FLAIR Sequences Research Articles

Automatic segmentation of demyelination lesions in multiple sclerosis

Aim – To evaluate the effectiveness of the YOLOv8 algorithm for automatic segmentation of demyelination lesions in various locations in patients with multiple sclerosis. Material and methods. The study included 120 patients with a clinically confirmed diagnosis of multiple sclerosis who underwent contrast-enhanced MRI. MRI data from patients with different types of disease progression were analyzed. T1-weighted, T2-weighted, and FLAIR sequences were used for analysis. The YOLOv8 algorithm was adapted for medical imaging and trained on manually annotated MRI scans. Model performance was evaluated using precision, recall, and F1-Score metrics. Results. The YOLOv8 model demonstrated high segmentation performance with a precision of 0,79, recall of 00,73, and F1-Score of 0.65. The model effectively identified demyelination lesions in various locations typical for multiple sclerosis. However, there remains a need to improve recall to minimize missed lesions. Testing on independent data confirmed the stability of the model’s results. Conclusion. The YOLOv8 algorithm shows significant potential for automatic segmentation of demyelination lesions in multiple sclerosis patients. This method could be successfully implemented in clinical practice, enabling faster diagnosis and improved monitoring of disease progression. Further optimization of the model, through data augmentation techniques and hybrid architectures, may enhance both segmentation accuracy and recall.

T2/FLAIR mismatch and diffusion restriction as novel pathophysiological markers in MRI evaluation of central tegmental tract hyperintensity in pediatric patients.

Central tegmental tract hyperintensity (CTTH) on T2-weighted imaging is an uncommon neuroimaging finding in pediatric patients with unclear clinical significance. CTTH may represent either a physiological or pathological process. This study evaluates the relationship between CTTH and MRI sequences (FLAIR, DWI) to explore its diagnostic value. We retrospectively analyzed 3462 pediatric brain MRI scans conducted between July 2011 and January 2022, identifying 104 patients with bilateral CTTH. DWI, FLAIR sequences, and follow-up scans were visually assessed for T2/FLAIR mismatch and diffusion restriction. Clinical data were obtained from electronic patient records. Statistical analysis was performed using SPSS, with significance set at p < .05. A total of 104 pediatric patients with CTTH were included, ranging from 1 month to 16 years old (mean age: 31.34 months). Epilepsy, metabolic diseases, and cerebral palsy were the most common clinical diagnoses. Diffusion restriction was observed in 40.8% of patients, while 39.6% had FLAIR hyperintensity. T2/FLAIR mismatch, defined for the first time in CTTH, was found in 60.4% of patients. A significant correlation was found between T2/FLAIR mismatch and clinical diagnoses (p = .020), as well as between diffusion restriction and T2/FLAIR mismatch (p = .017). CTTH in pediatric patients may arise from two distinct processes: a transient, developmental phenomenon or a pathological process marked by irreversible myelin degeneration. T2/FLAIR mismatch and diffusion restriction provide valuable diagnostic markers, offering insights into the severity and chronicity of CTTH. Further studies are needed to validate these findings and their clinical implications.

Polymorphic low-grade neuroepithelial tumors of the young: disease characteristics and treatment decisions from the epilepsy surgery perspective.

The Polymorphic Low-Grade Neuroepithelial Tumor of the Young (PLNTY) is a rare, epilepsy-associated brain tumor that has been increasingly recognized but is not well understood due to the scarcity of clinical reports. Our study reviews the clinical characteristics and treatment outcomes of 14 patients with PLNTY to enhance the understanding of this condition from an epilepsy surgery perspective. We performed a retrospective analysis of 14 PLNTY cases at our hospital. A literature review on prior studies was also conducted. Our study included 8 males and 6 females, all presenting with epilepsy. Despite anti-seizure medication, 92.3% of patients continued to have seizures, with 58.3% diagnosed as having drug-resistant epilepsy. Neuroimaging revealed that 64.3% of the lesions were in the temporal lobe, with 75.0% showing calcification on CT, 71.4% exhibiting mixed signals on T2-weighted images, and 92.7% showing tumor enhancement. The transmantle sign was noted in 57.1% of T2 FLAIR sequences. EEGs indicated abnormal activity in 69.2% of patients, with 30.7% showing bilateral discharges. SEEG in two patients confirmed the tumor's epileptogenicity. A 78.6% total resection rate was achieved, with a 90.0% postoperative seizure-free rate and an 85.7% excellent Engel grade 1 rate. No instances co-occurring with focal cortical dysplasia (FCD) were observed. PLNTY is characterized by unique neuroimaging features and a strong association with epilepsy. SEEG is pivotal for cases with unclear lateralization, aiding in identifying the link between the tumor and seizures. Following established epilepsy surgery protocols for brain tumor management, early intervention and extended resection can improve the rate of postoperative seizure freedom.

