Magnetic Resonance Imaging Features Research Articles

Magnetic resonance imaging-based prognostic model for subsequent distant metastasis in patients with ipsilateral breast tumor recurrence following breast-conserving surgery.

Ipsilateral breast tumor recurrence (IBTR) following breast-conserving surgery (BCS) has been considered a risk factor for distant metastasis (DM). Limited data are available regarding the subsequent outcomes after IBTR. Therefore, this study aimed to determine the clinical course after IBTR and develop a magnetic resonance imaging (MRI)-based predictive model for subsequent DM. We retrospectively extracted quantitative features from MRI to construct a radiomics cohort, with all eligible patients undergoing preoperative MRI at time of primary tumor and IBTR between 2010 and 2018. Multivariate Cox analysis was performed to identify factors associated with DM. Three models were constructed using different sets of clinicopathological, qualitative, and quantitative MRI features and compared. Additionally, Kaplan-Meier analysis was performed to assess the prognostic value of the optimal model. Among the 183 patients who experienced IBTR, 47 who underwent MRI for both primary and recurrent tumors were enrolled. Multivariate analysis demonstrated that the independent prognostic factors were human epidermal growth factor receptor 2 (HER2) status [hazard ratio (HR) =5.40] and background parenchymal enhancement (BPE) (HR =7.94) (all P values <0.01). Furthermore, four quantitative MRI features of recurrent tumors were selected through the least absolute shrinkage and selection operator (LASSO) method. The combined model exhibited superior performance [concordance index (C-index) 0.77] compared to the clinicoradiological model (C-index 0.71; P=0.006) and radiomics model (C-index 0.70; and P=0.01). Furthermore, the combined model successfully categorized patients into low- and high-risk subgroups with distinct prognoses (P<0.001). The clinicopathological and MRI features of IBTR were associated with secondary events following surgery. Additionally, the MRI-based combined model exhibited the highest predictive efficacy. These findings could be helpful in risk stratification and tailoring follow-up strategies in patients with IBTR.

Enhancing Early Diagnosis of Bipolar Disorder in Adolescents Through Multimodal Neuroimaging

BackgroundBipolar disorder (BD), a severe neuropsychiatric condition, often appears during adolescence. Traditional diagnostic methods, which primarily rely on clinical interviews and single-modal magnetic resonance imaging (MRI) techniques, may have limitations in accuracy. This study aimed to improve adolescent BD diagnosis by integrating behavioral assessments with multimodal MRI. We hypothesized that this combination would enhance diagnostic accuracy for at-risk adolescents. MethodsA retrospective cohort of 309 participants, including patients with BD, offspring of patients with BD (with and without subthreshold symptoms), non-BD offspring with subthreshold symptoms, and healthy control participants, was analyzed. Behavioral attributes were integrated with MRI features from T1-weighted, resting-state functional MRI, and diffusion tensor imaging. Three diagnostic models were developed using GLMNET multinomial regression: a clinical diagnosis model based on behavioral attributes, an MRI-based model, and a comprehensive model integrating both datasets. ResultsThe comprehensive model achieved a prediction accuracy of 0.83 (95% CI, 0.72–0.92), significantly higher than the clinical (0.75) and MRI-based (0.65) models. Validation with an external cohort showed high accuracy (0.89, area under the curve = 0.95). Structural equation modeling revealed that clinical diagnosis (β = 0.487, p < .0001), parental BD history (β = −0.380, p < .0001), and global function (β = 0.578, p < .0001) significantly affected brain health, while psychiatric symptoms showed only a marginal influence (β = −0.112, p = .056). ConclusionsThis study highlights the value of integrating multimodal MRI with behavioral assessments for early diagnosis in at-risk adolescents. Combining neuroimaging enables more accurate patient subgroup distinctions, facilitating timely interventions and improving health outcomes. Our findings suggest a paradigm shift in BD diagnostics, advocating for incorporating advanced imaging techniques in routine evaluations.

Magnetic Resonance Imaging Features of Sporadic Optic Chiasmatic-Hypothalamic Gliomas and Correlation with Histopathology and BRAF Gene Alterations.

