Fluid-attenuated Inversion Recovery Research Articles

Artificial intelligence for volumetric measurement of cerebral white matter hyperintensities on thick-slice fluid-attenuated inversion recovery (FLAIR) magnetic resonance images from multiple centers

We aimed to develop a new artificial intelligence software that can automatically extract and measure the volume of white matter hyperintensities (WMHs) in head magnetic resonance imaging (MRI) using only thick-slice fluid-attenuated inversion recovery (FLAIR) sequences from multiple centers. We enrolled 1092 participants in Japan, comprising the thick-slice Private Dataset. Based on 207 randomly selected participants, neuroradiologists annotated WMHs using predefined guidelines. The annotated images of participants were divided into training (n = 138) and test (n = 69) datasets. The WMH segmentation model comprised a U-Net ensemble and was trained using the Private Dataset. Two other models were trained for validation using either both thin- and thick-slice MRI datasets or the thin-slice dataset alone. The voxel-wise Dice similarity coefficient (DSC) was used as the evaluation metric. The model trained using only thick-slice MRI showed a DSC of 0.820 for the test dataset, which is comparable to the accuracy of human readers. The model trained with the additional thin-slice dataset showed only a slightly improved DSC of 0.822. This automatic WMH segmentation model comprising a U-Net ensemble trained on a thick-slice FLAIR MRI dataset is a promising new method. Despite some limitations, this model may be applicable in clinical practice.

A radiomics-based nomogram may be useful for predicting telomerase reverse transcriptase promoter mutation status in adult glioblastoma.

As a crucial diagnostic and prognostic biomarker, telomerase reverse transcriptase (TERT) promoter mutation holds immense significance for personalized treatment of patients with glioblastoma (GBM). In this study, we developed a radiomics nomogram to determine the TERT promoter mutation status and assessed its prognostic efficacy in GBM patients. The study retrospectively included 145 GBM patients. A comprehensive set of 3736 radiomics features was extracted from preoperative magnetic resonance imaging, including T2-weighted imaging, T1-weighted imaging (T1WI), contrast-enhanced T1WI, and fluid-attenuated inversion recovery. The construction of the radiomics model was based on integrating the radiomics signature (rad-score)with clinical features. Receiver-operating characteristic curve analysis was employed to evaluate the discriminative ability of the prediction model, and the risk score was used to stratify patient outcomes. The least absolute shrinkage and selection operator classifier identified 10 robust features for constructing the prediction model, and the radiomics nomogram exhibited excellent performance in predicting TERT promoter mutation status, with area under the curve values of.906 (95% confidence interval [CI]:.850-.963) and.899 (95% CI:.708-.966) in the training and validation sets, respectively. The clinical utility of the radiomics nomogram is further supported by calibration curve and decision curve analyses. Additionally, the radiomics nomogram effectively stratified GBM patients with significantly different prognoses (HR=1.767, p=.019). The radiomics nomogram holds promise as a modality for evaluating TERT promoter mutations and prognostic outcomes in patients with GBM.

Quantifying chronic lesion expansion in multiple sclerosis: Exploring imaging markers for longitudinal assessment

ObjectivesGradual expansion of multiple sclerosis lesions over time is known to have a significant impact on disease progression. However, accurately quantifying the volume changes in chronic lesions presents challenges due to their slow rate of progression and the need for longitudinal segmentation. Our study addresses this by estimating the expansion of chronic lesions using data collected over a 1–2 year period and exploring imaging markers that do not require longitudinal lesion segmentation. MethodsPre- and post-gadolinium 3D-T1, 3D FLAIR and diffusion tensor images were acquired from 42 patients with MS. Lesion expansion, stratified by the severity of tissue damage as measured by mean diffusivity change, was analysed between baseline and 48 months (Progressive Volume/Severity Index, PVSI). Central brain atrophy (CBA) and the degree of tissue loss inside chronic lesions (measured by the change of T1 intensity and mean diffusivity (MD)) were used as surrogate markers. ResultsCBA measured after 2 years of follow-up estimated lesion expansion at 4 years with a high degree of accuracy (r = 0.82, p < 0.001, ROC area under the curve 0.92, sensitivity of 94 %, specificity of 85 %). Increased MD within chronic lesions measured over 2 years was strongly associated with future expansion (r = 0.77, p < 0.001, ROC area under the curve 0.87, sensitivity of 81 % and specificity of 81 %). In contrast, change in lesion T1 hypointensity poorly explained future PVSI (best sensitivity and specificity 60 % and 59 % respectively). InterpretationCBA and, to a lesser extent, the change in MD within chronic MS lesions, measured over a period of 2 years, can provide a reliable and sensitive estimate of the extent and severity of chronic lesion expansion.