Predicting intraoperative 5-ALA-induced tumor fluorescence via MRI and deep learning in gliomas with radiographic lower-grade characteristics.

Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely sampled to avoid undergrading. We aimed to analyze whether a deep learning model could predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). We evaluated a cohort of 163 glioma patients categorized intraoperatively as fluorescent (n = 83) or non-fluorescent (n = 80). The preoperative MR images of gliomas lacking high-grade characteristics (e.g., necrosis or irregular ring contrast-enhancement) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a tenfold cross-validation procedure. Our proposed approach's performance was assessed using mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively. Our findings highlight the potential of a U-Net model, coupled with a Random Forest classifier, for pre-operative prediction of intraoperative fluorescence. We achieved high accuracy using the features extracted by the U-Net model pre-trained for brain tumor segmentation. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.

Improving Deep Learning Models for Pediatric Low-Grade Glioma Tumours Molecular Subtype Identification Using MRI-based 3D Probability Distributions of Tumour Location.

Purpose: Pediatric low-grade gliomas (pLGG) are the most common brain tumour in children, and the molecular diagnosis of pLGG enables targeted treatment. We use MRI-based Convolutional Neural Networks (CNNs) for molecular subtype identification of pLGG and augment the models using tumour location probability maps. Materials and Methods: MRI FLAIR sequences of 214 patients (110 male, mean age of 8.54 years, 143 BRAF fused and 71 BRAF V600E mutated pLGG tumours) from January 2000 to December 2018 were included in this retrospective REB-approved study. Tumour segmentations (volumes of interest-VOIs) were provided by a pediatric neuroradiology fellow and verified by a pediatric neuroradiologist. Patients were randomly split into development and test sets with an 80/20 ratio. The 3D binary VOI masks for each class in the development set were combined to derive the probability density functions of tumour location. Three pipelines for molecular diagnosis of pLGG were developed: location-based, CNN-based, and hybrid. The experiment was repeated 100 times each with different model initializations and data splits, and the Areas Under the Receiver Operating Characteristic Curve (AUROC) was calculated, and Student's t-test was conducted. Results: The location-based classifier achieved an AUROC of 77.9, 95% confidence interval (CI) (76.8, 79.0). CNN-based classifiers achieved an AUROC of 86.1, 95% CI (85.0, 87.3), while the tumour-location-guided CNNs outperformed the other classifiers with an average AUROC of 88.64, 95% CI (87.6, 89.7), which was statistically significant (P-value .0018). Conclusion: Incorporating tumour location probability maps into CNN models led to significant improvements for molecular subtype identification of pLGG.

