Recovering SWI-filtered phase data using deep learning

An update on susceptibility-weighted imaging in brain gliomas

Susceptibility-weighted imaging (SWI) has become a standard component of most brain MRI protocols. While traditionally used for detecting and characterising brain hemorrhages typically associated with stroke or trauma, SWI has also shown promising results in glioma assessment. Numerous studies have highlighted SWI's role in differentiating gliomas from other brain lesions, such as primary central nervous system lymphomas or metastases. Additionally, SWI aids radiologists in non-invasively grading gliomas and predicting their phenotypic profiles. Various researchers have suggested incorporating SWI as an adjunct sequence for predicting treatment response and for post-treatment monitoring. A significant focus of these studies is on the detection of intratumoural susceptibility signals (ITSSs) in gliomas, which are indicative of microhemorrhages and vessels within the tumour. The quantity, distribution, and characteristics of these ITSSs can provide radiologists with more precise information for evaluating and characterising gliomas. Furthermore, the potential benefits and added value of performing SWI after the administration of gadolinium-based contrast agents (GBCAs) have been explored. This review offers a comprehensive, educational, and practical overview of the potential applications and future directions of SWI in the context of glioma assessment. CLINICAL RELEVANCE STATEMENT: SWI has proven effective in evaluating gliomas, especially through assessing intratumoural susceptibility signal changes, and is becoming a promising, easily integrated tool in MRI protocols for both pre- and post-treatment assessments. KEY POINTS: • Susceptibility-weighted imaging is the most sensitive sequence for detecting blood and calcium inside brain lesions. • This sequence, acquired with and without gadolinium, helps with glioma diagnosis, characterisation, and grading through the detection of intratumoural susceptibility signals. • There are ongoing challenges that must be faced to clarify the role of susceptibility-weighted imaging for glioma assessment.

Iron Deficiency and Sleep/Wake Behaviors: A Scoping Review of Clinical Practice Guidelines-How to Overcome the Current Conundrum?

Current evidence suggests that iron deficiency (ID) plays a key role in the pathogenesis of conditions presenting with restlessness such as attention deficit hyperactivity disorder (ADHD) and restless legs syndrome (RLS). In clinical practice, ID and iron supplementation are not routinely considered in the diagnostic work-up and/or as a treatment option in such conditions. Therefore, we conducted a scoping literature review of ID guidelines. Of the 58 guidelines included, only 9 included RLS, and 3 included ADHD. Ferritin was the most frequently cited biomarker, though cutoff values varied between guidelines and depending on additional factors such as age, sex, and comorbidities. Recommendations surrounding measurable iron biomarkers and cutoff values varied between guidelines; moreover, despite capturing the role of inflammation as a concept, most guidelines often did not include recommendations for how to assess this. This lack of harmonization on the interpretation of iron and inflammation biomarkers raises questions about the applicability of current guidelines in clinical practice. Further, the majority of ID guidelines in this review did not include the ID-associated disorders, ADHD and RLS. As ID can be associated with altered movement patterns, a novel consensus is needed for investigating and interpreting iron status in the context of different clinical phenotypes.

Deeply 3D-T1-TFE hypointense voxels are characteristic of phase-rim lesions in multiple sclerosis

OBJECTIVES

The development of new drugs for the treatment of progressive multiple sclerosis (MS) highlights the need for new prognostic biomarkers. Phase-rim lesions (PRLs) have been proposed as markers of progressive disease but are difficult to identify and quantify. Previous studies have identified T1-hypointensity in PRLs. The aim of this study was to compare the intensity profiles of PRLs and non-PRL white-matter lesions (nPR-WMLs) on three-dimensional T1-weighted turbo field echo (3DT1TFE) MRI. We then evaluated the performance of a derived metric as a surrogate for PRLs as potential markers for risk of disease progression.

METHODS

This study enrolled a cohort of relapsing-remitting (n = 10) and secondary progressive MS (n = 10) patients for whom 3 T MRI was available. PRLs and nPR-WMLs were segmented, and voxel-wise normalized T1-intensity histograms were analyzed. The lesions were divided equally into training and test datasets, and the fifth-percentile (p5)-normalized T1-intensity of each lesion was compared between groups and used for classification prediction.

RESULTS

Voxel-wise histogram analysis showed a unimodal histogram for nPR-WMLs and a bimodal histogram for PRLs with a large peak in the hypointense limit. Lesion-wise analysis included 1075 nPR-WMLs and 39 PRLs. The p5 intensity of PRLs was significantly lower than that of nPR-WMLs. The T1 intensity-based PRL classifier had a sensitivity of 0.526 and specificity of 0.959.