Reversible Cytotoxic Edema in Patients with COVID-19 Associated Encephalitis Presenting Status Epilepticus

Coronavirus disease 2019 (COVID-19) is a serious infectious disease with multisystem alteration including neurological complications. COVID-19 associated encephalitis is a potentially fatal viral infection of the brain. Diffusion-weighted images (DWI) are a useful evaluation modality of cytotoxic edema in patients with encephalitis. We report on the reversible DWI change in a patient with COVID-19 associated encephalitis, who had diffused cytotoxic edema in the affected temporal lobe and accompanied status epilepticus. Sequential imaging showed that the cytotoxic edema in DWI confirmed recovery to normal after 12 days in the presence of cortical edema in fluid-attenuated inversion recovery image after aggressive neurocritical management. Thus, prompt, proper management is indispensable during the acute period and DWI may be a valuable tool for reflecting the clinical course of COVID-19 associated encephalitis.

Leveraging radiomics and machine learning to differentiate radiation necrosis from recurrence in patients with brain metastases.

Radiation necrosis (RN) can be difficult to radiographically discern from tumor progression after stereotactic radiosurgery (SRS). The objective of this study was to investigate the utility of radiomics and machine learning (ML) to differentiate RN from recurrence in patients with brain metastases treated with SRS. Patients with brain metastases treated with SRS who developed either RN or tumor reccurence were retrospectively identified. Image preprocessing and radiomic feature extraction were performed using ANTsPy and PyRadiomics, yielding 105 features from MRI T1-weighted post-contrast (T1c), T2, and fluid-attenuated inversion recovery (FLAIR) images. Univariate analysis assessed significance of individual features. Multivariable analysis employed various classifiers on features identified as most discriminative through feature selection. ML models were evaluated through cross-validation, selecting the best model based on area under the receiver operating characteristic (ROC) curve (AUC). Specificity, sensitivity, and F1 score were computed. Sixty-six lesions from 55 patients were identified. On univariate analysis, 27 features from the T1c sequence were statistically significant, while no features were significant from the T2 or FLAIR sequences. For clinical variables, only immunotherapy use after SRS was significant. Multivariable analysis of features from the T1c sequence yielded an AUC of 76.2% (standard deviation [SD] ± 12.7%), with specificity and sensitivity of 75.5% (± 13.4%) and 62.3% (± 19.6%) in differentiating radionecrosis from recurrence. Radiomics with ML may assist the diagnostic ability of distinguishing RN from tumor recurrence after SRS. Further work is needed to validate this in a larger multi-institutional cohort and prospectively evaluate it's utility in patient care.

Inferior Frontal Sulcal Hyperintensities on Brain MRI Are Associated with Amyloid Positivity beyond Age-Results from the Multicentre Observational DELCODE Study.

Inferior frontal sulcal hyperintensities (IFSHs) on fluid-attenuated inversion recovery (FLAIR) sequences have been proposed to be indicative of glymphatic dysfunction. Replication studies in large and diverse samples are nonetheless needed to confirm them as an imaging biomarker. We investigated whether IFSHs were tied to Alzheimer's disease (AD) pathology and cognitive performance. We used data from 361 participants along the AD continuum, who were enrolled in the multicentre DELCODE study. The IFSHs were rated visually based on FLAIR magnetic resonance imaging. We performed ordinal regression to examine the relationship between the IFSHs and cerebrospinal fluid-derived amyloid positivity and tau positivity (Aβ42/40 ratio ≤ 0.08; pTau181 ≥ 73.65 pg/mL) and linear regression to examine the relationship between cognitive performance (i.e., Mini-Mental State Examination and global cognitive and domain-specific performance) and the IFSHs. We controlled the models for age, sex, years of education, and history of hypertension. The IFSH scores were higher in those participants with amyloid positivity (OR: 1.95, 95% CI: 1.05-3.59) but not tau positivity (OR: 1.12, 95% CI: 0.57-2.18). The IFSH scores were higher in older participants (OR: 1.05, 95% CI: 1.00-1.10) and lower in males compared to females (OR: 0.44, 95% CI: 0.26-0.76). We did not find sufficient evidence linking the IFSH scores with cognitive performance after correcting for demographics and AD biomarker positivity. IFSHs may reflect the aberrant accumulation of amyloid β beyond age.