Diagnosis of vascular lesions in the brain – comparing T_2 and FLAIR sequences

ABSTRACT Introduction: Vascular brain lesions refer to brain damage caused by problems with blood vessels and can include various disorders such as stroke, aneurysms, blood clots, and others. Because different brain tissues have different characteristic relaxation times, and the FLAIR sequence can also be used to deal with different tissue stresses. the sequence provides high intensity while the FLAIR sequence achieves complete saturation of cerebrospinal fluid. The objectives of this study are to compare the visualization of vascular lesions using and the FLAIR sequence and to determine which sequence provides a better depiction and additional information about vascular lesions. Research Methods: The study was designed as a retrospective descriptive study, conducted at the Private Healthcare Institution 'Medical Center' in Travnik using an MRI machine: MRI Siemens Avanto A + Tim + Dot System, with a strength of 1.5 T. The study involved 50 patients diagnosed with vascular lesions. Results: In the age group from 50 to 59 years, 7 patients with FAZEKAS 0 – 1 (46.66%), 4 patients with FAZEKAS 1 (26.66%), 3 patients with FAZEKAS 2 (20%) and one patient with FAZEKAS 3 (6.66%) were diagnosed. In the age group from 60 to 69 years, 6 patients with FAZEKAS 0 – 1 (28.57%), 6 patients with FAZEKAS 1 (28.57%), 6 patients with FAZEKAS 2 and 3 patients with FAZEKAS 3 (14.28%) were diagnosed. In the 70 to 79 age group, 2 patients were diagnosed with FAZEKAS 0 – 1 (14.28%), 5 patients were diagnosed with FAZEKAS 1 (35.71%), 5 patients were diagnosed with FAZEKAS 2 (35.71%) and 2 patients were diagnosed with FAZEKAS 3 (14.28%). Discussion: Several studies have been conducted to evaluate the sensitivity of and FLAIR sequences in the diagnosis of vascular lesions in the brain. In the mentioned studies, it was found that the FLAIR sequence possesses superior capabilities in identifying and better displaying vascular lesions compared to healthy brain tissue. After measuring lesions in all 50 patients enrolled in the study, they were divided by size into three different groups: Lesions smaller than 10 millimeters; Lesions larger than 10 millimeters and smaller than 20 millimeters; Lesions larger than 20 millimeters. After statistical processing of the examined sample within this study, it was found that the FLAIR sequence provides a better representation of vascular lesions in the brain compared to the sequence in all three different groups, and it is concluded that the differences are statistically significant in favor of the FLAIR sequence in all three observed lesion sizes. The prognostic value of FLAIR vascular hyperintensity still needs to be investigated. Future studies will determine in which settings the presence of FLAIR vascular hyperintensity can be used as valuable information for the clinician. FLAIR vascular hyperintensities indicate a risk of persistent vascular stenosis or occlusion, associated with an increased risk of future stroke. They also help identify patients with favorable collateral blood flow, who could benefit from aggressive revascularization therapy. Conclusion: Statistically, there was a difference in the better presentation of vascular lesions on the FLAIR sequence compared to the sequence. In some cases, a sequence may be sufficient but in most cases a FLAIR sequence is preferable. Although the noise level is higher on the FLAIR sequence compared to the standard sequence, the FLAIR sequence is more useful in detecting vascular lesions.

RADT-38. CLINICAL, MOLECULAR AND IMAGING FEATURES ASSOCIATED WITH LONG TERM SURVIVAL IN GLIOBLASTOMA PATIENTS

Abstract INTRODUCTION Glioblastoma (GBM) is the most common malignant brain tumor in adults and has poor prognosis despite standard of care treatment. Nevertheless, certain patients surpass survival expectations. This study seeks to identify the clinical, molecular, and imaging characteristics of GBM associated with extended patient survival. METHODS In this retrospective cohort study, we examined records of adult GBM patients (WHO 2016 classification) treated at Thomas Jefferson University Hospital from 2010 to 2023. Exclusion criteria included a preoperative Karnofsky Performance Status (KPS) below 60 and treatment with hypo-fractionated radiation therapy. Patients were categorized into two groups: short-term survivors (STS), who survived less than 36 months from diagnosis, and long-term survivors (LTS), who survived more than 36 months. We reviewed patient charts and pathology reports for comprehensive clinical and molecular data. For radiomics analysis, tumor segmentation was performed using CaPTk software on the initial diagnostic MRI (T1 pre and post-contrast, FLAIR and T2 sequences). The relationship between overall survival of more than three years was analyzed with univariable logistic models for potential predictors using R statistical software. RESULTS Of the cohort of 210 patients, 37 (17.6%) survived beyond three years. The median age at diagnosis was 55 years (range; 29-79) Twenty-two patients were male and 15 were female. Twenty-two percent had IDH mutation and 65% had MGMT methylation. Factors associated with long-term survival included younger age at diagnosis (p =0.007), MGMT hypermethylation (p =0.019), IDH mutation (p=0.001), absence of TERT mutation (p = 0.002), higher average number of adjuvant temozolomide cycles (10 vs. 5; p = 0.005), and smaller volume of enhancing tumor on T1 post-contrast imaging segmentation (p=0.022). But there was no significant difference in FLAIR abnormality or necrotic core volumes between the groups. CONCLUSION In our cohort of GBM patients, patients diagnosed at a younger age, MGMT hypermethylation, IDH mutation, absence of TERT mutation, receiving more cycles of adjuvant temozolomide treatment, and smaller enhancing tumor volume on preoperative T1 post-contrast imaging were associated with longer survival. Future research involving larger cohorts and validation of our findings is needed.

