T2-FLAIR Magnetic Resonance Images Research Articles

Unsupervised MRI motion artifact disentanglement: introducing MAUDGAN

Objective. This study developed an unsupervised motion artifact reduction method for magnetic resonance imaging (MRI) images of patients with brain tumors. The proposed novel design uses multi-parametric multicenter contrast-enhanced T1W (ceT1W) and T2-FLAIR MRI images. Approach. The proposed framework included two generators, two discriminators, and two feature extractor networks. A 3-fold cross-validation was used to train and fine-tune the hyperparameters of the proposed model using 230 brain MRI images with tumors, which were then tested on 148 patients’ in-vivo datasets. An ablation was performed to evaluate the model’s compartments. Our model was compared with Pix2pix and CycleGAN. Six evaluation metrics were reported, including normalized mean squared error (NMSE), structural similarity index (SSIM), multi-scale-SSIM (MS-SSIM), peak signal-to-noise ratio (PSNR), visual information fidelity (VIF), and multi-scale gradient magnitude similarity deviation (MS-GMSD). Artifact reduction and consistency of tumor regions, image contrast, and sharpness were evaluated by three evaluators using Likert scales and compared with ANOVA and Tukey’s HSD tests. Main results. On average, our method outperforms comparative models to remove heavy motion artifacts with the lowest NMSE (18.34±5.07%) and MS-GMSD (0.07 ± 0.03) for heavy motion artifact level. Additionally, our method creates motion-free images with the highest SSIM (0.93 ± 0.04), PSNR (30.63 ± 4.96), and VIF (0.45 ± 0.05) values, along with comparable MS-SSIM (0.96 ± 0.31). Similarly, our method outperformed comparative models in removing in-vivo motion artifacts for different distortion levels except for MS- SSIM and VIF, which have comparable performance with CycleGAN. Moreover, our method had a consistent performance for different artifact levels. For the heavy level of motion artifacts, our method got the highest Likert scores of 2.82 ± 0.52, 1.88 ± 0.71, and 1.02 ± 0.14 (p-values ≪ 0.0001) for our method, CycleGAN, and Pix2pix respectively. Similar trends were also found for other motion artifact levels. Significance. Our proposed unsupervised method was demonstrated to reduce motion artifacts from the ceT1W brain images under a multi-parametric framework.

Cardiometabolic health across menopausal years is linked to white matter hyperintensities up to a decade later.

The menopause transition is associated with several cardiometabolic risk factors. Poor cardiometabolic health is further linked to microvascular brain lesions, which can be detected as white matter hyperintensities (WMHs) using T2-FLAIR magnetic resonance imaging (MRI) scans. Females show higher risk for WMHs post-menopause, but it remains unclear whether changes in cardiometabolic risk factors underlie menopause-related increase in brain pathology. In this study, we assessed whether cross-sectional measures of cardiometabolic health, including body mass index (BMI) and waist-to-hip ratio (WHR), blood lipids, blood pressure, and long-term blood glucose (HbA1c), as well as longitudinal changes in BMI and WHR, differed according to menopausal status at baseline in 9,882 UK Biobank females (age range 40-70 years, n premenopausal = 3,529, n postmenopausal = 6,353). Furthermore, we examined whether these cardiometabolic factors were associated with WMH outcomes at the follow-up assessment, on average 8.78 years after baseline. Postmenopausal females showed higher levels of baseline blood lipids (HDL = 0.14, p < 0.001, LDL = 0.20, p < 0.001, triglycerides = 0.12, p < 0.001) and HbA1c ( = 0.24, p < 0.001) compared to premenopausal women, beyond the effects of age. Over time, BMI increased more in the premenopausal compared to the postmenopausal group ( = -0.08, p < 0.001), while WHR increased to a similar extent in both groups ( = -0.03, p = 0.102). The change in WHR was however driven by increased waist circumference only in the premenopausal group. While the group level changes in BMI and WHR were in general small, these findings point to distinct anthropometric changes in pre- and postmenopausal females over time. Higher baseline measures of BMI, WHR, triglycerides, blood pressure, and HbA1c, as well as longitudinal increases in BMI and WHR, were associated with larger WMH volumes ( range = 0.03-0.13, p ≤ 0.002). HDL showed a significant inverse relationship with WMH volume ( = -0.27, p < 0.001). Our findings emphasise the importance of monitoring cardiometabolic risk factors in females from midlife through the menopause transition and into the postmenopausal phase, to ensure improved cerebrovascular outcomes in later years.