Predicting glioblastoma recurrence using multiparametric MR imaging of non-enhancing peritumoral regions at baseline

BackgroundTo assess the feasibility of multiparametric magnetic resonance imaging in predicting tumor recurrence in nonenhancing peritumoral regions in patients with glioblastoma at baseline. MethodsFifty-eight patients with recurrent glioblastoma underwent multiparametric magnetic resonance imaging, including T2-weighted fluid-attenuated inversion recovery, diffusion-weighted imaging, and dynamic susceptibility contrast perfusion-weighted imaging. Nonenhancing peritumoral regions with glioblastoma recurrence were identified by coregistering preoperative and post-recurrent magnetic resonance images. Regions of interest were placed in nonenhancing peritumoral regions with and without tumor recurrence to calculate the apparent diffusion coefficient value, and relative ratios of T2-weighted fluid-attenuated inversion recovery signal intensity, apparent diffusion coefficient, and cerebral blood volume values. ResultsSignificant lower relative T2-weighted fluid-attenuated inversion recovery signal intensity, apparent diffusion coefficient, and relative apparent diffusion coefficient but higher relative cerebral blood volume values were found in the nonenhancing peritumoral regions with tumor recurrence than without recurrence (all P < 0.05). The threshold values ≥ 0.89 for relative cerebral blood volume provide the optimal performance for predicting the nonenhancing peritumoral regions with future tumor recurrence, with the sensitivity, specificity, and accuracy of 84.7%, 83.6%, and 85.8%, respectively. The combination of relative T2-weighted fluid-attenuated inversion recovery signal intensity, apparent diffusion coefficient, and relative cerebral blood volume can provide better predictive performance than relative cerebral blood volume (P = 0.015). ConclusionThe combined use of T2-weighted fluid-attenuated inversion recovery, diffusion-weighted imaging, and dynamic susceptibility contrast perfusion-weighted imaging can effectively estimate the risk of future tumor recurrence at baseline.

Spontaneous intracranial hypotension: Exploring the viability of non-contrast FLAIR as a substitute for contrast-enhanced T1WI in assessing pachymeningeal thickening.

To avoid contrast administration in spontaneous intracranial hypotension (SIH), some studies suggest accepting diffuse pachymeningeal hyperintensity (DPMH) on non-contrast fluid-attenuated inversion recovery (FLAIR) as an equivalent sign to diffuse pachymeningeal enhancement (DPME) on contrast-enhanced T1WI (T1ce), despite lacking thoroughperformance metrics. This study aimed to comprehensively explore its feasibility. In this single-center retrospective study, between April 2021 and November 2023, brain MRI examinations of 43 patients clinically diagnosed with SIH were assessed using 1.5 and 3.0 Tesla MRI scanners. Two radiologists independentlyassessed the presence or absence of DPMH on FLAIR and DPME on T1ce, with T1ce serving as a gold-standard for pachymeningeal thickening. The contribution of the subdural fluid collections to DPMH was investigated with quantitative measurements. Using Cohen's kappa statistics, interobserver agreement was assessed. In 39 out of 43 patients (90.7%), pachymeningeal thickening was observed on T1ce. FLAIR sequence produced an accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 72.1%, 71.8%, 75.0%, 96.6%, and 21.4% respectively, for determining pachymeningeal thickening. FLAIR identified pachymeningeal thickening in 28 cases; however, among these, 21 cases (75%) revealed that the pachymeningeal hyperintense signal was influenced by subdural fluid collections. False-negative rate for FLAIR was 28.2% (11/39). The lack of complete correlation between FLAIR and T1ce in identifying pachymeningeal thickening highlights the need for caution in removing contrast agent administration from the MRI protocol of SIH patients, as it reveals a major criterion (i.e., pachymeningeal enhancement) of Bern score.