NIMG-65. SYNTHETIC MRI GENERATION TO FACILITATE AUTOSEGMENTATION OF PEDIATRIC BRAIN TUMORS IN LIMITED DATA SCENARIOS

Abstract BACKGROUND The availability of standard multiparametric MRI sequences, including pre-contrast T1w (T1w-pre), post-contrast T1w (T1w-post), T2w, and FLAIR images, is essential for accurate segmentation of tumor subregions and subsequent response assessment in pediatric brain tumors (PBTs). However, clinical MRI sets are often incomplete due to imaging artifacts or inconsistent acquisition protocols across different centers. This study leverages Generative Adversarial Networks (GANs) to synthesize missing FLAIR and T1w-pre images from T2w and T1w-post images, respectively, to facilitate tumor segmentation in PBTs. METHODS We developed two GAN models based on the pix2pix framework, trained, validated, and tested on FLAIR-T2w and T1w-post-T1w-pre pairs from a multi-histology and multi-institutional cohort of 476 subjects with PBTs from the Children’s Brain Tumor Network (CBTN). The perceptual quality of the synthesized T1w-pre and FLAIR images was evaluated using the Structural Similarity Index (SSI; ideal value = 1). The robustness of the synthesized sequences to replace missing MRI sequences was evaluated by comparing the segmentation performance (Dice score) of our pre-trained autosegmentation model using all real modalities versus replacing real sequences with their synthesized counterparts. RESULTS The T1w-pre and FLAIR synthesis GANs achieved mean SSI values of 0.95 and 0.93, respectively. Median Dice scores for segmentation of whole tumor (WT), enhancing tumor (ET), and tumor core (TC) were calculated for real sequences: 0.90, 0.83, 0.89, replacing real FLAIR with synthetic: 0.86, 0.81, 0.86, and replacing real T1w-pre with synthetic: 0.90, 0.75, 0.89. No statistical significance (p&amp;gt;0.05) was observed in segmentation performance for WT, TC, ET when replacing real T1w-pre with synthetic, and for ET when replacing real with synthetic FLAIR sequences. CONCLUSION This method achieves robust segmentation performance in limited data scenarios by synthesizing missing MRI sequences. Future work includes improving FLAIR synthesis and segmentation performance for WT and ET by implementing and comparing other GAN architectures.

Integrating standard epilepsy protocol, ASL-perfusion, MP2RAGE/EDGE and the MELD-FCD classifier in the detection of subtle epileptogenic lesions: a 3 Tesla MRI pilot study.

Malformations of cortical development (MCDs) in children with focal epilepsy pose significant diagnostic challenges, and a precise radiological diagnosis is crucial for surgical planning. New MRI sequences and the use of artificial intelligence (AI) algorithms are considered very promising in this regard, yet studies evaluating the relative contribution of each diagnostic technique are lacking. The study was conducted using a dedicated "EPI-MCD MR protocol" with a 3 Tesla MRI scanner in patients with focal epilepsy and previously negative MRI. MRI sequences evaluated included 3D FLAIR, 3D T1 MPRAGE, T2 Turbo Spin Echo (TSE), 3D T1 MP2RAGE, and Arterial Spin Labelling (ASL). Two paediatric neuroradiologists scored each sequence for localisation and extension of the lesion. The MELD-FCD AI classifier's performance in identifying pathological findings was also assessed. We only included patients where a diagnosis of MCD was subsequently confirmed on histology and/or sEEG. The 3D FLAIR sequence showed the highest yield in detecting epileptogenic lesions, with 3D T1 MPRAGE, T2 TSE, and 3D T1 MP2RAGE sequences showing moderate to low yield. ASL was the least useful. The MELD-FCD classifier achieved a 69.2% true positive rate. In one case, MELD identified a subtle area of cortical dysplasia overlooked by the neuroradiologists, changing the management of the patient. The 3D FLAIR sequence is the most effective in the MRI-based diagnosis of subtle epileptogenic lesions, outperforming other sequences in localisation and extension. This pilot study emphasizes the importance of careful assessment of the value of additional sequences.

P10.22.B PREDICTING INTRAOPERATIVE 5-ALA-INDUCED TUMOR FLUORESCENCE VIA MRI AND DEEP LEARNING IN GLIOMAS WITH RADIOGRAPHIC LOWER-GRADE CHARACTERISTICS

Abstract BACKGROUND Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely resected to avoid undergrading. We aimed to analyze whether a deep learning model can predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). Material and Methods: The MRI images of gliomas lacking high-grade characteristics (necrosis, extended contrast-enhancement, a.o.) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a 10-fold cross-validation procedure. RESULTS We evaluated a cohort of 163 glioma patients categorized as fluorescent (n=83) or non-fluorescent (n=80). Our proposed approach’s performance was evaluated using metrics such as mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively. CONCLUSION Our findings highlight the potential of a U-Net model, coupled with a random forest classifier, for intraoperative fluorescence prediction. We achieved good accuracy using advanced techniques such as deep learning-based tumor segmentation and Variational Autoencoder for radiomics feature extraction. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.