Sporadic optic chiasmatic-hypothalamic gliomas (OCHGs), though histologically low-grade tumors, manifest as aggressive neoplasms radiologically, leading to difficulty in diagnosis. Molecular alterations of the BRAF gene are detectable in a majority of sporadic OCHGs. The purpose of our study was to elucidate the characteristic imaging features of sporadic OCHGs and to investigate whether imaging phenotypes could potentially correlate with specific BRAF gene alterations associated with these tumors. We retrospectively reviewed baseline magnetic resonance (MR) images and medical records of 26 patients with histopathologically proven sporadic OCHGs. MR imaging (MRI) features were systematically evaluated. Statistical analysis was performed to determine whether there was a significant association between imaging findings and BRAF molecular alterations. Twenty-two cases (84.6%) presented with solid-cystic masses, while four (15.4%) presented with purely solid lesions. In all 26 cases, the solid component revealed central necrosis; there was minimal necrosis in 11 cases (42.3%), moderate in 8 (30.7%), and marked in 7 (26.9%). The presence of multiple cysts (>4) and minimal necrosis showed a significant association with BRAFV600E mutation (P < 0.005). Marked necrosis in the solid component significantly correlated with BRAF wild genotype (P < 0.001). The presence of a single peripheral cyst significantly correlated with BRAF fusion (P = 0.04). Sporadic OCHGs have a distinctive appearance on imaging. The solid-cystic composition coupled with varying degrees of central necrosis are clues to the radiological diagnosis of this entity and can facilitate early recognition in clinical practice. Imaging could potentially serve as a non-invasive predictor of the BRAF alteration status, thereby serving as a prognostic marker and guiding personalized management.

Nomogram of magnetic resonance imaging (MRI) histogram analysis to predict telomerase reverse transcriptase promoter mutation status in glioblastoma.

Telomerase reverse transcriptase promoter (pTERT) status is a strong biomarker to diagnose and predict the prognosis of glioblastoma (GBM). In this study, we explored the predictive value of preoperative magnetic resonance imaging (MRI) histogram analysis in the form of nomogram for evaluating pTERT mutation status in GBM. The clinical and imaging data of 181 patients with GBM at our hospital between November 2018 and April 2023 were retrospectively assessed. We used the molecular sequencing results to classify the datasets into pTERT mutations (C228T and C250T) and pTERT-wildtype groups. FireVoxel software was used to extract preoperative T1-weighted contrast-enhanced (T1C) histogram parameters of GBM patients. The T1C histogram parameters were compared between groups. Univariate and multivariate logistic regression analyses were used to construct the nomogram, and the predictive efficacy of model was evaluated using calibration and decision curves. Receiver operating characteristic curve was used to assess model performance. Patient age and percentage of unenhanced tumor area showed statistically significant differences between the pTERT mutation and pTERT-wildtype groups (P<0.001). Among the T1C histogram features, the maximum, standard deviation (SD), variance, coefficient of variation (CV), skewness, 5th, 10th, 25th, 95th and 99th percentiles were statistically significantly different between groups (P=0.000-0.040). Multivariate logistic regression analysis showed that age, percentage of unenhanced tumor area, SD and CV were independent risk factors for predicting pTERT mutation status in GBM patients. The logistic regression model based on these four features showed a better sample predictive performance, and the area under the curve (AUC) [95% confidence interval (CI)], accuracy, sensitivity, specificity were 0.842 (0.767-0.917), 0.796, 0.820, and 0.729, respectively. There were no significant differences in the T1C histogram parameters between the C228T and C250T groups (P=0.055-0.854). T1C histogram parameters can be used to evaluate pTERT mutations status in GBM. A nomogram based on conventional MRI features and T1C histogram parameters is a reliable tool for the pTERT mutation status, allowing for non-invasive radiological prediction before surgery.

A Characteristic Magnetic Resonance Imaging Finding to Identify Morton Neuroma: The Slug Sign.

Morton neuroma is a common cause of forefoot pain and sensory disturbances, but it is difficult to identify on magnetic resonance imaging (MRI). The aim of this study was to verify the usefulness of a characteristic MRI finding (slug sign) for identifying Morton neuroma and to clarify the relationship between excised neuroma characteristics and preoperative MRI findings. Twenty-two web spaces were retrospectively assessed from the second and third intermetatarsal spaces of 11 feet of 10 patients (7 women and 3 men, aged average 59.5 years) who underwent surgical excision of Morton neuroma between 2017 and 2022. Asymptomatic web spaces were used as control. Neuromas with 2 branches of the plantar digital nerves on axial T1-weighted MRI (MRI-T1WI) were considered the slug sign. We investigated the preoperative presence of the slug sign in Morton neuroma and asymptomatic control web spaces. We also investigated the relationship between the maximum transverse diameter of the excised specimen and that estimated on coronal MRI-T1WI. A total of 15 Morton neuromas were excised and assessed. The slug signs were present in 10 intermetatarsal spaces in 15 web spaces with Morton neuroma whereas the sign was found in 1 intermetatarsal space in 7 asymptomatic web spaces. The sensitivity and specificity for the slug sign to diagnose Morton neuroma was 66.7% and 85.7%, respectively. The positive and negative predictive values were 90.9% and 54.5%, respectively. The mean maximum transverse diameter of excised neuromas was 4.7 mm. The mean maximum transverse diameter of neuromas on coronal MRI-T1WI was 3.4 mm. A significant positive correlation was found between the maximum transverse diameters of excised specimens and diameters estimated on coronal MRI-T1WI (r = 0.799, P < .001). The slug sign may be a useful indicator of Morton neuroma on MRI to confirm nerve involvement after bifurcation. Level IV, retrospective series.