Endovascular thrombectomy in wake-up stroke guided by arterial spin-labeling and fluid-attenuated inversion recovery versus diffusion-weighted imaging mismatch on MRI.

This purpose of this study is to investigate the effectiveness and safety of utilizing the arterial spin-labeling (ASL) combined with diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) combined with DWI double mismatch in the endovascular treatment of patients diagnosed with wake-up stroke (WUS). In this single-center trial, patients diagnosed with WUS underwent thrombectomy if acute ischemic lesions were observed on DWI indicating large precerebral circulation occlusion. Patients with no significant parenchymal hypersignal on FLAIR and ASL imaging showing a hypoperfusion tissue to infarct core volume ratio of at least 1.2 were included. The participants were divided into groups receiving endovascular thrombectomy plus medical therapy or medical therapy alone, based on their subjective preference. Functional outcomes were assessed using the ordinal score on the modified Rankin scale (mRs) at 90 days, along with the rate of functional independence. In this study, a total of 77 patients were included, comprising 38 patients in the endovascular therapy group and 39 patients in the medical therapy group. The endovascular therapy group exhibited more favorable changes in the distribution of functional prognosis measured by mRs at 90 days, compared to the medical therapy group (adjusted common odds ratio, 3.25; 95% CI, 1.03 to 10.26; P < 0.01). Additionally, the endovascular therapy group had a higher proportion of patients achieving functional independence (odds ratio, 4.0; 95% CI, 1.36 to 11.81; P < 0.01). Importantly, there were no significant differences observed in the incidence of intracranial hemorrhage or mortality rates between the two groups. Guided by the ASL-DWI and FLAIR-DWI double mismatch, endovascular thrombectomy combined with standard medical treatment appears to yield superior functional outcomes in patients with WUS and large vessel occlusion compared to standard medical treatment alone.

FLAMES overlaying anti-N-methyl-D-aspartate receptor encephalitis: a case report and literature review

BackgroundIn recent years, simultaneous or sequential occurrence of MOG antibody disease and anti-NMDAR encephalitis in the same patient has been reported with increasing frequency. Scholars refer to the overlapping occurrence of these two disorders as MOG antibody disease and anti-NMDAR encephalitis overlap syndrome (MNOS). Cortical T2-weighted fluid-attenuated inversion recovery (FLAIR) -hyperintense lesions in anti-MOG-associated encephalitis with seizures (FLAMES) is a rare clinical phenotype of MOGAD in which cortical FLAIR high-signal lesions are unilateral, with little spread to the cortex and meninges bilaterally. Although cases of FLAMES have been consistently reported. However, to our knowledge, such cases of FLAMES combined with NMDARE are rare.Case presentationHere, we describe a case of FLAMES combined with anti-NMDARE. The patient was a young male, 29 years old, admitted to our hospital with isolated seizures, whose MRI showed unilateral thalamic and bilateral frontal and parietal leptomeningeal involvement. Since we were unaware of the possibility of bilateral meningo-cortical MOGAD manifestations, the case was initially diagnosed as viral encephalitis and was given antiviral therapy. The diagnosis was not clarified until anti-NMDAR-IgG and MOG-IgG positivity was detected in the cerebrospinal fluid and serum. The patient was then treated with high-dose corticosteroids and his symptoms responded well to the steroids. Therefore, this case expands the clinical spectrum of MNOS overlap syndrome. In addition, we describe the clinical features of MNOS by summarizing the existing literature and exploring the possible mechanisms of its immune response.ConclusionsOur case serves as a reminder to clinicians that when patients present with atypical clinical manifestations such as seizures, consideration should be given to MNOS and conduct testing for various relevant autoantibodies (including MOG abs) and viruses in both serum and cerebrospinal fluid, as it is easy to misdiagnose the disease as other CNS diseases, such as viral meningoencephalitis. This syndrome exhibits a high responsiveness to steroids, highlighting the critical importance of recognizing the clinical and neuroimaging features of this overlap syndrome for prompt diagnosis and treatment. Furthermore, it enriches the disease spectrum of MNOS.