Normative values of the brain health index in UK biobank

BackgroundThe Brain Health Index (BHI) is an automated approach to quantifying brain integrity, combining different types of structural magnetic resonance imaging (MRI). Normative values derived from generally healthy individuals provide a vital baseline for understanding neurodegenerative change. Although commonplace in other areas of medicine, these are not always established when proposing new analytical approaches using MRI. The scale and quality of the UK Biobank imaging cohort (approximately N = 50k, as of 2022) allows for derivation of such values, and the wealth of additional lifestyle, physiological and demographic data enables validation of BHI through comparison with more established variables which may affect brain health. AimThis study aimed to: 1) establish normative BHI values in a cohort of ‘healthy’ participants, and 2) explore associations between BHI and risk factors for brain health. MethodsThe BHI was computed using voxel-based Gaussian mixture model cluster analysis of T1 and T2 FLAIR MRI in a sub-cohort of UK Biobank participants. From these data, normative score curves – with bounds described as 1, 2 and 3 standard deviations from the mean – were produced for males and females, using regression analyses to measure the scale of the BHI values as a function of age. Additional Pearson’s correlation testing was used to examine known risk factors to brain health and their relationship to BHI scores, with t-tests and ANOVAs used to determine between-group differences in BHI scoring. ResultsData from 2,990 participants (50.07% male, 97.05% Caucasian, 43.6% with degree-level education) were used to derive normative BHI curves from 48 to 77 years old. BHI scores were higher in female than male participants (95% CI: 0.0103 to 0.0162, p <0.001, Cohen’s d = 0.0416), males with a degree (95% CI: 0.000 to 0.009; p < 0.05; Cohen’s d = 0.044), and lower in people with type 2 diabetes mellitus (95% CI: 0.018 to 0.033; p <0.001; Cohen’s d = 0.0417), hypertension (95% CI: 0.008 to 0.018; p <0.001; Cohen’s d = 0.0419), and regular smokers (95% CI: 0.009 to 0.017, p <0.001, Cohen’s d = 0.041). BHI scores were higher in those with lower waist-to-hip ratios (WHR; males: R2 = 0.02121, F(1, 1466) = 31.77, p <0.001; females: R2 = 0.02201, F(1, 1454) = 32.72, p <0.001), and lower pulse pressure (males: R2 = 0.06261, F(1, 1215) = 81.16, p <0.001; females: R2 = 0.07616, F(1, 1205) = 99.34, p <0.001). ConclusionsBHI score curves may provide useful reference values for future clinical research. More work is required to determine normative values in more diverse populations.

Correlation between quantitative and qualitative assessments of white matter hyperintensities in patients from a multicentric memory clinic population