The association of magnetic resonance imaging features with five molecular subtypes of breast cancer

ObjectiveTo identify the association of magnetic resonance imaging (MRI) features with molecular subtypes of breast cancer (BC). Materials and methodsA retrospective study was conducted on 112 invasive BC patients with preoperative breast MRI. The confirmed diagnosis and molecular subtypes of BC were based on the postoperative specimens. MRI features were collected by experienced radiologists. The association of MRI features of each subtype was compared to other molecular subtypes in univariate and multivariate logistic regression analyses. ResultsThe proportions of luminal A, luminal B HER2-negative, luminal B HER2-positive, HER2-enriched, and triple-negative BC were 14.3 %, 52.7 %, 12.5 %, 10.7 %, and 9.8 %, respectively. Luminal A was associated with hypo-isointensityon T2-weighted images (OR=6.214, 95 % CI: 1.163–33.215) and non-restricted diffusion on DWI-ADC (OR=6.694, 95 % CI: 1.172–38.235). Luminal B HER2-negative was related to the presence of mass (OR=7.245, 95 % CI: 1.760–29.889) and slow/medium initial enhancement pattern (OR=3.654, 95 % CI: 1.588–8.407). There were no associations between MRI features and luminal B HER2-positive. HER2-enriched tended to present as non-mass enhancement lesions (OR=20.498, 95 % CI: 3.145–133.584) with fast uptake in the initial postcontrast phase (OR=9.788, 95 % CI: 1.689–56.740), and distortion (OR=11.471, 95 % CI: 2.250–58.493). Triple-negative were associated with unifocal (OR=7.877, 95 % CI: 1.180–52.589), hyperintensityon T2-weighted images (OR=14.496, 95 % CI: 1.303–161.328), rim-enhanced lesions (OR=18.706, 95 % CI: 1.915–182.764), and surrounding tissue edema (OR=5.768, 95 % CI: 1.040–31.987). ConclusionEach molecular subtype of BC has distinct features on breast MRI. These characteristics can serve as an adjunct to immunohistochemistry in diagnosing molecular subtypes, particularly in cases, where traditional methods yield equivocal results.

Implications of unconventional histological subtypes on magnetic resonance imaging and oncological outcomes in patients who have undergone radical prostatectomy

The prognostic significance of unconventional histology (UH) subtypes including intraductal carcinoma of the prostate (IDC-P), ductal adenocarcinoma, and cribriform pattern has been investigated for prostate cancer (PCa). However, little is known about magnetic resonance imaging (MRI) features and the oncological impact of tumor localization in localized PCa with UH. Clinical data of 211 patients with acinar adenocarcinoma (conventional histology [CH]) and 82 patients with UH who underwent robotic-assisted radical prostatectomy (RARP) were reviewed. Patients with UH are more likely to be older and have higher Gleason grade group, higher Prostate Imaging-Reporting and Data System (PI-RADS) v2.1 score, and larger tumor volume (TV) than those with CH. Multivariate analysis identified the presence of UH as an independent prognostic factor for progression-free survival (PFS) (hazard ration (HR) 2.41, 95% confidence interval (CI) 0.22–0.79, P = 0.0073). No significant difference in PFS was seen regarding tumor localization (transition zone [TZ] or peripheral zone [PZ]) in patients with UH (P = 0.8949), whereas PZ cancer showed shorter PFS in patients with CH (P = 0.0174). PCa with UH was associated with higher progression than PCa with CH among resection margin (RM)-negative cases (P < 0.0001). Further, increased PI-RADS v2.1 score did not correlate with larger TV in UH (P = 0.991), whereas a significant difference in TV was observed in CH (P < 0.0001). The prognostic significance of UH tumor was independent of tumor localization, and shorter PFS was observed even in RM-negative cases, indicating an aggressive subtype with micro-metastatic potential. Furthermore, UH tumors are more likely to harbor a large TV despite PI-RADS v2.1 score ≤ 3. These findings will help optimal perioperative management for PCa with UH.