CONCLUSIONS

Profound hypointensity on 3DT1TFE MRI is characteristic of PRLs and rare in other white-matter lesions. Given the widespread availability of T1-weighted imaging, this feature might serve as a surrogate biomarker for smoldering inflammation.

CLINICAL RELEVANCE STATEMENT

Quantitative analysis of 3DT1TFE may detect deeply hypointense voxels in multiple sclerosis lesions, which are highly specific to PRLs. This could serve as a specific indicator of smoldering inflammation in MS, aiding in early detection of disease progression.

KEY POINTS

• Phase-rim lesions (PRLs) in multiple sclerosis present a characteristic T1-hypointensity on 3DT1TFE MRI. • Intensity-normalized 3DT1TFE can be used to systematically identify and quantify these deeply hypointense foci. • Deep T1-hypointensity may act as an easily detectable, surrogate marker for PRLs.

The iron burden of cerebral microbleeds contributes to brain atrophy through the mediating effect of white matter hyperintensity

The goal of this work was to explore the total iron burden of cerebral microbleeds (CMBs) using a semi-automatic quantitative susceptibility mapping and to establish its effect on brain atrophy through the mediating effect of white matter hyperintensities (WMH). A total of 95 community-dwelling people were enrolled. Quantitative susceptibility mapping (QSM) combined with a dynamic programming algorithm (DPA) was used to measure the characteristics of 1309 CMBs. WMH were evaluated according to the Fazekas scale, and brain atrophy was assessed using a 2D linear measurement method. Histogram analysis was used to explore the distribution of CMBs susceptibility, volume, and total iron burden, while a correlation analysis was used to explore the relationship between volume and susceptibility. Stepwise regression analysis was used to analyze the risk factors for CMBs and their contribution to brain atrophy. Mediation analysis was used to explore the interrelationship between CMBs and brain atrophy. We found that the frequency distribution of susceptibility of the CMBs was Gaussian in nature with a mean of 201 ppb and a standard deviation of 84 ppb; however, the volume and total iron burden of CMBs were more Rician in nature. A weak but significant correlation between the susceptibility and volume of CMBs was found (r = -0.113, P < 0.001). The periventricular WMH (PVWMH) was a risk factor for the presence of CMBs (number: β = 0.251, P = 0.014; volume: β = 0.237, P = 0.042; total iron burden: β = 0.238, P = 0.020) and was a risk factor for brain atrophy (third ventricle width: β = 0.325, P = 0.001; Evans's index: β = 0.323, P = 0.001). PVWMH had a significant mediating effect on the correlation between CMBs and brain atrophy. In conclusion, QSM along with the DPA can measure the total iron burden of CMBs. PVWMH might be a risk factor for CMBs and may mediate the effect of CMBs on brain atrophy.

HFP-QSMGAN: QSM from homodyne-filtered phase images

PURPOSE

Homodyne filtering is a standard preprocessing step in the estimation of SWI. Unfortunately, SWI is not quantitative, and QSM cannot be accurately estimated from filtered phase images. Compared with gradient-echo sequences suitable for computing QSM, SWI is more readily available and is often the only susceptibility-sensitive sequence acquired in the clinical setting. In this project, we aimed to quantify susceptibility from the homodyne-filtered phase (HFP), acquired for computing susceptibility-weighted images, using convolutional neural networks to solve the compounded problem of (1) computing the solution to the inverse dipole problem, and (2) compensating for the effects of the homodyne filtering.

METHODS

Two convolutional neural networks, the U-Net and a modified QSMGAN architecture (HFP-QSMGAN), were trained to predict QSM maps at different TEs from HFP images. The QSM maps were quantified from a gradient-echo sequence acquired in the same individuals using total generalized variation (TGV)-QSM. The QSM maps estimated directly from the HFP were also included for comparison. Voxel-wise predictions and, importantly, regional predictions of susceptibility with adjustment to a reference region, were compared.

RESULTS

Our results indicate that the U-Net model provides more accurate voxel-wise predictions of susceptibility compared with HFP-QSMGAN and HFP-QSM. However, regional estimates of susceptibility predicted by HFP-QSMGAN are more strongly correlated with the values from TGV-QSM compared with those of U-Net and HFP-QSM.

CONCLUSION

Accurate prediction of susceptibility can be achieved from filtered SWI phase using convolutional neural networks.