AbstractBackgroundWhite matter hyperintensities (WMH) can be visualized as abnormal T2 signal in the periventricular, deep and subcortical white matter on Magnetic Resonance Imaging (MRI). WMH increase with age and are associated with stroke, cognitive decline and dementia. The most common visual rating scale used to assess WMH in the clinical setting is the Fazekas scale (Fazekas et al., 1987). The current study investigated the relationship between WMH volume (expressed as a % of intra‐cranial volume (ICV)) calculated using an automated method included in the QyScore® medical device, and Fazekas scores in a multicentric memory clinic population at baseline.Method1959 participants from the MEMENTO cohort (Age 71.02 +/‐ 8.61, 1218 Female, MMSE 27.95 +/‐ 1.91) had 3DT1 and T2 FLAIR MRI scans analyzed with QyScore®, an FDA‐approved and CE‐marked image analysis software. 814 had amyloid status from CSF or PET, of which 216 were Amyloid+. WMH volumes are reported in mL, corrected for %ICV. Correlation between Fazekas deep white matter (DWM) scores and quantitative WMH measurements was ascertained by Spearman’s rank correlation.ResultThere was a significant positive correlation between Fazekas DWM scores and WMH %ICV (0.76 p&lt;0.001) for the total sample, amyloid positive (0.81 p&lt;0.001) and negative (0.72 p&lt;0.001) patients. The correlation was also strong when separated by clinical diagnosis: patients with Subjective Cognitive Complaint (SCC, N = 305, AGE: 69.87 +/‐ 8.03, 197 female, MMSE: 28.86 +/‐ 1.17) and MCI (N = 1638, Age: 71.2 +/‐ 8.69, 1014 Female, MMSE: 27.8 +/‐ 1.95) presented Fazekas DWM scores correlated with WMH %ICV (0.66 p&lt;0.001 for SCC; 0.77 p&lt;0.001 for MCI).ConclusionThe automated quantification of ICV‐corrected WMH were well‐correlated to Fazekas DWM scores. Considering that visual rating of WMH is time consuming and suffers from intra and inter‐operator variability, the quantitative assessment of WMH load provided by QyScore® may improve the assessment of patients with cognitive impairment.

Correlation between quantitative and qualitative assessments of white matter hyperintensities inpatients from a multicentric memory clinic population

AbstractBackgroundWhite matter hyperintensities (WMH) can be visualized as abnormal T2 signal in the periventricular, deep and subcortical white matter on Magnetic Resonance Imaging (MRI). WMH increase with age and are associated with stroke, cognitive decline and dementia. The most common visual rating scale used to assess WMH in the clinical setting is the Fazekas scale (Fazekas et al., 1987). The current study investigated the relationship between WMH volume (expressed as a % of intra‐cranial volume (ICV)) calculated using an automated method included in the QyScore® medical device, and Fazekas scores in a multicentric memory clinic population at baseline.Method1959 participants from the MEMENTO cohort (Age 71.02 +/‐ 8.61, 1218 Female, MMSE 27.95 +/‐ 1.91) had 3DT1 and T2 FLAIR MRI scans analyzed with QyScore®, an FDA‐approved and CE‐marked image analysis software. 814 had amyloid status from CSF or PET, of which 216 were Amyloid+. WMH volumes are reported in mL, corrected for %ICV. Correlation between Fazekas deep white matter (DWM) scores and quantitative WMH measurements was ascertained by Spearman’s rank correlation.ResultThere was a significant positive correlation between Fazekas DWM scores and WMH %ICV (0.76 p&lt;0.001) for the total sample, amyloid positive (0.81 p&lt;0.001) and negative (0.72 p&lt;0.001) patients. The correlation was also strong when separated by clinical diagnosis: patients with Subjective Cognitive Complaint (SCC, N= 305, AGE: 69.87 +/‐ 8.03, 197 female, MMSE: 28.86 +/‐ 1.17) and MCI (N = 1638, Age: 71.2 +/‐ 8.69, 1014 Female, MMSE: 27.8 +/‐ 1.95) presented Fazekas DWM scores correlated with WMH %ICV (0.66 p&lt;0.001 for SCC; 0.77 p&lt;0.001 for MCI).ConclusionThe automated quantification of ICV‐corrected WMH were well‐correlated to Fazekas DWM scores. Considering that visual rating of WMH is time consuming and suffers from intra and inter‐operator variability, the quantitative assessment of WMH load provided by QyScore® may improve the assessment of patients with cognitive impairment.

Brain Imaging Abnormalities in Mixed Alzheimer's and Subcortical Vascular Dementia.