High bioavailable testosterone levels increase the incidence of isolated REM sleep behavior disorder: Results from multivariable and network Mendelian randomization analysis

ObjectivesTo explore the causal relationships between sex hormone levels and incidence of isolated REM sleep behavior disorder (iRBD). MethodsIn our study, we utilized Genome-Wide Association Studies (GWAS) data for iRBD, including 9447 samples with 1061 cases of iRBD provided by the International RBD Study Group. Initially, we conducted a two-sample univariate MR analysis to explore the impact of sex hormone-related indicators on iRBD. This was followed by the application of multivariable MR methods to adjust for other hormone levels and potential confounders. Finally, we undertook a network MR analysis, employing brain structure Magnetic Resonance Imaging (MRI) characteristics as potential mediators, to examine whether sex hormones could indirectly influence the incidence of iRBD by affecting brain structure. ResultsBioavailable testosterone (BioT) is an independent risk factor for iRBD (Odds Ratio [95 % Confidence Interval] = 2.437 [1.308, 4.539], P = 0.005, corrected-P = 0.020), a finding that remained consistent even after adjusting for other sex hormone levels and potential confounders. Additionally, BioT appears to indirectly increase the risk of iRBD by reducing axial diffusivity and increasing the orientation dispersion index in the left cingulum and cingulate gyrus. ConclusionsOur research reveals that elevated levels of BioT contribute to the development of iRBD. However, the specific impact of BioT on different sexes remains unclear. Furthermore, high BioT may indirectly lead to iRBD by impairing normal pathways in the left cingulum and cingulate gyrus and fostering abnormal pathway formation.

Diagnostic accuracy of ultrasound and MR imaging in peroneal neuropathy: A prospective, single-center study.

Magnetic resonance imaging (MRI) findings in peroneal neuropathy are not well documented and the prognostic value of imaging remains uncertain. Upper limits of cross-sectional area (CSA) on ultrasound (US) have been established, but uncertainty regarding generalizability remains. We aimed to describe MRI findings of the peroneal nerve in patients and healthy controls and to compare these results to US findings and clinical characteristics. We prospectively included patients with foot drop and electrodiagnostically confirmed peroneal neuropathy, and performed clinical follow-up, US and MRI of both peroneal nerves. We compared MRI findings to healthy controls. Two radiologists evaluated MRI features in an exploratory analysis after images were anonymized and randomized. Twenty-two patients and 38 healthy controls were included. Whereas significant increased MRI CSA values were documented in patients (mean CSA 20 mm2 vs. 13 mm2 in healthy controls), intra- and interobserver variability was substantial (variability of, respectively, 7 and 9 mm2 around the mean in 95% of repeated measurements). A pathological T2 hyperintense signal of the nerve was found in 52.6% of patients (50% interobserver agreement). Increased CSA measurements (MRI/US), pathological T2 hyperintensity of the nerve and muscle edema were not predictive for recovery. Imaging is recommended in all patients with peroneal neuropathy to exclude compressive intrinsic and extrinsic masses but we do not advise routine MRI for diagnosis or prediction of outcome in patients with peroneal neuropathy due to high observer variability. Further studies should aim at reducing MRI observer variability potentially by semi-automation.

Evaluation of machine learning-based classification of clinical impairment and prediction of clinical worsening in multiple sclerosis

BackgroundRobust predictive models of clinical impairment and worsening in multiple sclerosis (MS) are needed to identify patients at risk and optimize treatment strategies.ObjectiveTo evaluate whether machine learning (ML) methods can classify clinical impairment and predict worsening in people with MS (pwMS) and, if so, which combination of clinical and magnetic resonance imaging (MRI) features and ML algorithm is optimal.MethodsWe used baseline clinical and structural MRI data from two MS cohorts (Berlin: n = 125, Amsterdam: n = 330) to evaluate the capability of five ML models in classifying clinical impairment at baseline and predicting future clinical worsening over a follow-up of 2 and 5 years. Clinical worsening was defined by increases in the Expanded Disability Status Scale (EDSS), Timed 25-Foot Walk Test (T25FW), 9-Hole Peg Test (9HPT), or Symbol Digit Modalities Test (SDMT). Different combinations of clinical and volumetric MRI measures were systematically assessed in predicting clinical outcomes. ML models were evaluated using Monte Carlo cross-validation, area under the curve (AUC), and permutation testing to assess significance.ResultsThe ML models significantly determined clinical impairment at baseline for the Amsterdam cohort, but did not reach significance for predicting clinical worsening over a follow-up of 2 and 5 years. High disability (EDSS ≥ 4) was best determined by a support vector machine (SVM) classifier using clinical and global MRI volumes (AUC = 0.83 ± 0.07, p = 0.015). Impaired cognition (SDMT Z-score ≤ −1.5) was best determined by a SVM using regional MRI volumes (thalamus, ventricles, lesions, and hippocampus), reaching an AUC of 0.73 ± 0.04 (p = 0.008).ConclusionML models could aid in classifying pwMS with clinical impairment and identify relevant biomarkers, but prediction of clinical worsening is an unmet need.

