Fast Fluid Attenuated Inversion Recovery (FLAIR) imaging and associated artefacts in Magnetic Resonance Imaging (MRI)

Detection of subtle white matter lesions in MRI through texture feature extraction and boundary delineation using an embedded clustering strategy

White matter lesions (WML) underlie multiple brain disorders, and automatic WML segmentation is crucial to evaluate the natural disease course and effectiveness of clinical interventions, including drug discovery. Although recent research has achieved tremendous progress in WML segmentation, accurate detection of subtle WML present early in the disease course remains particularly challenging. Here we propose an approach to automatic WML segmentation of mild WML loads using an intensity standardisation technique, gray level co-occurrence matrix (GLCM) embedded clustering technique, and random forest (RF) classifier to extract texture features and identify morphology specific to true WML. We precisely define their boundaries through a local outlier factor (LOF) algorithm that identifies edge pixels by local density deviation relative to its neighbors. The automated approach was validated on 32 human subjects, demonstrating strong agreement and correlation (excluding one outlier) with manual delineation by a neuroradiologist through Intra-Class Correlation (ICC = 0.881, 95% CI 0.769, 0.941) and Pearson correlation (r = 0.895, p-value < 0.001), respectively, and outperforming three leading algorithms (Trimmed Mean Outlier Detection, Lesion Prediction Algorithm, and SALEM-LS) in five of the six established key metrics defined in the MICCAI Grand Challenge. By facilitating more accurate segmentation of subtle WML, this approach may enable earlier diagnosis and intervention.

Infratentorial lesions in multiple sclerosis patients: intra- and inter-rater variability in comparison to a fully automated segmentation using 3D convolutional neural networks

OBJECTIVE

Automated quantification of infratentorial multiple sclerosis lesions on magnetic resonance imaging is clinically relevant but challenging. To overcome some of these problems, we propose a fully automated lesion segmentation algorithm using 3D convolutional neural networks (CNNs).

METHODS

The CNN was trained on a FLAIR image alone or on FLAIR and T1-weighted images from 1809 patients acquired on 156 different scanners. An additional training using an extra class for infratentorial lesions was implemented. Three experienced raters manually annotated three datasets from 123 MS patients from different scanners.

RESULTS

The inter-rater sensitivity (SEN) was 80% for supratentorial lesions but only 62% for infratentorial lesions. There was no statistically significant difference between the inter-rater SEN and the SEN of the CNN with respect to the raters. For supratentorial lesions, the CNN featured an intra-rater intra-scanner SEN of 0.97 (R1 = 0.90, R2 = 0.84) and for infratentorial lesion a SEN of 0.93 (R1 = 0.61, R2 = 0.73).

CONCLUSION

The performance of the CNN improved significantly for infratentorial lesions when specifically trained on infratentorial lesions using a T1 image as an additional input and matches the detection performance of experienced raters. Furthermore, for infratentorial lesions the CNN was more robust against repeated scans than experienced raters.

KEY POINTS

• A 3D convolutional neural network was trained on MRI data from 1809 patients (156 different scanners) for the quantification of supratentorial and infratentorial multiple sclerosis lesions. • Inter-rater variability was higher for infratentorial lesions than for supratentorial lesions. The performance of the 3D convolutional neural network (CNN) improved significantly for infratentorial lesions when specifically trained on infratentorial lesions using a T1 image as an additional input. • The detection performance of the CNN matches the detection performance of experienced raters.

Cognitive impairment and the regional distribution of cerebellar lesions in multiple sclerosis

BACKGROUND

Cerebellar lesions are often reported in relapsing-remitting multiple sclerosis (RRMS) and have been associated with impaired motor function and cognitive status. However, prior research has primarily focused on summary measures of cerebellar involvement (e.g. total lesion load, gray/white matter volume) and not on the effect of lesion load within specific regions of cerebellar white matter.

OBJECTIVE

Spatially map the probability of cerebellar white matter lesion (CWML) occurrence in RRMS and explore the relationship between cognitive impairment and lesion (CWML) location within the cerebellum.

METHODS

High-resolution structural magnetic resonance imaging (MRI) was acquired on 16 cognitively impaired (CI) and 15 cognitively preserved (CP) RRMS subjects at 3T and used for lesion identification and voxel-based lesion-symptom mapping (VLSM).

RESULTS

CI RRMS demonstrated a predilection for the middle cerebellar peduncle (MCP). VLSM results indicate that lesions of the MCP are significantly associated with CI in RRMS. Measures of cerebellar lesion load were correlated with age at disease onset but not disease duration.

CONCLUSION

A specific pattern of cerebellar lesions involving the MCP, rather than the total CWML load, contributes to cognitive dysfunction in RRMS. Cerebellar lesion profiles may provide a biomarker of current or evolving risk for cognitive status change in RRMS.