A large proportion of Alzheimer's disease (AD) patients have coexisting subcortical vascular dementia (SVaD), a condition referred to as mixed dementia (MixD). Brain imaging features of MixD presumably include those of cerebrovascular disease and AD pathology, but are difficult to characterize due to their heterogeneity. To perform an exploratory analysis of conventional and non-conventional structural magnetic resonance imaging (MRI) abnormalities in MixD and to compare them to those observed in AD and SVaD. We conducted a cross-sectional, region-of-interest-based analysis of 1) hyperintense white-matter signal abnormalities (WMSA) on T2-FLAIR and hypointense WMSA on T1-weighted MRI; 2) diffusion tensor imaging; 3) quantitative susceptibility mapping; and 4) effective transverse relaxation rate (R2*) in N = 17 participants (AD:5, SVaD:5, MixD:7). General linear model was used to explore group differences in these brain imaging measures. Model findings suggested imaging characteristics specific to our MixD group, including 1) higher burden of WMSAs on T1-weighted MRI (versus both AD and SVaD); 2) frontal lobar preponderance of WMSAs on both T2-FLAIR and T1-weighted MRI; 3) higher fractional anisotropy values within normal-appear white-matter tissues (versus SVaD, but not AD); and 4) lower R2* values within the T2-FLAIR WMSA areas (versus both AD and SVaD). These findings suggest a preliminary picture of the location and type of brain imaging characteristics associated with MixD. Future imaging studies may employ region-specific hypotheses to distinguish MixD more rigorously from AD or SVaD.

Automatic differentiation of Grade I and II meningiomas on magnetic resonance image using an asymmetric convolutional neural network

The Grade of meningioma has significant implications for selecting treatment regimens ranging from observation to surgical resection with adjuvant radiation. For most patients, meningiomas are diagnosed radiologically, and Grade is not determined unless a surgical procedure is performed. The goal of this study is to train a novel auto-classification network to determine Grade I and II meningiomas using T1-contrast enhancing (T1-CE) and T2-Fluid attenuated inversion recovery (FLAIR) magnetic resonance (MR) images. Ninety-six consecutive treatment naïve patients with pre-operative T1-CE and T2-FLAIR MR images and subsequent pathologically diagnosed intracranial meningiomas were evaluated. Delineation of meningiomas was completed on both MR images. A novel asymmetric 3D convolutional neural network (CNN) architecture was constructed with two encoding paths based on T1-CE and T2-FLAIR. Each path used the same 3 × 3 × 3 kernel with different filters to weigh the spatial features of each sequence separately. Final model performance was assessed by tenfold cross-validation. Of the 96 patients, 55 (57%) were pathologically classified as Grade I and 41 (43%) as Grade II meningiomas. Optimization of our model led to a filter weighting of 18:2 between the T1-CE and T2-FLAIR MR image paths. 86 (90%) patients were classified correctly, and 10 (10%) were misclassified based on their pre-operative MRs with a model sensitivity of 0.85 and specificity of 0.93. Among the misclassified, 4 were Grade I, and 6 were Grade II. The model is robust to tumor locations and sizes. A novel asymmetric CNN with two differently weighted encoding paths was developed for successful automated meningioma grade classification. Our model outperforms CNN using a single path for single or multimodal MR-based classification.

Initial Condition Assessment for Reaction-Diffusion Glioma Growth Models: A Translational MRI-Histology (In)Validation Study.

Reaction-diffusion models have been proposed for decades to capture the growth of gliomas. Nevertheless, these models require an initial condition: the tumor cell density distribution over the whole brain at diagnosis time. Several works have proposed to relate this distribution to abnormalities visible on magnetic resonance imaging (MRI). In this work, we verify these hypotheses by stereotactic histological analysis of a non-operated brain with glioblastoma using a 3D-printed slicer. Cell density maps are computed from histological slides using a deep learning approach. The density maps are then registered to a postmortem MR image and related to an MR-derived geodesic distance map to the tumor core. The relation between the edema outlines visible on T2-FLAIR MRI and the distance to the core is also investigated. Our results suggest that (i) the previously proposed exponential decrease of the tumor cell density with the distance to the core is reasonable but (ii) the edema outlines would not correspond to a cell density iso-contour and (iii) the suggested tumor cell density at these outlines is likely overestimated. These findings highlight the limitations of conventional MRI to derive glioma cell density maps and the need for other initialization methods for reaction-diffusion models to be used in clinical practice.