Clinical outcomes following transtibial medial meniscal root repair are maintained at long-term follow-up.

To evaluate long-term outcomes of patients treated with posterior medial meniscal root tear (PMMRT) repair through assessment of functional outcome scores and to identify patient surgical and magnetic resonance imaging (MRI) characteristics associated with improved outcomes. This was a single-centre, retrospective study evaluating patients who had undergone a PMMR repair using a transtibial suture pullout technique with two locking cinch sutures. This was performed as a follow-up to previously published 2-year and 5-year outcome studies, using the same cohort. All patients from the prior short-term and midterm studies were invited to participate. Patient-reported outcome (PROs) scores, including the International Knee Documentation Committee (IKDC) and Lysholm scores, were collected. Previously collected demographic data were updated based on review of the electronic medical record. Patient outcomes were assessed preoperatively, as well as at 2-year, 5-yearand 8-yearpostoperatively. MRI outcome measurements were assessed at 2-year and 5-year follow-ups. All statistical analysis was performed using SPSS version 26. Seventeen patients of the original 18 patients (94.4%) were included in the final analysis. Additionally, three patients who had additional ipsilateral surgery were excluded from the analysis of PROs. The IKDC score significantly increased from 44.7 ± 11.6 at preoperative baseline to 71.2 ± 21.3 at 8-yearpost-operation (p = 0.001). There were no significant differences in IKDC score between 2-year and 8-year follow-ups (p = n.s.) or 5-year and 8-year follow-ups (p = n.s.). The Lysholm score significantly increased from 49.6 ± 7.3 at preoperative baseline to 76.4 ± 17.2 at 8-year follow-up (p < 0.001). There was no significant difference in Lysholm scores between 2-year and 8-year follow-ups (p = n.s.) or 5-year and 8-year follow-ups (p = n.s.). A linear regression analysis found that 5-year IKDC scores were significantly correlated with 8-year IKDC scores (β = 0.681, p = 0.038). At 8-year follow-up, four (23.5%) patients required additional procedures on their operative knee (one total knee arthroplasty conversion). Patients treated with repair of PMMRT had maintenance of clinical outcome improvements at long-term follow-up despite worsening MRI outcomes at short-term and medium-term follow-ups. While a high proportion of patients required additional procedures on their operative knee at 8-yearfollow-up, few of these patient's additional procedures were related to failure of their primary surgery. Providers and patients may expect durable clinical outcomes following the repair of PMMRT, irrespective of radiographic appearance. Level IV.

A review of graph theory-based diagnosis of neurological disorders based on EEG and MRI

Graph theory analysis, as a mathematical tool, has been widely employed in studying the connectivity of the brain to explore the structural organization. Through the computation of graph theory metrics, it can effectively reveal the nonlinear and complex behavioral features of neuroimaging data, e.g., Electroencephalogram (EEG) and Magnetic Resonance Imaging (MRI), which are often challenging to interpret using simple linear methods. Graph neural networks (GNNs), employing deep learning, offer a more flexible approach to handling large-scale, high-dimensional brain network data. This review aims to investigate the applications of graph theory and Graph Neural Networks in the diagnosis of neurological disorders. The complexity and multi-level features of neurological disorders pose challenges for traditional methods in addressing such issues. The paper begins by introducing the fundamental principles of graph theory and GNNs, elucidates the mechanisms behind diagnosis process using these methods, and then provides a comprehensive overview of their specific applications. Finally, it discusses and summarizes the current challenges in this research field, proposing future directions for development. In conclusion, this review provides a thorough theoretical foundation and methodological insight for exploring the potential applications of graph theory and GNNs in the diagnosis of neurological disorders.