DTI fiber-tracking parameters adjacent to gliomas: the role of tract irregularity value in operative planning, resection, and outcome.

The goal of glioma surgery is maximal tumor resection associated with minimal post-operative morbidity. Diffusion tensor imaging-tractography/fiber tracking (DTI-FT) is a valuable white-matter (WM) visualization tool for diagnosis and surgical planning. Still, it assumes a descriptive role since the main DTI metrics and parameters showed several limitations in clinical use. New applications and quantitative measurements were recently applied to describe WM architecture that surround the tumor area. The brain adjacent tumor area (BAT) is defined as the region adjacent to the gross tumor volume, which contains signal abnormalities on T2-weighted or FLAIR sequences. The DTI-FT analysis of the BAT can be adopted as predictive values and a guide for safe tumor resection. This is an observational prospective study on an extensive series of glioma patients who performed magnetic resonance imaging (MRI) with pre-operative DTI-FT analyzed on the BAT by two different software. We examined DTI parameters of Fractional anisotropy (FA mean, min-max), Mean diffusivity (MD), and the shape-metric "tract irregularity" (TI) grade, comparing it with the surgical series' clinical, radiological, and outcome data. The population consisted of 118 patients, with a mean age of 60.6 years. 82 patients suffering from high-grade gliomas (69.5%), and 36 from low-grade gliomas (30.5%). A significant inverse relationship exists between the FA mean value and grading (p = 0.001). The relationship appears directly proportional regarding MD values (p = 0.003) and TI values (p = 0.005). FA mean and MD values are susceptible to significant variations with tumor and edema volume (p = 0.05). TI showed an independent relationship with grading regardless of tumor radiological features and dimensions, with a direct relationship with grading, ki67% (p = 0,05), PFS (p < 0.001), and EOR (p < 0.01). FA, MD, and TI are useful predictive measures of the clinical behavior of glioma, and TI could be helpful for tumor grading identification and surgical planning.

Vermian multinodular and vacuolating lesion of unknown significance discovered following syncope: a case report

Introduction and importance: Multinodular and Vacuolating Posterior Fossa Lesions of Unknown Significance (MV PLUS) are benign cystic lesions that, though typically asymptomatic, can present with neurological symptoms such as seizures, headaches, and syncope. These lesions are predominantly found in sub-tentorial brain structures but can also appear in supratentorial areas. MRI is crucial in detecting these lesions, characterized by small nodules with high intensity on T2-FLAIR sequences. Despite increasing awareness, the pathophysiology and classification of MV PLUS lesions remain unclear, necessitating further research and careful monitoring. Case presentation: A 52-year-old female presented with subjective dizziness and a recent syncope episode. Neurological examination showed ataxia and a positive Romberg sign. MRI revealed a multicystic and nodular lesion in the vermian and paravermian regions, with altered signal intensity on T1-weighted and FLAIR sequences. The lesion showed no pathological enhancement post-gadolinium administration, and spectroscopy revealed no significant metabolite peaks. Clinical improvement was observed following corticosteroid and antivertiginous therapy, and the patient was discharged with a recommendation for neuroradiological follow-up. Clinical discussion: MV PLUS lesions are a subset of multinodular and vacuolating lesions that present significant diagnostic challenges due to their complex radiological features. First described in 2013, these lesions have distinct MRI characteristics, including a nodular appearance with high T2-FLAIR intensity and occasional cystic components. Despite being benign and typically stable, the differential diagnosis includes various other intracranial lesions, requiring careful evaluation. The pathogenesis and optimal management strategies for MV PLUS lesions are still under investigation, emphasizing the need for continued research. Conclusion: MV PLUS lesions, although rare and benign, present unique diagnostic challenges due to their varied radiological features and potential neurological symptoms. Regular MRI monitoring is essential to track their stability, given the current lack of understanding regarding their pathophysiology and long-term implications. Further research is needed to elucidate the etiology, natural history, and optimal management of these intriguing lesions.

Brain microbleeds resulting from presumed extensive fat emboli in a patient with bone marrow necrosis following a sickle cell disease vaso-occlusive crisis.