Simulation of acquisition shifts in T2 weighted fluid-attenuated inversion recovery magnetic resonance images to stress test artificial intelligence segmentation networks.

To provide a simulation framework for routine neuroimaging test data, which allows for "stress testing" of deep segmentation networks against acquisition shifts that commonly occur in clinical practice for T2 weighted (T2w) fluid-attenuated inversion recovery magnetic resonance imaging protocols. The approach simulates "acquisition shift derivatives" of MR images based on MR signal equations. Experiments comprise the validation of the simulated images by real MR scans and example stress tests on state-of-the-art multiple sclerosis lesion segmentation networks to explore a generic model function to describe the F1 score in dependence of the contrast-affecting sequence parameters echo time (TE) and inversion time (TI). The differences between real and simulated images range up to 19% in gray and white matter for extreme parameter settings. For the segmentation networks under test, the F1 score dependency on TE and TI can be well described by quadratic model functions (). The coefficients of the model functions indicate that changes of TE have more influence on the model performance than TI. We show that these deviations are in the range of values as may be caused by erroneous or individual differences in relaxation times as described by literature. The coefficients of the F1 model function allow for a quantitative comparison of the influences of TE and TI. Limitations arise mainly from tissues with a low baseline signal (like cerebrospinal fluid) and when the protocol contains contrast-affecting measures that cannot be modeled due to missing information in the DICOM header.

Radiomics for predicting MGMT status in cerebral glioblastoma: comparison of different MRI sequences.

Using radiomics to predict O6-methylguanine-DNA methyltransferase promoter methylation status in patients with newly diagnosed glioblastoma and compare the performances of different MRI sequences. Preoperative MRI scans from 215 patients were included in this retrospective study. After image preprocessing and feature extraction, two kinds of machine-learning models were established and compared for their performances. One kind was established using all MRI sequences (T1-weighted image, T2-weighted image, contrast enhancement, fluid-attenuated inversion recovery, DWI_b_high, DWI_b_low and apparent diffusion coefficient), and the other kind was based on single MRI sequence as listed above. For the machine-learning model based on all sequences, a total of seven radiomic features were selected with the Maximum Relevance and Minimum Redundancy algorithm. The predictive accuracy was 0.993 and 0.750 in the training and validation sets, respectively, and the area under curves were 1.000 and 0.754 in the two sets, respectively. For the machine-learning model based on single sequence, the numbers of selected features were 8, 10, 10, 13, 9, 7 and 6 for T1-weighted image, T2-weighted image, contrast enhancement, fluid-attenuated inversion recovery, DWI_b_high, DWI_b_low and apparent diffusion coefficient, respectively, with predictive accuracies of 0.797-1.000 and 0.583-0.694 in the training and validation sets, respectively, and the area under curves of 0.874-1.000 and 0.538-0.697 in the two sets, respectively. Specifically, T1-weighted image-based model performed best, while contrast enhancement-based model performed worst in the independent validation set. The machine-learning models based on seven different single MRI sequences performed differently in predicting O6-methylguanine-DNA methyltransferase status in glioblastoma, while the machine-learning model based on the combination of all sequences performed best.

Brain MRI sequence and view plane identification using deep learning.

Brain magnetic resonance imaging (MRI) scans are available in a wide variety of sequences, view planes, and magnet strengths. A necessary preprocessing step for any automated diagnosis is to identify the MRI sequence, view plane, and magnet strength of the acquired image. Automatic identification of the MRI sequence can be useful in labeling massive online datasets used by data scientists in the design and development of computer aided diagnosis (CAD) tools. This paper presents a deep learning (DL) approach for brain MRI sequence and view plane identification using scans of different data types as input. A 12-class classification system is presented for commonly used MRI scans, including T1, T2-weighted, proton density (PD), fluid attenuated inversion recovery (FLAIR) sequences in axial, coronal and sagittal view planes. Multiple online publicly available datasets have been used to train the system, with multiple infrastructures. MobileNet-v2 offers an adequate performance accuracy of 99.76% with unprocessed MRI scans and a comparable accuracy with skull-stripped scans and has been deployed in a tool for public use. The tool has been tested on unseen data from online and hospital sources with a satisfactory performance accuracy of 99.84 and 86.49%, respectively.