Meningioma grading via diagnostic imaging: A systematic review and meta-analysis

PurposeMeningioma is the most common intracranial tumor, graded on pathology using WHO criteria to predict tumor course and treatment. However, pathological grading via biopsy may not be possible in cases with poor surgical access due to tumor location. Therefore, our systematic review aims to evaluate whether diagnostic imaging features can differentiate high grade (HG) from low grade (LG) meningiomas as an alternative to pathological grading.MethodsThree databases were searched for primary studies that either use routine magnetic resonance imaging (MRI) or computed tomography (CT) to assess pathologically WHO-graded meningiomas. Two investigators independently screened and extracted data from included studies.Results24 studies met our inclusion criteria with 12 significant (p < 0.05) CT and MRI features identified for differentiating HG from LG meningiomas. Cystic changes in the tumor had the highest specificity (93.4%) and irregular tumor-brain interface had the highest positive predictive value (65.0%). Mass effect had the highest sensitivity (81.0%) and negative predictive value (90.7%) of all imaging features. Imaging feature with the highest accuracy for identifying HG disease was irregular tumor-brain interface (79.7%). Irregular tumor-brain interface and heterogenous tumor enhancement had the highest AUC values of 0.788 and 0.703, respectively.ConclusionOur systematic review highlight imaging features that can help differentiate HG from LG meningiomas.

Thoracolumbar hydrated nucleus pulposus extrusion and intervertebral disc extrusion in dogs: Comparison of clinical presentation and magnetic resonance imaging findings

Thoracolumbar hydrated nucleus pulposus extrusion (TL-HNPE) is an increasingly recognised pathology with a substantial lack of literature describing its features. The aim of this retrospective case-control study was to analyse the clinical and magnetic resonance imaging (MRI) features of dogs with TL-HNPE compared to dogs affected with thoracolumbar intervertebral disc extrusion (TL-IVDE). Data from dogs diagnosed with TL-HNPE and TL-IVDE via MRI at two referral hospitals, were retrospectively collected and compared in terms of clinical signs and MRI features. Cases diagnosed with TL-IVDE were deemed controls. The MRI features of the affected IVD space, herniated IVD material, affected overlying spinal cord and local epaxial musculature were evaluated for each group. Fifty-one cases with TL-HNPE and 105 randomly selected cases of TL-IVDE were included. Several signalment and neurological signs were identified as statistically distinct between groups in univariate analysis. Multivariate analysis identified that dogs affected with TL-HNPE were typically older, less likely to be chondrodystrophic (62.2 % vs. 91 %), more frequently experiencing a peracute onset (90.2 % vs. 61.9 %) often attributed to a suspected trauma linked with exercise (37.3 % vs. 10.5 %), being less frequently progressive (41.2 % vs. 86.5 %) and with herniated disc material less frequently lateralised (72.6 % vs. 89.5 %) than cases with TL-IVDE. MRI-identifiable intervertebral disc degeneration was found in every TL-IVDE case but only in 60 % of TL-HNPE cases. TL-HNPEs were associated to significantly less spinal cord compression and less hyperalgesia than TL-IVDE.

Radiomic analysis based on magnetic resonance imaging for the prediction of VEGF expression in hepatocellular carcinoma patients

ObjectiveThe purpose of this study was to investigate the ability of radiomic characteristics of magnetic resonance images to predict vascular endothelial growth factor (VEGF) expression in hepatocellular carcinoma (HCC) patients.MethodsOne hundred and twenty-four patients with HCC who underwent fat-suppressed T2-weighted imaging (FS-T2WI) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) one week before surgical resection were enrolled in this retrospective study. Immunohistochemical analysis was used to evaluate the expression level of VEGF. Radiomic features were extracted from the axial FS-T2WI, DCE-MRI (arterial phase and portal venous phase) images of axial MRI. Least absolute shrinkage and selection operator (LASSO) and stepwise regression analyses were performed to select the best radiomic features. Multivariate logistic regression models were constructed and validated using tenfold cross-validation. Receiver operating characteristic (ROC) curve analysis, calibration curve analysis and decision curve analysis (DCA) were employed to evaluate these models.ResultsOur results show that there were 94 patients with high VEGF expression and 30 patients with low VEGF expression among the 124 HCC patients. The FS-T2WI, DCE-MRI and combined MRI radiomics models had AUCs of 0.8713, 0.7819, and 0.9191, respectively. There was no significant difference in the AUC between the FS-T2WI radiomics model and the DCE-MRI radiomics model (p > 0.05), but the AUC for the combined model was significantly greater than the AUCs for the other two models (p < 0.05) according to the DeLong test. The combined model had the greatest net benefit according to the DCA results.ConclusionThe radiomic model based on multisequence MR images has the potential to predict VEGF expression in HCC patients. The combined model showed the best performance.Graphical

Vanishing white matter disease: imaging, clinical and molecular correlation in Brazilian families.

