and pathogenesis of this system has become a prevalent topic among neuroradiologists. It is now believed that this system carries out the similar functions as the lymphatic system in other parts of the body and plays an important role in the removal of metabolic waste and the maintenance of homeostatic fluid circulation in the brain. In this article, we will briefly describe the composition of the cerebral glymphatic system, the influencing factors, the MR manifestations of the PVS and the related imaging technological advances. The aim of this research is to provide a reference for future clinical studies of the PVS and glymphatic system.

Characterization of motion patterns by a spatio-temporal saliency descriptor in cardiac cine MRI

BACKGROUND AND OBJECTIVE

Abnormalities of the heart motion reveal the presence of a disease. However, a quantitative interpretation of the motion is still a challenge due to the complex dynamics of the heart. This work proposes a quantitative characterization of regional cardiac motion patterns in cine magnetic resonance imaging (MRI) by a novel spatio-temporal saliency descriptor.

METHOD

The strategy starts by dividing the cardiac sequence into a progression of scales which are in due turn mapped to a feature space of regional orientation changes, mimicking the multi-resolution decomposition of oriented primitive changes of visual systems. These changes are estimated as the difference between a particular time and the rest of the sequence. This decomposition is then temporarily and regionally integrated for a particular orientation and then for the set of different orientations. A final spatio-temporal 4D saliency map is obtained as the summation of the previously integrated information for the available scales. The saliency dispersion of this map was computed in standard cardiac locations as a measure of the regional motion pattern and was applied to discriminate control and hypertrophic cardiomyopathy (HCM) subjects during the diastolic phase.

RESULTS

Salient motion patterns were estimated from an experimental set, which consisted of 3D sequences acquired by MRI from 108 subjects (33 control, 35 HCM, 20 dilated cardiomyopathy (DCM), and 20 myocardial infarction (MINF) from heterogeneous datasets). HCM and control subjects were classified by an SVM that learned the salient motion patterns estimated from the presented strategy, by achieving a 94% AUC. In addition, statistical differences (test t-student, p<0.05) were found among groups of disease in the septal and anterior ventricular segments at both the ED and ES, with salient motion characteristics aligned with existing knowledge on the diseases.

CONCLUSIONS

Regional wall motion abnormality in the apical, anterior, basal, and inferior segments was associated with the saliency dispersion in HCM, DCM, and MINF compared to healthy controls during the systolic and diastolic phases. This saliency analysis may be used to detect subtle changes in heart function.

Semi-automated Segmentation and Quantification of Perivascular Spaces at 7 Tesla in COVID-19

While COVID-19 is primarily considered a respiratory disease, it has been shown to affect the central nervous system. Mounting evidence shows that COVID-19 is associated with neurological complications as well as effects thought to be related to neuroinflammatory processes. Due to the novelty of COVID-19, there is a need to better understand the possible long-term effects it may have on patients, particularly linkage to neuroinflammatory processes. Perivascular spaces (PVS) are small fluid-filled spaces in the brain that appear on MRI scans near blood vessels and are believed to play a role in modulation of the immune response, leukocyte trafficking, and glymphatic drainage. Some studies have suggested that increased number or presence of PVS could be considered a marker of increased blood-brain barrier permeability or dysfunction and may be involved in or precede cascades leading to neuroinflammatory processes. Due to their size, PVS are better detected on MRI at ultrahigh magnetic field strengths such as 7 Tesla, with improved sensitivity and resolution to quantify both concentration and size. As such, the objective of this prospective study was to leverage a semi-automated detection tool to identify and quantify differences in perivascular spaces between a group of 10 COVID-19 patients and a similar subset of controls to determine whether PVS might be biomarkers of COVID-19-mediated neuroinflammation. Results demonstrate a detectable difference in neuroinflammatory measures in the patient group compared to controls. PVS count and white matter volume were significantly different in the patient group compared to controls, yet there was no significant association between PVS count and symptom measures. Our findings suggest that the PVS count may be a viable marker for neuroinflammation in COVID-19, and other diseases which may be linked to neuroinflammatory processes.