Acute manifestations of sickle cell disease (SCD) are numerous and multisystemic.Cerebral fat embolism (CFE) is a rare but serious complication of SCD caused by bone marrow necrosis (BMN) during vaso-occlusive crises (VOC). We present the case of a41-year-old man with SCD who developed severe VOC and multi-organ dysfunction.He subsequently experienced neurological deterioration with decreased consciousness and diffuse encephalopathy on serial electroencephalograms. Bone marrow aspiration confirmed BMN. Brain MRI revealed extensive diffuse leukoencephalopathy, vasogenic and cytotoxic edema in the white matter, patchy edema in the cranial vault bone marrow on fat-suppressed FLAIR sequence (a finding consistent with the confirmed BMN), and multiple cerebral microbleeds on susceptibility-weighted imaging consistent with CFE. The management of acute neurological complications of SCD varies depending on the specific complication. Brain MRI plays a crucial role in the accurate diagnosis of these complications to guide appropriate treatment.

Clinical and neuroimaging features in neurological Wilson’s disease with claustrum lesions

According to early research, the incidence of claustrum lesions in patients with neurological Wilson’s disease (WD) was inconsistent, ranging from 1.8 to 75% on magnetic resonance imaging (MRI). Our study aims to explore the incidence, clinical presentation features, iconography features, and possible pathological mechanisms in WD patients with claustrum lesions on magnetic resonance imaging (MRI), to characterize the clinical, and brain imaging findings and possible pathological mechanisms in the patients with WD. Retrospective cases meeting the inclusion criteria were studied for analyzing MRI characteristics and associated physicochemical examination data in neurological WD patients with claustrum lesions. 443 (66.3%) with brain MRI abnormalities were screened from 668 WD patients. The three (0.7%) patients with the claustrum lesions characteristics on MRI images were: (a) “bright claustrum” in T2-weighted and FLAIR sequences, (b) bilateral symmetrical, (c) non-isolated lesions, (d) occurred only in severe neurological manifestations. The claustrum lesions are not common in neurological WD and mainly appear in cases with severe neurological symptoms. On MRI, the “bright claustrum” signs may be a radiographic marker of neuroinflammation, the features of the lesions showed bilateral symmetry, and hyperintensity signals on T2-weighted, FLAIR, and DWI.

Radiomic detection of abnormal brain regions in tuberous sclerosis complex.

Radiomics refers to the extraction of quantitative information from medical images and is most commonly utilized in oncology to provide ancillary information for solid tumor diagnosis, prognosis, and treatment response. The traditional radiomic pipeline involves segmentation of volumes of interest with comparison to normal brain. In other neurologic disorders, such as epilepsy, lesion delineation may be difficult or impossible due to poor anatomic definition, small size, and multifocal or diffuse distribution. Tuberous sclerosis complex (TSC) is a rare genetic disease in which brain magnetic resonance imaging (MRI) demonstrates multifocal abnormalities with variable imaging and epileptogenic features. The purpose of this study was to develop a radiomic workflow for identification of abnormal brain regions in TSC, using a whole-brain atlas-based approach with generation of heatmaps based on signal deviation from normal controls. This was a retrospective pilot study utilizing high-resolution whole-brain 3D FLAIR MRI datasets from retrospective enrollment of tuberous sclerosis complex (TSC) patients and normal controls. Subjects underwent MRI including high-resolution 3D FLAIR sequences. Preprocessing included skull stripping, coregistration, and intensity normalization. Using the Brainnetome and Harvard-Oxford atlases, brain regions were parcellated into 318 discrete regions. Expert neuroradiologists spatially labeled all tubers in TSC patients using ITK-SNAP. The pyradiomics toolbox was used to extract 88 radiomic features based on IBSI guidelines, comparing tuber-affected and non-tuber-affected parenchyma in TSC patients, as well as normal brain tissue in control patients. For model training and validation, regions with tubers from 20 TSC patients and 30 normal control subjects were randomly divided into two training sets (80%) and two validation sets (20%). Additional model testing was performed on a separate group of 20 healthy controls. LASSO (least absolute shrinkage and selection operator) was used to perform variable selection and regularization to identify regions containing tubers. Relevant radiomic features selected by LASSO were combined to produce a radiomic score ω, defined as the sum of squared differences from average control group values. Region-specific ω scores were converted to heat maps and spatially coregistered with brain MRI to reflect overall radiomic deviation from normal. The proposed radiomic workflow allows for quantification of deviation from normal in 318 regions of the brain with the use of a summative radiomic score ω. This score can be used to generate spatially registered heatmaps to identify brain regions with radiomic abnormalities. The pilot study of TSC showed radiomic scores ω that were statistically different in regions containing tubers from regions without tubers/normal brain (p<0.0001). Our model exhibits an AUC of 0.81 (95% confidence interval: 0.78-0.84) on the testing set, and the best threshold obtained on the training set, when applied to the testing set, allows us to identify regions with tubers with a specificity of 0.91 and a sensitivity of 0.60. We describe a whole-brain atlas-based radiomic approach to identify abnormal brain regions in TSC patients. This approach may be helpful for identifying specific regions of interest based on relatively greater signal deviation, particularly in clinical scenarios with numerous or poorly defined anatomic lesions.