To characterize Vanishing White Matter Disease (VWM) cases from a Brazilian University Tertiary hospital, focusing on brain magnetic resonance image (MRI) aspects, clinical and molecular data. Medical records and brain MRI of 13 genetically confirmed VWM patients were reviewed. Epidemiological data such as age at symptom onset, gender and main symptoms were analyzed, along with genetic mutations and MRI characteristics, such as the distribution of white matter lesions and atrophy. The majority of patients were female, with the age of symptom onset ranging from 1year and 6months to 40years. All mutations were identified in the EIF2B5 gene, the most prevalent being c.338G > A (p.Arg113His), and a novel mutation related to the disease was discovered, c.1051G > A (p.Gly351Ser). Trauma or infection were significant triggers. The most frequent symptoms were ataxia and limb spasticity. All MRI scans displayed deep white matter involvement, cystic degeneration, with U-fibers relatively spared and a predilection for the frontoparietal region. Lesions in the corpus callosum and posterior fossa were present in all patients. Follow-up exams revealed the evolution of white matter lesions and cerebral atrophy, which correlated with clinical deterioration. VWM affects various age groups, with a significant clinical and genetic variability. A novel mutation associated with the disease is highlighted. MRI reveals a typical pattern of white matter involvement, characterized by diffuse lesions in the periventricular and deep regions, with subsequent extension to the subcortical areas, accompanied by cystic degeneration, and plays a crucial role in diagnosis and follow-up.

IMG-02. USING MRI RADIOMICS AND MACHINE LEARNING TO PREDICT OVERALL SURVIVAL FOR PEDIATRIC DIFFUSE MIDLINE GLIOMAS

Abstract BACKGROUND Pediatric diffuse midline gliomas (DMG) are aggressive central nervous system tumors with a median overall survival (OS) of less than one year from diagnosis. There is no curative therapy for DMG, and radiation therapy (RT) is the standard treatment. Magnetic resonance imaging (MRI) is the common noninvasive tool for DMG diagnosis and monitoring of tumor response to therapy. We developed an automatic pipeline to segment subregions of DMG and select MRI features that predict patient OS. METHODS We acquired diagnostic and post-RT multisequence MRI (T1, T1ce, T2, T2 FLAIR) and manual segmentations of pediatric DMG patients from two centers: 53 from Children’s National Hospital (internal) and 16 from Children’s Hospital of Philadelphia (external). We pretrained a deep learning model on a public adult brain tumor dataset, and finetuned the model to segment tumor core (TC) and whole tumor (WT) of DMG. We used PyRadiomics and sequential feature selection to select discriminative features based on the segmented volumes. Two machine learning models were trained on our internal cohort to predict patient 1-year survival from diagnosis. One model used only diagnostic tumor features and the other used both diagnostic and post-RT features. RESULTS For segmentation, Dice score (mean [median]±SD) was 0.91 (0.94)±0.12 and 0.74 (0.83)±0.32 for TC, and 0.88 (0.91)±0.07 and 0.86 (0.89)±0.06 for WT for internal and external cohorts, respectively. For OS prediction, accuracy was 77% and 81% at time of diagnosis, and 85% and 78% post-RT for internal and external cohorts, respectively. Heterogeneous WT intensity in baseline T2 FLAIR and smaller post-RT TC/WT volume ratio indicate longer OS. CONCLUSIONS Our method accurately predict OS for DMG patients and can be extended to other rare pediatric brain tumors. With automated and standardized analysis, early prognostication of OS can guide patient risk stratification and clinical decisions.

High pulse wave velocity is associated with enlarged perivascular spaces in dementia with Lewy bodies

Previous studies have demonstrated associations between enlarged perivascular spaces (EPVS) and dementias such as Alzheimer’s disease. However, an association between EPVS and dementia with Lewy bodies (DLB) has not yet been clarified. We performed a cross-sectional analysis of our prospective study cohort of 109 participants (16 with DLB). We assessed cognitive function, pulse wave velocity (PWV), and brain magnetic resonance imaging features. The relationships between EPVS and DLB were evaluated using multivariable logistic regression analyses. Compared with the non-dementia group, the DLB group was more likely to have EPVS in the basal ganglia. Compared with participants without EPVS, those with EPVS were older and had cognitive impairment and high PWV. In multivariable analyses, EPVS in the basal ganglia was independently associated with DLB. High PWV was also independently associated with EPVS in both the basal ganglia and centrum semiovale. High PWV may cause cerebrovascular pulsatility, leading to accelerated EPVS in DLB participants.