Automated grading of enlarged perivascular spaces in clinical imaging data of an acute stroke cohort using an interpretable, 3D deep learning framework

Enlarged perivascular spaces (EPVS), specifically in stroke patients, has been shown to strongly correlate with other measures of small vessel disease and cognitive impairment at 1 year follow-up. Typical grading of EPVS is often challenging and time consuming and is usually based on a subjective visual rating scale. The purpose of the current study was to develop an interpretable, 3D neural network for grading enlarged perivascular spaces (EPVS) severity at the level of the basal ganglia using clinical-grade imaging in a heterogenous acute stroke cohort, in the context of total cerebral small vessel disease (CSVD) burden. T2-weighted images from a retrospective cohort of 262 acute stroke patients, collected in 2015 from 5 regional medical centers, were used for analyses. Patients were given a label of 0 for none-to-mild EPVS (< 10) and 1 for moderate-to-severe EPVS (≥ 10). A three-dimensional residual network of 152 layers (3D-ResNet-152) was created to predict EPVS severity and 3D gradient class activation mapping (3DGradCAM) was used for visual interpretation of results. Our model achieved an accuracy 0.897 and area-under-the-curve of 0.879 on a hold-out test set of 15% of the total cohort (n = 39). 3DGradCAM showed areas of focus that were in physiologically valid locations, including other prevalent areas for EPVS. These maps also suggested that distribution of class activation values is indicative of the confidence in the model's decision. Potential clinical implications of our results include: (1) support for feasibility of automated of EPVS scoring using clinical-grade neuroimaging data, potentially alleviating rater subjectivity and improving confidence of visual rating scales, and (2) demonstration that explainable models are critical for clinical translation.

Direct Rating Estimation of Enlarged Perivascular Spaces (EPVS) in Brain MRI Using Deep Neural Network

In this article, we propose a deep-learning-based estimation model for rating enlarged perivascular spaces (EPVS) in the brain’s basal ganglia region using T2-weighted magnetic resonance imaging (MRI) images. The proposed method estimates the EPVS rating directly from the T2-weighted MRI without using either the detection or the segmentation of EVPS. The model uses the cropped basal ganglia region on the T2-weighted MRI. We formulated the rating of EPVS as a multi-class classification problem. Model performance was evaluated using 96 subjects’ T2-weighted MRI data that were collected from two hospitals. The results show that the proposed method can automatically rate EPVS—demonstrating great potential to be used as a risk indicator of dementia to aid early diagnosis.

The Glymphatic System: A Novel Therapeutic Target for Stroke Treatment

The glymphatic system (GS) is a novel defined brain-wide perivascular transit network between cerebrospinal fluid (CSF) and interstitial solutes that facilitates the clearance of brain metabolic wastes. The complicated network of the GS consists of the periarterial CSF influx pathway, astrocytes-mediated convective transport of fluid and solutes supported by AQP4 water channels, and perivenous efflux pathway. Recent researches indicate that the GS dysfunction is associated with various neurological disorders, including traumatic brain injury, hydrocephalus, epilepsy, migraine, and Alzheimer’s disease (AD). Meanwhile, the GS also plays a pivotal role in the pathophysiological process of stroke, including brain edema, blood–brain barrier (BBB) disruption, immune cell infiltration, neuroinflammation, and neuronal apoptosis. In this review, we illustrated the key anatomical structures of the GS, the relationship between the GS and the meningeal lymphatic system, the interaction between the GS and the BBB, and the crosstalk between astrocytes and other GS cellular components. In addition, we contributed to the current knowledge about the role of the GS in the pathology of stroke and the role of AQP4 in stroke. We further discussed the potential use of the GS in early risk assessment, diagnostics, prognostics, and therapeutics of stroke.

Interpretation and visualization techniques for deep learning models in medical imaging

Deep learning (DL) approaches to medical image analysis tasks have recently become popular; however, they suffer from a lack of human interpretability critical for both increasing understanding of the methods' operation and enabling clinical translation. This review summarizes currently available methods for performing image model interpretation and critically evaluates published uses of these methods for medical imaging applications. We divide model interpretation in two categories: (1) understanding model structure and function and (2) understanding model output. Understanding model structure and function summarizes ways to inspect the learned features of the model and how those features act on an image. We discuss techniques for reducing the dimensionality of high-dimensional data and cover autoencoders, both of which can also be leveraged for model interpretation. Understanding model output covers attribution-based methods, such as saliency maps and class activation maps, which produce heatmaps describing the importance of different parts of an image to the model prediction. We describe the mathematics behind these methods, give examples of their use in medical imaging, and compare them against one another. We summarize several published toolkits for model interpretation specific to medical imaging applications, cover limitations of current model interpretation methods, provide recommendations for DL practitioners looking to incorporate model interpretation into their task, and offer general discussion on the importance of model interpretation in medical imaging contexts.