Automated segmentation of midbrain nuclei using deep learning and multisequence MRI: a longitudinal study on iron accumulation with age

Abstract Elevated levels of brain iron, particularly within the basal ganglia, have been associated with cognitive and motor impairment in normal aging and neurodegenerative conditions. The subthalamic nucleus (STN), substantia nigra (SN), and red nucleus (RN), despite their high iron content and contribution to motor and cognitive processes, are less frequently studied. This oversight can largely be attributed to the challenges posed by in-vivo assessments of these small, deep-seated midbrain structures. We developed and validated an automated tool for the segmentation of the STN, SN, and RN. Multi-sequence magnetic resonance imaging (MRI) data including T1-weighted, FLAIR, Quantitative Susceptibility Mapping (QSM) and R2* alongside manual delineation on QSM images of 40 individuals, was used to train segmentation models based on nnU-Net deep-learning framework. A combination of QSM and FLAIR sequences was found to be optimal for structure segmentation (mean Dice scores of 0.84, 0.91 and 0.94 for STN, SN and RN, respectively). We next applied the automated segmentation method to an independent 3-year longitudinal dataset including 175 healthy adults (age range at baseline: 20-79 years old). Structural equation modelling was used to assess iron accumulation over time using age, sex, baseline iron and regional volume as factors of interest. Cross-sectionally, older age was linearly associated with higher iron load in SN and STN; the association was non-linear in RN. Longitudinally, results indicated significant iron accumulation in the STN (Mean increase = 0.02, p = 0.005) and SN (Mean increase = 0.035, p = 0.001), but not in the RN (Mean increase = 0.015, p = 0.2). Our findings demonstrated high performance of nnU-Net in automated segmentation, and advanced our understanding of iron accumulation in midbrain nuclei in aging.

Compressed SENSitivity Encoding (SENSE): Qualitative and Quantitative Analysis.

This study aimed to qualitatively and quantitatively evaluate T1-TSE, T2-TSE and 3D FLAIR sequences obtained with and without Compressed-SENSE technique by assessing the contrast (C), the contrast-to-noise ratio (CNR) and the signal-to-noise ratio (SNR). A total of 142 MRI images were acquired: 69 with Compressed-SENSE and 73 without Compressed-SENSE. All the MRI images were contoured, spatially aligned and co-registered using 3D Slicer Software. Two radiologists manually drew 12 regions of interests on three different structures of CNS: white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF). C values were significantly higher in Compressed-SENSE T1-TSE compared to No Compressed-SENSE T1-TSE for three different structures of the CNS. C values were also significantly lower for Compressed-SENSE 3D FLAIR and Compressed-SENSE T2-TSE compared to the corresponding No Compressed-SENSE scans. While CNR values did not significantly differ in GM-WM between Compressed-SENSE and No Compressed-SENSE for the 3D FLAIR and T1-TSE sequences, the differences in GM-CSF and WM-CSF were always statistically significant. Compressed-SENSE for 3D T2 FLAIR, T1w and T2w sequences enables faster MRI acquisition, reducing scan time and maintaining equivalent image quality. Compressed-SENSE is very useful in specific medical conditions where lower SAR levels are required without sacrificing the acquisition of helpful diagnostic sequences.

Optimizing Glioblastoma, IDH-wildtype Treatment Outcomes : A Radiomics and Support Vector Machine -Based Approach to Overall Survival Estimation.