Arterial Stiffening Moderates the Relationship Between Type-2 Diabetes Mellitus and White Matter Hyperintensity Burden in Older Adults With Mild Cognitive Impairment.

Background: Cerebrovascular dysfunction has been proposed as a possible mechanism underlying cognitive impairment in the context of type 2 diabetes mellitus (DM). Although magnetic resonance imaging (MRI) evidence of cerebrovascular disease, such as white matter hyperintensities (WMH), is often observed in DM, the vascular dynamics underlying this pathology remain unclear. Thus, we assessed the independent and combined effects of DM status and different vascular hemodynamic measures (i.e., systolic, diastolic, and mean arterial blood pressure and pulse pressure index [PPi]) on WMH burden in cognitively unimpaired (CU) older adults and those with mild cognitive impairment (MCI).Methods: 559 older adults (mean age: 72.4 years) from the Alzheimer’s Disease Neuroimaging Initiative were categorized into those with diabetes (DM+; CU = 43, MCI = 34) or without diabetes (DM-; CU = 279; MCI = 203). Participants underwent BP assessment, from which all vascular hemodynamic measures were derived. T2-FLAIR MRI was used to quantify WMH burden. Hierarchical linear regression, adjusting for age, sex, BMI, intracranial volume, CSF amyloid, and APOE ε4 status, examined the independent and interactive effects of DM status and each vascular hemodynamic measure on total WMH burden.Results: The presence of DM (p = 0.046), but not PPi values (p = 0.299), was independently associated with greater WMH burden overall after adjusting for covariates. Analyses stratified by cognitive status revealed a significant DM status x PPi interaction within the MCI group (p = 0.001) such that higher PPi values predicted greater WMH burden in the DM + but not DM- group. No significant interactions were observed in the CU group (all ps > 0.05).Discussion: Results indicate that higher PPi values are positively associated with WMH burden in diabetic older adults with MCI, but not their non-diabetic or CU counterparts. Our findings suggest that arterial stiffening and reduced vascular compliance may have a role in development of cerebrovascular pathology within the context of DM in individuals at risk for future cognitive decline. Given the specificity of these findings to MCI, future exploration of the sensitivity of earlier brain markers of vascular insufficiency (i.e., prior to macrostructural white matter changes) to the effects of DM and arterial stiffness/reduced vascular compliance in CU individuals is warranted.

Automatic Differentiation of Grade I and II Meningioma on Magnetic Resonance Image Using an Asymmetric Convolutional Neural Network

<h3>Purpose/Objective(s)</h3> The grade of meningioma has significant implications on the selection of treatment regimens ranging from observation to surgical resection with adjuvant radiation. For most patients, meningiomas are diagnosed radiologically and grade is not determined unless a surgical procedure is completed. We hypothesize that the use of a 3D convolutional neural network (CNN) architecture with two encoding paths will provide auto-classification of grade I and II meningioma using T1-contrast enhancing (T1-CE) and T2-Fluid attenuated inversion recovery (FLAIR) magnetic resonance (MR) images. <h3>Materials/Methods</h3> Ninety-six consecutive treatment naïve patients with pre-operative T1-CE and T2-FLAIR MR images from 2010 to 2019 were evaluated. The patients underwent surgical resection resulting in a diagnosis of grade I or II meningioma. Histopathology was confirmed by a neuropathologist and neuropathology fellow based on current classification guidelines described in the 2016 World Health Organization (WHO) Bluebook. The delineation of meningiomas was completed on both T1-CE and T2-FLAIR MR with the inclusion of surrounding T2-FLAIR hyperintensity. A novel asymmetric 3D CNN architecture was constructed with two encoding paths based on T1-CE and T2-FLAIR MR. Each path used the same 3 × 3 × 3 kernel with different filters to weight the spatial features of each sequence separately. Final model performance was assessed by 10-fold cross-validation. <h3>Results</h3> Of the 96 patients, 55 (57%) were pathologically classified as grade I and 41 (43%) as grade II meningiomas. Optimization of our model led to a filter weighting of 18:2 between the T1-CE and T2-FLAIR MR image paths with alternative weighting shown in Table 1. Eighty-six (90%) patients were classified correctly and 10 (10%) were misclassified based on their pre-operative MRs with a model sensitivity of 0.85 and specificity of 0.93. Among the misclassified, 4 were grade I, and 6 were grade II. The model was robust to tumor locations and sizes. <h3>Conclusion</h3> A novel asymmetric CNN with two differently weighted encoding paths was developed for successful automated meningioma grade classification. Our model outperforms CNN using a single path for single or multimodal MR-based classification.