Association of enlarged perivascular spaces with Aβ and tau deposition in cognitively normal older population

The relationship between magnetic resonance imaging (MRI)-visible enlarged perivascular spaces (EPVS) and Aβ and tau deposition is poorly investigated in cognitively normal older population. In our study, a total of 106 cognitively normal older subjects from the Alzheimer's Disease Neuroimaging Initiative database were included. All the subjects underwent brain MRI, florbetapir positron emission tomography (PET), and flortaucipir PET examinations. EPVS were rated on MRI using a 5-point scale in the basal ganglia (BG-EPVS) and the centrum semiovale (CSO-EPVS). Our study revealed that 43 subjects had high-degree BG-EPVS (degree >1) and 58 subjects had high-degree CSO-EPVS (degree >1). In logistic regression, high degree of BG-EPVS was associated with age (odds ratio [OR]: 1.08, 95% confidence interval [CI]: 1.01-1.16) and severe deep white matter hyperintensity (OR: 2.67, 95% CI: 1.12-6.35). High degree of CSO-EPVS was associated with flortaucipir PET positivity (OR: 2.24, 95% CI: 1.02-4.93). In conclusion, high degree of CSO-EPVS was associated with tau deposition in the brain, whereas high degree of BG-EPVS was associated with age and severe deep white matter hyperintensity, a marker of small vessel disease.

3D Deep Learning on Medical Images: A Review

The rapid advancements in machine learning, graphics processing technologies and the availability of medical imaging data have led to a rapid increase in the use of deep learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for the analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, we provide a brief mathematical description of 3D CNN and provide the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models in general) and possible future trends in the field.

Fetal brain age estimation and anomaly detection using attention-based deep ensembles with uncertainty

MRI-based brain age prediction has been widely used to characterize normal brain development, and deviations from the typical developmental trajectory are indications of brain abnormalities. Age prediction of the fetal brain remains unexplored, although it can be of broad interest to prenatal examination given the limited diagnostic tools available for assessment of the fetal brain. In this work, we built an attention-based deep residual network based on routine clinical T2-weighted MR images of 659 fetal brains, which achieved an overall mean absolute error of 0.767 weeks and R² of 0.920 in fetal brain age prediction. The predictive uncertainty and estimation confidence were simultaneously quantified from the network as markers for detecting fetal brain anomalies using an ensemble method. The novel markers overcame the limitations in conventional brain age estimation and demonstrated promising diagnostic power in differentiating several types of fetal abnormalities, including small head circumference, malformations and ventriculomegaly with the area under the curve of 0.90, 0.90 and 0.67, respectively. In addition, attention maps were derived from the network, which revealed regional features that contributed to fetal age estimation at each gestational stage. The proposed attention-based deep ensembles demonstrated superior performance in fetal brain age estimation and fetal anomaly detection, which has the potential to be translated to prenatal diagnosis in clinical practice.

Computational quantification of brain perivascular space morphologies: Associations with vascular risk factors and white matter hyperintensities. A study in the Lothian Birth Cohort 1936

BACKGROUND AND PURPOSE

Perivascular Spaces (PVS), also known as Virchow-Robin spaces, seen on structural brain MRI, are important fluid drainage conduits and are associated with small vessel disease (SVD). Computational quantification of visible PVS may enable efficient analyses in large datasets and increase sensitivity to detect associations with brain disorders. We assessed the associations of computationally-derived PVS parameters with vascular factors and white matter hyperintensities (WMH), a marker of SVD.

PARTICIPANTS

Community dwelling individuals (n = 700) from the Lothian Birth Cohort 1936 who had multimodal brain MRI at age 72.6 years (SD = 0.7).

METHODS

We assessed PVS computationally in the centrum semiovale and deep corona radiata on T2-weighted images. The computationally calculated measures were the total PVS volume and count per subject, and the mean individual PVS length, width and size, per subject. We assessed WMH by volume and visual Fazekas scores. We compared PVS visual rating to PVS computational metrics, and tested associations between each PVS measure and vascular risk factors (hypertension, diabetes, cholesterol), vascular history (cardiovascular disease and stroke), and WMH burden, using generalized linear models, which we compared using coefficients, confidence intervals and model fit.