Glioblastoma multiforme (GBM), particularly the IDH-wildtype type, represents a significant clinical challenge due to its aggressive nature and poor prognosis. Despite advancements in medical imaging and its modalities, survival rates have not improved significantly, demanding innovative treatment planning and outcome prediction approaches. This study utilizes a Support Vector Machine (SVM) classifier using radiomics features to predict the overall survival (OS) of GBM, IDH-wildtype patients to short (< 12 Months) and long (>=12 Months) survivors. A dataset comprising multi-parametric MRI (mpMRI) scans from 574 patients was analyzed. Radiomic features were extracted from T1, T2, FLAIR, and T1-Gd sequences. Low variance features were removed, and Recursive Feature Elimination (RFE) was used to select the most informative features. The SVM model was trained using a k-fold cross-validation approach. Furthermore, clinical parameters such as age, gender, and MGMT promoter methylation status were integrated to enhance prediction accuracy. The model showed reasonable results in terms of cross-validated AUC of 0.84 (95% CI: 0.80-0.90) with (p-value < 0.001) effectively categorizing patients into short and long survivors. Log-rank test (Chi-square statistics) analysis for the developed model was 0.00029 along with the 1.20 Cohen's d effect size. Most importantly, clinical data integration further refined the survival estimates, providing a more fitted prediction that considers individual patient characteristics by Kaplan-Meier curve with p-value<0.0001. The proposed method significantly enhances the predictive accuracy of OS outcomes in GBM, IDH-wildtype patients. By integrating detailed imaging features with key clinical indicators, this model offers a robust tool for personalized treatment planning, potentially improving OS.

Multicenter validation of synthetic FLAIR as a substitute for FLAIR sequence in acute ischemic stroke.

To evaluate performance of synthetic and real FLAIR for identifying early stroke in a multicenter cohort. This retrospective study was conducted using DWI and FLAIR extracted from the Endovascular Treatment in Ischemic Stroke image registry (2017-2021). The database was partitioned into subsets according to MRI field strength and manufacturer, and randomly divided into training set (70%) used for model fine-tuning, validation set (15%), and test set (15%). In test set, five readers, blinded to FLAIR sequence type, assessed DWI-FLAIR mismatch using real and synthetic FLAIR. Interobserver agreement for DWI-FLAIR rating and concordance between synthetic and real FLAIR were evaluated with kappa statistics. Sensitivity and specificity for identification of ⩽4.5 h AIS were compared in patients with known onset-to-MRI delay using McNemar's test. 1454 complete MRI sets (1172 patients, median (IQR) age: 73 years (62-82); 762 women) acquired on 125 MRI units were analyzed. In test set (207 MRI), interobserver reproducibility for DWI-FLAIR mismatch labeling was substantial for real and synthetic FLAIR (Fleiss κ = 0.79 (95%CI: 0.73-0.84) and 0.77 (95%CI: 0.71-0.82), respectively). After consensus, concordance between real and synthetic FLAIR was excellent (κ = 0.85 (95%CI: 0.78-0.92)). In 141 MRI sets with known onset-to-MRI delay, diagnostic performances for ⩽4.5 h AIS identification did not differ between real and synthetic FLAIR (sensitivity: 60/71 (85%) vs 59/71 (83%), p = .56; specificity: 65/70 (93%) vs 65/70 (93%), p > 0.99). A deep-learning-based FLAIR fine-tuned on multicenter data can provide comparable performances to real FLAIR for early AIS identification. This approach may help reducing MR protocol duration and motion artifacts.

Non-contrast magnetic resonance evaluation of active multiple sclerosis lesions: Emerging role of quantitative synthetic magnetic resonance imaging.

The current study aims to explore the utility of novel synthetic MRI-derived quantitative parameters including myelin-correlated volume (MyC) in identifying active MS lesions without injecting gadolinium contrast. 43 MS patients underwent institutional MS protocol including 3D FLAIR and post-contrast 3D T1VIBE sequence on a 1.5T MR Scanner in addition to synthetic MRI sequence. MS plaques were categorised into enhancing (C) and non-enhancing (N) lesions. They were also sub-categorised based on location into periventricular WM lesions (P), deep WM lesions (D), infratentorial lesions (I) and cortical-juxtacortical (C) lesions. ROIs were placed on Synthetic FLAIR images in MS lesions and quantitative parameters of R1, R2, PD and myelin-correlated volume (MyC) obtained. Sensitivity and specificity for various cut-off values to differentiate enhancing from non-enhancing multiple sclerosis lesions were calculated by performing ROC curve analysis and logistic regression analysis. Contrast enhancing lesions demonstrated significantly higher mean R1, R2 values and lower mean PD values in comparison to non-enhancing lesions (p < 0.05) but with limited specificity. Region-wise analysis revealed high AUC values for mean R1 and R2 at cortical-juxtacortical lesions (p < 0.001) followed by periventricular lesions (p < 0.003) for differentiating enhancing from non-enhancing lesions with no significant contribution from MyC and PD values. Synthetic MRI-derived quantitative parameters of mean R1, R2, MyC and PD hold value in differentiating contrast enhancing and non-enhancing MS lesions without administering gadolinium-based contrast agent. However, the current study did not achieve significant specificity for establishing the same.