Association of regional white matter hyperintensity volumes with cognitive dysfunction and vascular risk factors in patients with amnestic mild cognitive impairment.

AimWhite matter hyperintensities (WMH) obtained by magnetic resonance imaging (MRI) have been reported to promote neurodegeneration and cognitive decline in patients with mild cognitive impairment (MCI). However, little is known about the association between regional WMH (rWMH) and cognitive dysfunction in MCI. We hence investigated the associations between rWMH volumes and cognitive dysfunction in MCI.MethodsThirty‐eight subjects with amnestic MCI were analysed. The volumes of periventricular hyperintensities (PVH) and deep WMH (DWMH) were measured on a T2‐FLAIR MRI using a 3D‐slicer, and regional PVH and DWMH (rPVH and rDWMH) volumes were calculated. The associations of rPVH and rDWMH volumes with cognition and blood levels of various molecules were investigated. Furthermore, rPVH and rDWMH volumes were compared between MCI with vascular risk factors, such as hypertension, diabetes mellitus (DM), and dyslipidemia, and those without these risk factors.ResultsrPVH volume (bilateral cornu frontale, pars parietalis, and cornu occipitale) positively correlated with Trail Making Test‐A/B scores and CysC level, whereas rDWMH volume did not correlate with any of the items. rPVH volumes (right cornu frontale, bilateral pars parietalis and cornu occipitale, and right pars temporalis) and rDWMH volumes (left frontal and parietal lobes) were significantly larger in MCI patients with DM than in those without.ConclusionsPVH volumes (bilateral areas of cornu frontale, pars parietalis, and cornu occipitale) were closely associated with attention and executive dysfunction. Serum CysC level and DM were associated with WMH volume, suggesting that CysC level and DM might be important markers for determining treatment strategies for white matter abnormalities in MCI. Geriatr Gerontol Int 2021; 21: 644–650.

NIMG-33. CHANGES IN MAGNETIC RESONANCE IMAGING AFTER PROTON BOOST THERAPY FOR GLIOBLASTOMA WITH AND WITHOUT TUMOR TREATING FIELDS THERAPY

Abstract BACKGROUND Tumor treating fields (TTFields) are an approved glioblastoma (GBM) treatment modality that demonstrated a significant improved median overall survival in newly diagnosed GBM patients. Data about morphologic changes in serial magnetic resonance imaging (MRI) for patients with a combination therapy of TTFields and proton boost therapy does not exist. METHODS Twenty-two patients were included in this study. All patients were treated with initial tumor resection followed by combined chemo- and radiation therapy. Radiation therapy was performed with 50.0 Gy photons and a proton boost with 10 Gy equivalent (Gy(RBE)). 11 patients were additionally treated with TTFields. RESULTS A new increase in contrast enhancement and/or a progress in the T2 FLAIR hyperintensity was observed in 54.5% (N=12) at 3 months and in 31.8% (N=7) at 6 months. No differences were observed between patients with and without TTFields therapy at 3 months [63.6% (N=7) vs. 45.5% (N=5); P=0.392] and at 6 months [27.3 (N=3) vs. 36.3% (N=4); P=0.647). By the RANO criteria a progressive disease (PD) was observed in 6 patients (27.3%) at 3 months and in 7 patients (31.8%) at 6 months. Pseudoprogression (PP) was observed in in 36.4% (N=8) at months and in 27.3% (N=6) at 6 months. Neither for PD at 3 months [36.4% (N=4) vs. 18.2% (N=2); P=0.338] or at 6 months [36.4% (N=4) vs. 27.3% (N=3); P=0.647), nor for PP at 3 months [45.5% (N=5) vs. 27.2% (N=3); P=0.375] or at 6 months [18.2% (N=2) vs. 36.4% (N=4); P=0.338] differences for patients with and without TTFields therapy were found. CONCLUSION Increased contrast enhancement and/or increased T2 FLAIR MRI hyperintensity after proton boost therapy are common. Furthermore, the rates for new contrast enhancement, PD, and PP after photon therapy with and without additional TTFields therapy are comparable.

Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images

We present the application of limited one-time sampling irregularity map (LOTS-IM): a fully automatic unsupervised approach to extract brain tissue irregularities in magnetic resonance images (MRI), for quantitatively assessing white matter hyperintensities (WMH) of presumed vascular origin, and multiple sclerosis (MS) lesions and their progression. LOTS-IM generates an irregularity map (IM) that represents all voxels as irregularity values with respect to the ones considered ”normal”. Unlike probability values, IM represents both regular and irregular regions in the brain based on the original MRI's texture information. We evaluated and compared the use of IM for WMH and MS lesions segmentation on T2-FLAIR MRI with the state-of-the-art unsupervised lesions’ segmentation method, Lesion Growth Algorithm from the public toolbox Lesion Segmentation Toolbox (LST-LGA), with several well established conventional supervised machine learning schemes and with state-of-the-art supervised deep learning methods for WMH segmentation. In our experiments, LOTS-IM outperformed unsupervised method LST-LGA on WMH segmentation, both in performance and processing speed, thanks to the limited one-time sampling scheme and its implementation on GPU. Our method also outperformed supervised conventional machine learning algorithms (i.e., support vector machine (SVM) and random forest (RF)) and deep learning algorithms (i.e., deep Boltzmann machine (DBM) and convolutional encoder network (CEN)), while yielding comparable results to the convolutional neural network schemes that rank top of the algorithms developed up to date for this purpose (i.e., UResNet and UNet). LOTS-IM also performed well on MS lesions segmentation, performing similar to LST-LGA. On the other hand, the high sensitivity of IM on depicting signal change deems suitable for assessing MS progression, although care must be taken with signal changes not reflective of a true pathology.

The association of sleep-disordered breathing and white matter hyperintensities in heart failure patients.

Heart failure patients often manifest white matter hyperintensites on brain magnetic resonance imaging (MRI). White matter hyperintnsities have also been linked with cognitive problems in patients with heart failure. Sleep disordered breathing may contribute to structural brain changes in heart failure. The purpose of this study was to test the extent to which the apnea hypopnea index is associated with global and regional white matter hyperintensities, and is a moderating factor in the relationship between age and white matter hyperintensites. A total of 28 HF patients [mean age (SD) = 67.89 (5.8)] underwent T1-weighted and T2FLAIR MRI and a home sleep monitoring study. The apnea hypopnea index cut off of 10 was used to compare between higher and lower risks of sleep disordered breathing. Regression analysis was used to test the association between apnea hypopnea index and both global and regional white matter hyperintensities. The interaction term was entered to identify the moderation effect. Apnea hypopnea index was associated with higher regional white matter hyperintensities but not global white matter hyperintensities. There was a significant interaction between the apnea hypopnea index and age, such that older participants with the apnea hypopnea index ≥10 showed greater regional white matter hyperintensities than those with the apnea hypopnea index <10. The results of this preliminary study indicate that a higher apnea hypopnea index is associated with more white matter hyperintensities. The age-related white matter hyperintensities appear to be exacerbated by apnea hypopnea index in our individuals with heart failure. Future studies are needed to further investigate the underlying mechanisms.