RESULTS

In 533 subjects, the computational PVS measures correlated positively with visual PVS ratings (PVS count r = 0.59; PVS volume r = 0.61; PVS mean length r = 0.55; PVS mean width r = 0.52; PVS mean size r = 0.47). PVS size and width were associated with hypertension (OR 1.22, 95% CI [1.03 to 1.46] and 1.20, 95% CI [1.01 to 1.43], respectively), and stroke (OR 1.34, 95% CI [1.08 to 1.65] and 1.36, 95% CI [1.08 to 1.71], respectively). We found no association between other PVS measures and diabetes, hypercholesterolemia or cardiovascular disease history. Computational PVS volume, length, width and size were more strongly associated with WMH (PVS mean size versus WMH Fazekas score β = 0.66, 95% CI [0.59 to 0.74] and versus WMH volume β = 0.43, 95% CI [0.38 to 0.48]) than computational PVS count (WMH Fazekas score β = 0.21, 95% CI [0.11 to 0.3]; WMH volume β = 0.14, 95% CI [0.09 to 0.19]) or visual score. Individual PVS size showed the strongest association with WMH.

CONCLUSIONS

Computational measures reflecting individual PVS size, length and width were more strongly associated with WMH, stroke and hypertension than computational count or visual PVS score. Multidimensional computational PVS metrics may increase sensitivity to detect associations of PVS with risk exposures, brain lesions and neurological disease, provide greater anatomic detail and accelerate understanding of disorders of brain fluid and waste clearance.

Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polyps

Colorectal polyps are known to be potential precursors to colorectal cancer, which is one of the leading causes of cancer-related deaths on a global scale. Early detection and prevention of colorectal cancer is primarily enabled through manual screenings, where the intestines of a patient is visually examined. Such a procedure can be challenging and exhausting for the person performing the screening. This has resulted in numerous studies on designing automatic systems aimed at supporting physicians during the examination. Recently, such automatic systems have seen a significant improvement as a result of an increasing amount of publicly available colorectal imagery and advances in deep learning research for object image recognition. Specifically, decision support systems based on Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on both detection and segmentation of colorectal polyps. However, CNN-based models need to not only be precise in order to be helpful in a medical context. In addition, interpretability and uncertainty in predictions must be well understood. In this paper, we develop and evaluate recent advances in uncertainty estimation and model interpretability in the context of semantic segmentation of polyps from colonoscopy images. Furthermore, we propose a novel method for estimating the uncertainty associated with important features in the input and demonstrate how interpretability and uncertainty can be modeled in DSSs for semantic segmentation of colorectal polyps. Results indicate that deep models are utilizing the shape and edge information of polyps to make their prediction. Moreover, inaccurate predictions show a higher degree of uncertainty compared to precise predictions.

Image processing approaches to enhance perivascular space visibility and quantification using MRI

Imaging the perivascular spaces (PVS), also known as Virchow-Robin space, has significant clinical value, but there remains a need for neuroimaging techniques to improve mapping and quantification of the PVS. Current technique for PVS evaluation is a scoring system based on visual reading of visible PVS in regions of interest, and often limited to large caliber PVS. Enhancing the visibility of the PVS could support medical diagnosis and enable novel neuroscientific investigations. Increasing the MRI resolution is one approach to enhance the visibility of PVS but is limited by acquisition time and physical constraints. Alternatively, image processing approaches can be utilized to improve the contrast ratio between PVS and surrounding tissue. Here we combine T1- and T2-weighted images to enhance PVS contrast, intensifying the visibility of PVS. The Enhanced PVS Contrast (EPC) was achieved by combining T1- and T2-weighted images that were adaptively filtered to remove non-structured high-frequency spatial noise. EPC was evaluated on healthy young adults by presenting them to two expert readers and also through automated quantification. We found that EPC improves the conspicuity of the PVS and aid resolving a larger number of PVS. We also present a highly reliable automated PVS quantification approach, which was optimized using expert readings.

Recent Advances of Deep Learning in Bioinformatics and Computational Biology

Extracting inherent valuable knowledge from omics big data remains as a daunting problem in bioinformatics and computational biology. Deep learning, as an emerging branch from machine learning, has exhibited unprecedented performance in quite a few applications from academia and industry. We highlight the difference and similarity in widely utilized models in deep learning studies, through discussing their basic structures, and reviewing diverse applications and disadvantages. We anticipate the work can serve as a meaningful perspective for further development of its theory, algorithm and application in bioinformatic and computational biology.