Magnetic Resonance Imaging Features of Anterolateral Ligament in Young Adults without Anterior Cruciate Ligament Injury: Preliminary Evaluation.

This study aimed to characterize the Magnetic Resonance Imaging (MRI) features of the Anterolateral Ligament (ALL) in young adults without Anterior Cruciate Ligament (ACL) injury and evaluate its visibility using MRI. In this retrospective analysis, MRI scans of 66 young adults without ACL injuries were assessed by two radiologists. The ALL was examined from its bone-to-bone attachment between the lateral femoral epicondyle and the lateral tibia. The visibility of the ALL was classified as normal, probably normal, abnormal, or non-visualized, based on ligament continuity and thickness relative to the Meniscotibial Ligament (MTL). A continuous structure with thickness equal to or greater than the MTL was considered normal; continuous but wavy and thin features were categorized as probably normal; discontinuity and angulation were deemed abnormal. The proximal attachment of the ALL was categorized as anterior, central, or posterior to the Fibular Collateral Ligament (FCL), while the distal attachment was noted as either at the same location or distal to the MTL. The ALL was identified in 87.9-95.5% of knees and was non-visualized in 4.5-12.1% of cases. Continuous ligamentous structures were observed in 63.7-71.2% of knees (normal in 30.3-37.9%; probably normal in 27.3-40.9%), whereas 19.7-30.3% exhibited abnormal features. Inter-observer agreement was moderate to substantial (κ = 0.66, 0.56), and intra-observer agreement was substantial to excellent (κ = 0.82, 0.66). Among the 58 visible ALLs, proximal attachments were predominantly anterior (63.8%) or central (32.8%) to the FCL, with a minority posterior (1.7%). In total, 4 of the 19 central insertions were incorporated into the FCL mid-substance, and one case was blended into the meniscofemoral ligament. Distal attachments were equally distributed between the same location (50%) and distal to the MTL (50%) (mean 3.7 mm distal). In conclusion, MRI was feasible for detecting the ALL in most young adults without ACL injury, revealing continuous ligament structures in about two-thirds of cases. Approximately 40% of cases exhibited a thickness equal to or greater than the MTL, with the majority of proximal attachments located anterior to the FCL and distal attachments evenly divided between the same insertion and distal to the MTL.

Long-term outcomes of ADEM-like and tumefactive presentations of CNS demyelination: a case-comparison analysis

A minority of initial multiple sclerosis (MS) presentations clinically or radiologically resemble other central nervous system (CNS) pathologies, acute disseminated encephalomyelitis (ADEM) or tumefactive demyelination (atypical demyelination presentations). With the aim of better defining the long-term outcomes of this group we have performed a retrospective cohort comparison of atypical demyelination versus ‘typical’ MS presentations. Twenty-seven cases with atypical presentations (both first and subsequent demyelinating events) were identified and compared with typical MS cases. Disease features analysed included relapse rates, disability severity, whole brain and lesion volumes, lesion number and distribution. Atypical cases represented 3.9% of all MS cases. There was considerable overlap in the magnetic resonance imaging (MRI) features of ADEM-like and tumefactive demyelination cases. ADEM-like cases tended to be younger but not significantly so. Atypical cases showed a trend towards higher peak expanded disability severity score (EDSS) score at the time of their atypical presentation. Motor, cranial nerve, cerebellar, cerebral and multifocal presentations were all more common in atypical cases, and less likely to present with optic neuritis. Cerebrospinal fluid (CSF) white cell counts were higher in atypical cases (p = 0.002). One atypical case was associated with peripheral blood myelin oligodendrocyte glycoprotein (MOG) antibodies, but subsequent clinical and radiological course was in keeping with MS. There was no difference in long-term clinical outcomes including annualised relapse rates (ARR), brain volume, lesion numbers or lesion distributions. Atypical demyelination cases were more likely to receive high potency disease modifying therapy early in the course of their illness. Despite the severity of initial illness, our cohort analysis suggests that atypical demyelination presentations do not confer a higher risk of long-term adverse outcomes.