[Effect of Contrast on FLAIR by Changing the Number of Packages]

We have found that the number of packages influences contrast for brain tissue signals on fluid-attenuated inversion recovery (FLAIR). The purpose of this study was to evaluate the contrast of white and gray matters by changing the number of packages. In a volunteer study (n=8), FLAIR images were obtained with the various number of packages (number of package=2, 3, 4, 5). We investigated the same imaging condition at both 1.5 and 3.0T. The signal intensity of white and gray matters in all volunteers was increased as increasing the number of packages. Moreover, the contrast ratio between white and gray matters was slightly decreased. In our conclusion, the contrast between the gray and white matters on FLAIR was influenced by the number of packages.

T2 FLAIR artifacts at 3-T brain magnetic resonance imaging

The purpose of this retrospective clinical study was to identify and evaluate the presence and frequency of T2 FLAIR artifacts on brain MRI studies performed at 3 T. We reviewed axial T2 FLAIR images in 200 consecutive unremarkable brain MRI studies performed at 3 T. All studies were reviewed for the presence of artifacts caused by pulsatile CSF flow, magnetic susceptibility and no nulling of the CSF signal. T2 FLAIR images introduce several artifacts that may degrade image quality and mimic pathology. Knowledge of these artifacts and increased severity and frequency at 3 T is of particular importance in avoiding a misdiagnosis.

White Matter Lesion Assessment in Patients with Cognitive Impairment and Healthy Controls: Reliability Comparisons between Visual Rating, a Manual, and an Automatic Volumetrical MRI Method-The Gothenburg MCI Study

Age-related white matter lesions (WML) are a risk factor for stroke, cognitive decline, and dementia. Different requirements are imposed on methods for the assessment of WML in clinical settings and for research purposes, but reliability analysis is of major importance. In this study, WML assessment with three different methods was evaluated. In the Gothenburg mild cognitive impairment study, MRI scans from 152 participants were used to assess WML with the Fazekas visual rating scale on T2 images, a manual volumetric method on FLAIR images, and FreeSurfer volumetry on T1 images. Reliability was acceptable for all three methods. For low WML volumes (2/3 of the patients), reliability was overall lower and nonsignificant for the manual volumetric method. Unreliability in the assessment of patients with low WML with manual volumetry may mainly be due to intensity variation in the FLAIR sequence used; hence, intensity standardization and normalization methods must be used for more accurate assessments. The FreeSurfer segmentations resulted in smaller WML volumes than the volumes acquired with the manual method and showed deviations from visible hypointensities in the T1 images, which quite likely reduces validity.

Quantitative measurements of relative fluid-attenuated inversion recovery (FLAIR) signal intensities in acute stroke for the prediction of time from symptom onset

In acute stroke magnetic resonance imaging, a 'mismatch' between visibility of an ischemic lesion on diffusion-weighted imaging (DWI) and missing corresponding parenchymal hyperintensities on fluid-attenuated inversion recovery (FLAIR) data sets was shown to identify patients with time from symptom onset ≤4.5 hours with high specificity. However, moderate sensitivity and suboptimal interpreter agreement are limitations of a visual rating of FLAIR lesion visibility. We tested refined image analysis methods in patients included in the previously published PREFLAIR study using refined visual analysis and quantitative measurements of relative FLAIR signal intensity (rSI) from a three-dimensional, segmented stroke lesion volume. A total of 399 patients were included. The rSI of FLAIR lesions showed a moderate correlation with time from symptom onset (r=0.382, P<0.001). A FLAIR rSI threshold of <1.0721 predicted symptom onset ≤4.5 hours with slightly increased specificity (0.85 versus 0.78) but also slightly decreased sensitivity (0.47 versus 0.58) as compared with visual analysis. Refined visual analysis differentiating between 'subtle' and 'obvious' FLAIR hyperintensities and classification and regression tree algorithms combining information from visual and quantitative analysis also did not improve diagnostic accuracy. Our results raise doubts whether the prediction of stroke onset time by visual image judgment can be improved by quantitative rSI measurements.

[Suppression of CSF artifact in fast FLAIR sequence at 3.0 Tesla]

The purpose of this study was to suppress CSF flow artifacts in the fast FLAIR sequence at 3.0T MRI. We investigated the influence of thickness of the inversion pulse in the sequence on the high-intensity CSF flow artifacts based on the flow phantom and in-vivo studies at 1.5T and 3.0T. Results demonstrated that CSF flow artifacts at 3.0T were clearly stronger than at as 1.5T. Moreover, 3.0T was influenced by the crosstalk between each inversion pulse compared with 1.5T. The optimal setting of inversion pulse for two interleaving acquisitions for fast FLAIR imaging at 3.0T was approximately 1.5 fold on the basis of sum of slice thickness and slice gap. The appropriate setting of thickness of inversion pulse in fast FLAIR imaging reduces the incidence of CSF flow artifacts at 3.0T.