Deep learning for discrimination of active and inactive lesions in multiple sclerosis using non-contrast FLAIR MRI: A multicenter study

BackgroundWithin the domain of multiple sclerosis (MS), the precise discrimination between active and inactive lesions bears immense significance. Active lesions are enhanced on T1-weighted MRI images after administration of gadolinium-based contrast agents, which brings about associated complexities. This study investigates the potential of deep learning to differentiate between active and inactive lesions in MS using non-contrast FLAIR-type MRI data, presenting a non-invasive alternative to conventional gadolinium-based MRI methods. MethodsThe dataset encompasses 9097 lesion images collected from 130 MS patients across four distinct imaging centers, with post-contrast T1-weighted images as the benchmark reference. We initially identified and labeled the lesions and carefully selected corresponding regions of interest (ROIs). These ROIs were employed as inputs for a convolutional neural network (CNN) to predict lesion status. Also, transfer learning was utilized, incorporating 12 pre-trained CNN models. Subsequently, an ensemble technique was applied to 3 of best models, followed by a systematic comparison of the results. ResultsThrough a 5-fold cross-validation, our custom designed network exhibited an average accuracy of 85 %, a sensitivity of 95 %, a specificity of 75 %, and an AUC value of 0.90. Among the pre-trained models, ResNet50 emerged as the most effective, achieving a specificity of 58 %, an accuracy of 75 %, a sensitivity of 91 %, and an AUC value of 0.81. Our comprehensive evaluations encompassed the receiver operating characteristic curve, precision-recall curve, and confusion matrix analyses. ConclusionThe findings underscore the efficacy of the proposed CNN, trained on FLAIR MRI data ROIs, in accurately discerning active and inactive lesions without reliance on contrast agents. Our multicenter study of 130 patients with diverse imaging devices outperforms the other single-center studies, achieving superior sensitivity and specificity. Unlike studies using multiple modalities, our exclusive use of FLAIR images streamlines the process, and our streamlined approach, excluding conventional pre-processing, demonstrates efficiency. The external validation conducted on diverse datasets, coupled with the analysis of dilated masks, underscores the adaptability and efficacy of our custom CNN model in discerning between active and inactive lesions.

Radiomic- and dosiomic-based clustering development for radio-induced neurotoxicity in pediatric medulloblastoma

BackgroundTexture analysis extracts many quantitative image features, offering a valuable, cost-effective, and non-invasive approach for individual medicine. Furthermore, multimodal machine learning could have a large impact for precision medicine, as texture biomarkers can underlie tissue microstructure. This study aims to investigate imaging-based biomarkers of radio-induced neurotoxicity in pediatric patients with metastatic medulloblastoma, using radiomic and dosiomic analysis.MethodsThis single-center study retrospectively enrolled children diagnosed with metastatic medulloblastoma (MB) and treated with hyperfractionated craniospinal irradiation (CSI). Histological confirmation of medulloblastoma and baseline follow-up magnetic resonance imaging (MRI) were mandatory. Treatment involved helical tomotherapy (HT) delivering a dose of 39 Gray (Gy) to brain and spinal axis and a posterior fossa boost up to 60 Gy. Clinical outcomes, such as local and distant brain control and neurotoxicity, were recorded. Radiomic and dosiomic features were extracted from tumor regions on T1, T2, FLAIR (fluid-attenuated inversion recovery) MRI-maps, and radiotherapy dose distribution. Different machine learning feature selection and reduction approaches were performed for supervised and unsupervised clustering.ResultsForty-eight metastatic medulloblastoma patients (29 males and 19 females) with a mean age of 12 ± 6 years were enrolled. For each patient, 332 features were extracted. Greater level of abstraction of input data by combining selection of most performing features and dimensionality reduction returns the best performance. The resulting one-component radiomic signature yielded an accuracy of 0.73 with sensitivity, specificity, and precision of 0.83, 0.64, and 0.68, respectively.ConclusionsMachine learning radiomic-dosiomic approach effectively stratified pediatric medulloblastoma patients who experienced radio-induced neurotoxicity. Strategy needs further validation in external dataset for its potential clinical use in ab initio management paradigms of medulloblastoma.