REtroSpective Evaluation of Cerebral Tumors (RESECT): A clinical database of pre-operative MRI and intra-operative ultrasound in low-grade glioma surgeries.

The advancement of medical image processing techniques, such as image registration, can effectively help improve the accuracy and efficiency of brain tumor surgeries. However, it is often challenging to validate these techniques with real clinical data due to the rarity of such publicly available repositories. Pre-operative magnetic resonance images (MRI), and intra-operative ultrasound (US) scans were acquired from 23 patients with low-grade gliomas who underwent surgeries at St. Olavs University Hospital between 2011 and 2016. Each patient was scanned by Gadolinium-enhanced T1w and T2-FLAIR MRI protocols to reveal the anatomy and pathology, and series of B-mode ultrasound images were obtained before, during, and after tumor resection to track the surgical progress and tissue deformation. Retrospectively, corresponding anatomical landmarks were identified across US images of different surgical stages, and between MRI and US, and can be used to validate image registration algorithms. Quality of landmark identification was assessed with intra- and inter-rater variability. In addition to co-registered MRIs, each series of US scans are provided as a reconstructed 3D volume. All images are accessible in MINC2 and NIFTI formats, and the anatomical landmarks were annotated in MNI tag files. Both the imaging data and the corresponding landmarks are available online as the RESECT database at https://archive.norstore.no (search for "RESECT"). The proposed database provides real high-quality multi-modal clinical data to validate and compare image registration algorithms that can potentially benefit the accuracy and efficiency of brain tumor resection. Furthermore, the database can also be used to test other image processing methods and neuro-navigation software platforms.

Low-Grade Glioma Segmentation Based on CNN with Fully Connected CRF.

This work proposed a novel automatic three-dimensional (3D) magnetic resonance imaging (MRI) segmentation method which would be widely used in the clinical diagnosis of the most common and aggressive brain tumor, namely, glioma. The method combined a multipathway convolutional neural network (CNN) and fully connected conditional random field (CRF). Firstly, 3D information was introduced into the CNN which makes more accurate recognition of glioma with low contrast. Then, fully connected CRF was added as a postprocessing step which purposed more delicate delineation of glioma boundary. The method was applied to T2flair MRI images of 160 low-grade glioma patients. With 59 cases of data training and manual segmentation as the ground truth, the Dice similarity coefficient (DSC) of our method was 0.85 for the test set of 101 MRI images. The results of our method were better than those of another state-of-the-art CNN method, which gained the DSC of 0.76 for the same dataset. It proved that our method could produce better results for the segmentation of low-grade gliomas.

Brain White Matter Hyperintensities Segmentation of T2-FLAIR MRI Using L*a*b* Color Transformation and K-Neasrest Neighbor Means Classifier

T2-플레어 MRI 영상에서 뇌백질 고강도(White Matter Hyperintensity, WMH)로는 알츠하이머 또는 혈관성치매 또는 발작의 위험을 나타낸다. 기존의 많은 연구에서 뇌백질 고강도는 혈관성 질병의 증대된 위험을 예측할 수 있는 것으로 알려져 있다. WMH는 위험도를 식별하는 새로운 정량적 중간마커로 간주되고 있다. 본 논문에서는 T2 플레어 MRI로부터 WMH를 추출하기 위한 방법을 제안한다. 본 논문의 방법은 두 개의 분할단계로 구성되는데, 첫째, 형태론적 기술과 k-means 집단화를 이용하여 입력영상에서 두개골로부터 뇌질을 분리시킨다. 둘째, 흑백 뇌질 영상은 L*a*b* 컬러 영상으로 변환되고, 다음 k-nearest neighbor means 분류 알고리듬을 통해 WMH, 비-WMH, 그리고 배경 영역으로 분할된다. 실제 T2 플레어 MRI 영상에 대한 실험을 통해 높은 recall,과 precision을 갖는 좋은 성능을 보였으며, Graph Cut 알고리듬에 비하여 안정적인 성능을 보였다.