The central vein sign in the diagnosis of multiple sclerosis

Objective: to determine the specificity and sensitivity of the central vein sign (CVS) for the diagnosis of multiple sclerosis (MS). Material and methods. We analyzed 76 patients. The main group consisted of 40 patients with a confirmed diagnosis of MS according to the McDonald criteria, 2017. The comparison group included 20 patients with migraine and 16 patients with cerebral microangiopathy. All patients underwent a standardized MRI scan of the brain, including 3D FLAIR and SWI modes. The total number of T2/FLAIR hyperintense lesions in the brain and the number of lesions with CVS were calculated. Results. In the group of MS patients, the total and relative number of lesions with CVS was higher than in the comparison group (p&lt;0.001). The 40% lesion rule had a sensitivity of 97.5% and a specificity of 94.4%. The sensitivity of the 3-lesion rule was 92.5% and the specificity 66.7%. The use of the 5-lesion rule had a sensitivity of 75% and a specificity of 83.7%. Conclusion. The data obtained indicate a significant diagnostic role for SCV in MS. The use of the 5-lesion rule provides high sensitivity and specificity with relative ease of use.

Recurrent demyelination attacks after BNT162b2 vaccination: Two case reports and literature review

We describe two cases with recurrent demyelinating attacks following BioNTech BNT162b2 immunization. No reports of any recurring demyelinating attack cases connected to COVID-19 immunization. Case-1: A 37-year-old male patient was admitted due to diplopia and ptosis. Neurological examination showed isolated oculomotor cranial paralysis on the right side. The second dose of BNT162b2 was given 10 days ago. On T2- and fluid-attenuated inversion recovery (FLAIR)-weighted magnetic resonance imaging (MRI), hyperintense lesions were seen in the pons on T1, with no evidence of contrast enhancement. We diagnosed the patient with central pontine myelinolysis associated with BNT162b2. Six months later after the first attack, a new lesion appeared in the same region. Case-2: He applied to the hospital at the age of 57 years, complaining of numbness in his hands and feet, confusion, and cooperation disorder. During the neurological assessment, apathy, cooperation, and orienting disorders were found. Hyperintense lesions were seen in both hemispheres, with cortico-subcortical localization on MRI. The patient received the BNT162b2 two weeks ago. After the initial attack six months ago, new clinical signs and an increase in demyelinating lesions were found. Despite early corticosteroid treatment, BNT162b2 immunization may be associated with repeated demyelination attacks. In patients with diffusion restriction on MRI, we might suggest using corticosteroid therapy for approximately one year, a lot longer than the literatures suggested.

DeepFLAIR: A neural network approach to mitigate signal and contrast loss in temporal lobes at 7 Tesla FLAIR images

Background and purposeHigher magnetic field strength introduces stronger magnetic field inhomogeneities in the brain, especially within temporal lobes, leading to image artifacts. Particularly, T2-weighted fluid-attenuated inversion recovery (FLAIR) images can be affected by these artifacts. Here, we aimed to improve the FLAIR image quality in temporal lobe regions through image processing of multiple contrast images via machine learning using a neural network. MethodsThirteen drug-resistant MR-negative epilepsy patients (age 29.2 ± 9.4y, 5 females) were scanned on a 7 T MRI scanner. Magnetization-prepared (MP2RAGE) and saturation-prepared with 2 rapid gradient echoes, multi-echo gradient echo with four echo times, and the FLAIR sequence were acquired. A voxel-wise neural network was trained on extratemporal-lobe voxels from the acquired structural scans to generate a new FLAIR-like image (i.e., deepFLAIR) with reduced temporal lobe inhomogeneities. The deepFLAIR was evaluated in temporal lobes through signal-to-noise (SNR), contrast-to-noise (CNR) ratio, the sharpness of the gray-white matter boundary and joint-histogram analysis. Saliency mapping demonstrated the importance of each input image per voxel. ResultsSNR and CNR in both gray and white matter were significantly increased (p < 0.05) in the deepFLAIR's temporal ROIs, compared to the FLAIR. The gray-white matter boundary sharpness was either preserved or improved in 10/13 right-sided temporal regions and was found significantly increased in the ROIs. Multiple image contrasts were influential for the deepFLAIR reconstruction with the MP2RAGE second inversion image being the most important. ConclusionsThe deepFLAIR network showed promise to restore the FLAIR signal and reduce contrast attenuation in temporal lobe areas. This may yield a valuable tool, especially when artifact-free FLAIR images are not available.

Comparison of MRI findings of hypothalamic-optic chiasmatic gliomas and craniopharyngiomas.

Differential diagnosis of hypothalamic-optic chiasmatic gliomas (HOCGs) and craniopharyngiomas on magnetic resonance imaging (MRI) can be quite challenging. To compare the MRI features of HOCGs and cranipharyngiomas. Patients diagnosed with HOCG or craniopharyngioma in histopathological evaluation between 2012 and 2022 and who underwent preoperative contrast-enhanced brain MRI were included. Various MRI features were retrospectively evaluated for each lesion: T2-weighted imaging and fluid attenuation inversion recovery hyperintensity, calcification, cystic change, T1-weighted (T1W) imaging hyperintensity of the cystic component, hemorrhage, involvement of sellar, suprasellar or other adjacent structures, lobulated appearance, presence of hydrocephalus, and contrast enhancement pattern. Apparent diffusion coefficient (ADC) values were also evaluated and compared. Among 38 patients included, 13 (34%) had HOCG and 25 (66%) had craniopharyngioma. Craniopharyngiomas had a significantly higher rate of cystic changes, calcification, and T1W imaging hyperintensity of the cystic component than HOCGs (P <0.05). Of HOCGs, 92% had chiasm involvement, 23% had optic nerve involvement, and 31% had brain stem involvement. On the other hand, chiasm involvement was observed in 8% of craniopharyngiomas, but none had optic nerve and/or brain stem involvement (P <0.05). While 62% (8/13) of HOCGs had diffuse homogeneous enhancement, 80% (20/25) of craniopharyngiomas had a diffuse heterogeneous enhancement pattern. Mean ADC values were significantly higher in craniopharyngiomas compared to HOCGs (2.1 vs. 1.6 ×10-3mm2/s, P <0.05). Although some neuroimaging findings may overlap, features such as presence of cyst and calcification, brain stem and optic pathway involvement, different enhancement patterns, and ADC values may be helpful in the differential diagnosis of HOCGs and craniopharyngiomas.

Multi-contrast echo-planar imaging sequence (Echo-planar imaging mix) in clinical situations demanding faster MRI-brain scans.

The excellent resolution offered by magnetic resonance imaging (MRI) has a trade-off in the form of scan duration. The purpose of the present study was to assess the clinical utility of echo-planar imaging mix (EPIMix), an echo-planar imaging-based MRI sequence for the brain with a short acquisition time. This was a retrospective observational study of 50 patients, who could benefit from faster MRI brain scans. The T1, T2, fluid attenuated inversion recovery, diffusion-weighted imaging (DWI), and T2*/susceptibility-weighted imaging sequences were acquired, conventionally and with EPIMix. Conventional and EPIMix images were assessed by two radiologists for overall quality, motion, and susceptibility artifacts and scored on a Likert scale. The scores given for conventional and EPIMix images were compared. The diagnostic performance of EPIMix was also assessed by the ability to detect clinically relevant findings. The acquisition time for conventional MRI was 11 min and 45 s and for EPIMix 1 min and 15 s. All EPIMix images were sufficient for diagnostic use. On assessment of the diagnostic performance, it was excellent for ischemic and hemorrhagic strokes. Smaller lesions, lesions adjacent to bone, and post-operative tumors were difficult to identify. Moderate to perfect agreement (Kappa values 0.41-1) was seen between radiologists for all categories except skull base, calvarial, and orbital lesions. Image quality, artifact assessment showed excellent interobserver agreement (>90%) for the scores. All EPIMix images showed reduced motion artifacts. The EPIMix-DWI was comparable to conventional-DWI in terms of quality and artifacts. The remaining sequences showed reduced quality and increased susceptibility. The EPIMix has a significantly reduced acquisition time than conventional MRI and could be used instead of conventional MRI in situations demanding faster scans such as suspected acute ischemic or hemorrhagic stroke. In other clinical scenarios, it could help tailor the MRI examination for each patient.